ABRACADABRA Labs Resource directory

Full index · 221 links

Everything, in one table

Sortable and filterable with JavaScript on; a complete, readable table with it off. On narrow screens each row collapses into a stacked record. Every entry has a permalink here — the # at the end of its row.

A dash in the Year column is deliberate. Repositories, people, conference series and trackers have no publication year, so they carry none rather than being stamped with the year I happened to check them. They sort as undated.

All 221 entries, alphabetical by title. Last reviewed 2026-11-18.
Title and annotationAuthorsYearTypeAccessTopicCitation
'Virtual' Disenfranchisement: Cyber Election Meddling in the Grey Zones of International Law
Distinguishes lawful overt propaganda from covert troll operations that disguise their source; argues concealing origin can breach sovereignty and may be coercive because voters cannot evaluate the information.
Schmitt, M. N. 2018 Paper Open Deception Law
"Deepfakes" and the Law of Armed Conflict: Are They Legal?
Concludes deepfakes are lawful as ruses but unlawful when perfidious (e.g., fake surrender used to attack) or when they spread terror among civilians or breach protective obligations.
Jensen, E. T.; Crockett, S. 2020 Blog Open Deception Law
0x4D31/deception-as-detection
Crosswalk from deception-based detections to ATT&CK techniques across Windows, Linux and macOS, with a worked deception story for each. MIT. Dormant for years, and nothing has replaced the mapping.
Karimi, A. — Tool Open Deception
0x4D31/galah
LLM-powered web honeypot: generates a plausible HTTP response to whatever arrives instead of emulating fixed applications. Go, Apache-2.0.
Karimi, A. — Tool Open Deception, Attackers
9.66J Computational Cognitive Science
Background rather than quantum cognition: the Bayesian modelling tradition that quantum accounts define themselves against, without which the arguments are hard to follow. Notes, readings, projects. CC BY-NC-SA, and twenty years old.
Tenenbaum, J. B. 2004 Course Open Quantum cognition
A 4-Month Dataset of SSH Botnet Interactions and Command Payloads
145,425 events from an SSH honeypot over four months. Command payloads, credential patterns, attack sequences. CC BY 4.0.
Boiko, V.; Niiakyi, O. 2026 Dataset Open Deception
A Comparative Study of Domestic Laws Constraining Private Sector Active Defense Measures in Cyberspace
Surveys 20 countries' laws on private active defense; analyzes honeypots and beacons, noting honeypots may implicate trap-and-trace prohibitions in many jurisdictions.
Corcoran, B. 2020 Paper Open Deception Law
A comprehensive survey on cyber deception techniques to improve honeypot performance
Open-access survey classifying techniques as advanced mimicking, fake cooperation and honeytoken bait, and proposing evaluation metrics plus a mathematical model for honeynet design. More current than Han et al.
Javadpour, A. et al. 2024 Survey / SoK Open Deception
A Cyber+Human Data Windfall to Revolutionize Cyberpsychology, Predictive Modeling, and Cyber Defense
Overview of IARPA's ReSCIND programme, in which five teams spent 18 months testing whether attackers' cognitive biases can be measured and exploited. Over 2,300 participants from 59 countries took part, more than 450 of them cyber experts, with linked psychometric and host/network data released through IARPA. The claim that attack behaviour can be steered summarises the teams' own papers, where the effect sizes sit, and most participants were not professionals. Written by the programme's managers and paywalled; read with iarpa-rescind.
Ferguson-Walter, K. J. et al. 2026 Paper Paywalled Deception
A Digital Emblem for Cyber Conflicts: Making Humanitarian Protection Machine-Readable
Addresses spoofing of a machine-readable emblem (attackers faking marks to shield offensive infrastructure) and proposes PKI-anchored authentication; cites Tallinn Manual 2.0 that perfidy and emblem abuse are prohibited online.
Llamas Covarrubias, J. Z. 2025 Report Open Deception Law
A formulation of computational trust based on quantum decision theory
Splits trust into objective and subjective components and uses interference terms to model how evaluations shift between isolated and comparative judgment. One of very few quantum-cognition papers aimed at a security-adjacent problem.
Ashtiani, M.; Azgomi, M. A. 2016 Paper Paywalled Quantum cognition, Deception
A Hybrid-Simulation LoRaWAN Honeypot for Detecting RF and Protocol Attacks Against IoT Networks: A Cyber-Electromagnetic Activities Perspective
Hybrid-simulation honeypot for LoRaWAN that instruments the radio side as well as the protocol layer, aimed at RF and protocol attacks on low-power wide-area IoT networks. Whether evaluation used live RF traffic or simulation alone is the point to check before citing it. Springer CCIS chapter;. Read after guan-2025-iot-honeypots.
Al-Mehaizaa, A. et al. 2026 Paper Paywalled Deception
A Review of Honeypots: Fingerprinting Techniques, Detection, and Evasion Mechanisms
The counter-deception side: how attackers fingerprint honeypots through behavioural and protocol tells, and how weak existing anti-fingerprinting defenses are. The corrective to optimistic deployment literature.
Chaudhry, A. et al. 2026 Survey / SoK Open Deception
A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes
Covers both directions of agentic AI in security and names systemic risks specific to agents: collusion between them, cascading failure, oversight evasion and memory poisoning. Preprint, with working prototypes included.
Lazer, S. J. et al. 2026 Survey / SoK Open Attackers
A Virtual Honeypot Framework
Honeyd: simulating whole virtual hosts at the network level so one machine can present thousands. The foundational low-interaction honeypot paper, and still the mental model most tooling inherits.
Provos, N. 2004 Paper Open Deception
Active Defense and Deception Technology Against Insider Threats: A Serverless and Cryptographically Verifiable Framework
Serverless cloud framework that plants generated honeyfiles, honeytokens and tracking beacons in PDF, DOCX and XLSX files to catch insiders, then revokes their cloud access automatically. In an emulated AWS setup it raised no alerts on 500 benign events from six simulated employees and issued revocations in about 2.2 seconds over 11 warm trials. The 100% detection claim rests on the authors' own scripted attacks with no trial count given, and Microsoft Word blocked the beacons. Peer reviewed in MDPI Informatics.
Zichella, L. P. et al. 2026 Paper Open Deception
Addressing the Gray Zone Between the Law of War and Information Operations
Information operations usually fall below the 'attack' threshold and are permitted; proposes prohibiting civilian-directed IO that threatens survival and is excessive relative to military advantage.
Wofford, K. 2025 Paper Open Deception Law
Advanced tools and concepts for quantum cognition: A tutorial
The formal machinery worked through: POVMs, temporal Bell inequalities, model comparison. Free accepted version in City's repository. For building models, not reading about them.
Yearsley, J. M. 2017 Course Open Quantum cognition
Adversarial Misuse of Generative AI
GTIG's January 2025 baseline on APT and information-operations use of Gemini, concluding threat actors gained speed and volume but no new capability. Useful as the deliberately deflationary counterweight to later autonomy claims.
Google Threat Intelligence Group 2025 Report Open Attackers
Adversary Village at DEF CON
DEF CON community track on adversary simulation, emulation tactics and purple teaming. The programme page links no recordings at all, so it is hard to follow remotely.
Adversary Village — Venue Open Attackers, Deception
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
Ninety-seven realistic agent tasks paired with 629 security test cases, built so attacks and defenses can be swapped independently — which is what makes it reusable rather than a one-off result. The standard reference environment for agent hijacking work.
Debenedetti, E. et al. 2024 Dataset Open Attackers
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
Threat taxonomy for agents acting across digital and physical environments, with a review of evaluation methods and both technical and governance defenses. Revised through April 2026; still a preprint.
Chhabra, A. et al. 2025 Survey / SoK Open Attackers
AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents
An LLM-driven honeypot endpoint that adapts its responses to an attacking agent and escalates to asking for the agent's own API key. Tested against eight open-source pentest agents with two models each, on a single SQL-injection target at three runs per configuration. Real-target success falls only from 95.8% to 79.2%, and keys leak in 18.8% of runs, all from CAI and PentestAgent. Other agents' models refused, or Strix's sandboxing blocked the leak. A four-page unreviewed preprint.
Wang, Y. et al. 2026 Paper Open Deception, Attackers
agmi: Agent Memory Integrity, a conformance test suite for tamper evidence in AI agent memory and checkpoint stores
Conformance suite testing whether AI agent memory and checkpoint stores reveal tampering. Release 0.6.3 runs nine storage-level edits against sixteen stores, eight of which claim tamper evidence, with a control confirming each edit changed only what was intended. The threat model is an attacker with write access to storage, not memory poisoned through the agent's own writes. Single-author Zenodo release, not peer reviewed.
Khandelwal, Y. — Tool Open Attackers
AI as tradecraft: How threat actors operationalize AI
Two years on from the 2024 baseline: AI embedded across phishing, malware development and post-compromise work, while humans keep targeting decisions. Notes DPRK use of fabricated identities for employment fraud.
Microsoft Threat Intelligence 2026 Report Open Attackers
AI Cyber Challenge marks pivotal inflection point for cyber defense
DARPA's results announcement. Team Atlanta's system found 54 of 63 synthetic vulnerabilities and patched 43, across 54 million lines of code, and all seven finalist systems were released under OSI-approved licences — which is the part with lasting value, since the systems themselves are now inspectable.
DARPA 2025 Programme Open Attackers
AIRT — AI Red Team Academy
Eight free modules with Docker labs: prompt injection, RAG exploitation, multi-agent attacks, automated red teaming.
Karimi, A. — Course Open Attackers
Amazon Threat Intelligence observes threat actors running cybercrime campaigns with ARTEX AI agents
Amazon's MadPot decoys posed as LLM inference APIs and, from 3 October to 5 November 2026, caught requests from ARTEX agents carrying their own campaign memory. Two campaigns are described, one stealing AI provider keys from exposed gateways to fund more hunting and one building deepfakes to pass exchange identity checks, but no counts of requests, sensors, keys or targets are given. Every outcome is the agents' own claim, which Amazon did not observe and cannot verify. Vendor threat report with indicators.
Moses, C. J. 2026 Report Open Attackers, Deception
An overview of the quantum cognition research program
The most current open-access survey, covering judgment fallacies, concept combination, order effects and memory, and engaging directly with replication failures such as Boyer-Kassem's order-effect results.
Huang, J. et al. 2025 Survey / SoK Open Quantum cognition
AN0M in the High Court – CD v Commonwealth [2025] HCA 37
Explains the High Court's unanimous upholding of legislation retrospectively validating ANOM evidence as an evidentiary provision, not a usurpation of judicial power.
Balani, R. 2026 Blog Open Deception Law
APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry
Benchmark for LLM agents doing SOC-style APT investigation: 370 cases built from 56 report-informed attack reconstructions (16.4 million synthetic log records generated with Cisco Talos's EvidenceForge) under seven telemetry conditions. Across eleven models, agents acquire sufficient evidence for 44.3% of recoverable attack actions but cite it for only 25.0%. Endpoint-only telemetry cuts coverage by just 1.6 points while 35.5% of previously covered actions lose support. The main study uses 10 of the 56 scenarios; unreviewed preprint.
Wang, Y. et al. 2026 Dataset Open Attackers
Assessing AI-Generated vs. Human-Authored Spear Phishing SMS Attacks: An Empirical Study
Pilot study of 25 participants comparing GPT-4 and student-written phishing SMS, finding 28% versus 21% click intention, a difference the authors themselves call statistically uncertain. Cite it carefully.
Francia, J. et al. 2024 Paper Open Attackers
Auditing Question-Order Effects in Large Language Models with the QQ Equality: Mechanism Characterization and a Saturation Caveat
Takes the parameter-free QQ equality from quantum cognition and applies it to model log-probabilities, finding most item pairs saturate into near-determinism and so cannot support a distribution-level test. The only direct link between these two literatures found.
Kang, P. 2026 Paper Open Quantum cognition, Attackers
Authorities and Legal Considerations for US Cyber and Information Operations in a Contested Environment
Argues LOAC-derived frameworks fit poorly with gray-zone cyber and influence operations; authorities and targeting approaches must differ for influence vs disruption objectives.
Corn, G. 2021 Blog Open Deception Law
AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
Targets post-breach hands-on-keyboard activity rather than initial access, which is the phase most later threat reporting says actually shifted. Written by Microsoft-affiliated authors and still an unreviewed preprint.
Xu, J. et al. 2024 Paper Open Attackers
Avoiding the Pitfalls of Operating a Honeypot
Lawyer's guide: phone-home tech on attackers' systems 'almost certainly' violates CFAA/state laws; honeypot domains risk trademark claims; GDPR/ECPA limit data collection; entrapment concerns may deter prosecution.
Overly, M. 2019 Blog Open Deception Law, Deception
awesome-ai-agent-security
Reading list built around the lethal trifecta framing: MCP CVEs, defensive tooling, documented incidents. A fork with almost no history, so treat the selection as one person's.
Matiny, H. — Tool Open Attackers
beelzebub-labs/beelzebub
Low-code deception runtime, Go, GPL-3.0. The interesting part is the MCP bait tooling: decoys aimed at AI agents rather than human intruders. A commercial product sits on top.
Beelzebub Labs — Tool Open Deception, Attackers
Big Enough to Break Out: Tracking the Rising Capability of LLM Penetration-Testing Agents
Compares a human-in-the-loop pentest harness against a newer autonomous one across three public targets, arguing that planning rather than memory is the current bottleneck. Small sample, September 2026 preprint.
Lovelace, V. et al. 2026 Paper Open Attackers
Black Holes and Open Secrets: The Impact of Covert Action on International Law
Argues covert, unacknowledged state conduct distorts the evidence other states use to form legal judgments and weakens the development of international law. Linked to a Lawfare summary;
Perina, A. H. 2015 Paper Open Deception Law
Botnet Defense under EU Data Protection Law
Analyzes GDPR and ePrivacy constraints on botnet defense, including a dedicated scenario on honeypot use by an ISP and DNS sinkholing by a public authority.
Rataj, P. 2025 Paper Paywalled Deception Law
Building Intrusion Detection Honeypots Training
Twelve-plus hours on HTTP, SSH and RDP honeypots, honey tokens, and the monitoring around them. $497 with the companion book. Listed despite the price because free material at this depth does not appear to exist.
Sanders, C. — Course Paywalled Deception
BypassGym: A Benchmark for Evaluating AI Agents' Endpoint Defense Evasion Capabilities
Benchmark in which an agent receives command-and-control shellcode and must build a loader that runs it on a real Windows endpoint without being stopped by the installed EDR product. Across 90 runs covering five lightweight models, six EDR products and three payloads, 71 succeeded (78.9%), and Windows Defender stopped none of its 15. Each combination ran once, and an injected evasion skill matters: GLM-5.3 Flash fell from 15 to 9 of 18 without it. Unreviewed preprint; code and data are promised only after review.
Yuan, W. et al. 2026 Paper Open Attackers
cage-challenge/CybORG
The environment behind the multinational CAGE Challenges for autonomous cyber defense agents. MIT. Challenge 4 adds multi-agent RL.
TTCP CAGE — Tool Open Attackers
Can quantum probability provide a new direction for cognitive modeling?
The target article that put quantum probability in front of the wider cognitive science community, published with dozens of peer commentaries. The commentaries are where the strongest objections live.
Pothos, E. M.; Busemeyer, J. R. 2013 Paper Paywalled Quantum cognition
Canarytokens
Hosted honeytoken generator, free: files, URLs, credentials, cloud keys that alert when touched.
Thinkst Applied Research — Tool Open Deception
Cheating and Deception
The deception typology cyber work keeps reimporting, often without citing it: masking, repackaging, dazzling, mimicking, inventing, decoying. Predates the field. Strong on structure, thin on evidence.
Bell, J. B.; Whaley, B. 1991 Book Paywalled Deception
Cognitive Bias in High-Stakes Decision-Making with LLMs
BiasBuster, a 16,800-prompt framework for measuring and mitigating cognitive bias in model decisions. Relevant here because deception doctrine assumes exploitable biases; this is the closest thing to an inventory of them in machines.
Echterhoff, J. M. 2024 Paper Open Quantum cognition, Attackers
Concepts and Their Dynamics: A Quantum-Theoretic Modeling of Human Thought
Treats contextuality, interference, entanglement and emergence in concept combination and ties them back to conventional psychological theories of concepts. Author list confirmed from the repository listing, not the arXiv header.
Aerts, D. et al. 2013 Paper Open Quantum cognition
Conference on Applied Machine Learning in Information Security (CAMLIS)
Practitioner venue for applied ML in security; 2024 proceedings open through CEUR-WS. The main site was serving stale cached content when I checked, so use the proceedings link.
CAMLIS — Venue Open Attackers
Container Orchestration Honeypot: Observing Attacks in the Wild
High-interaction honeypot for exposed Docker and Kubernetes endpoints that drew attackers within minutes and produced 94 days of attack data, shared with the community. Free PDF from the authors' lab.
Spahn, N. et al. 2023 Paper Open Deception
CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering
Fits a per-model residual-stream direction and subtracts it from every tool-result token at prefill, with no detector or fine-tuning. Across five open-weights models, AgentDojo compromise falls from 0.10–0.49 to 0.006–0.079 at 93–100% benign utility. An adaptive AutoDojo attacker is held to about a quarter of its undefended success. Parameter manipulation survives: 13 of 18 samples cracked under framing search. The 0/2052 LLMail-Inject result replays attacks tuned against other models. Requires white-box serving; single-author Microsoft preprint.
Russinovich, M. 2026 Paper Open Attackers
cowrie/cowrie
The default SSH and Telnet honeypot. Emulated shell, a proxy mode fronting a real host, an experimental LLM backend. Python, actively developed.
Oosterhof, M. — Tool Open Deception
Cross-Border Data Access and Active Cyber Defense: Assessing Legislative Options for a New International Cybersecurity Rulebook
Treats honeypots/tarpits as low-risk in-network measures and discusses ACDC's beacon carve-out, but argues CLOUD Act-style data access is a better route to attribution than hack-back.
Cook, C. 2018 Paper Open Deception Law
Crossing the Cyber Divide: Sim-to-Sim and Sim-to-Real Transfer for RL Agents
A PPO attacker trained in CyberWheel is transferred zero-shot to NetSecGame, CyberBattleSim and NASim through a kill-chain action/observation wrapper and a domain-adversarial encoder. On NetSecGame the encoder reaches 45.2% wins, no better than the wrapper alone (47.4%). On one CyberBattleSim chain topology it wins all 20 episodes where the wrapper wins none. The sim-to-real claim rests only on action-type divergence from an emulator policy (JS 0.085); actual emulation runs are deferred.
Saika, S. et al. 2026 Paper Open Attackers
Curriculum Vitae for Neil C. Rowe
Naval Postgraduate School; around 300 publications on deception in system defense, fake honeypots, and the ethics of deceptive operations. The CV links straight to full texts, which is why it is here rather than a departmental bio.
Rowe, N. C. — Person Open Deception
CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
Sandboxed reproductions of critical-severity web CVEs with automated success checks. Leading agent frameworks resolved up to 13%. That figure is the most defensible number currently available for end-to-end autonomous exploitation, and it is a long way below what the threat reporting implies.
Zhu, Y. et al. 2025 Dataset Open Attackers
Cybench
Task descriptions across six CTF categories, run instructions, evaluation logs, a frontier-model leaderboard. Start here rather than the paper if you mean to run it.
Zhang, A. K. — Dataset Open Attackers
Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
Forty professional CTF tasks from four competitions, each decomposed into subtasks so partial progress is measurable. The benchmark most frequently cited when labs and AI safety institutes report offensive cyber capability.
Zhang, A. K. et al. 2025 Paper Open Attackers
Cyber deception trials: what we've learned so far
NCSC's December 2025 interim findings, from trials across 121 UK organisations and 14 commercial providers. Deception does surface hidden compromise. It is also not plug-and-play, and needs deliberate configuration to produce anything — which is the finding most vendor material omits.
National Cyber Security Centre 2025 Blog Open Deception
Cyber Deception: Building the Scientific Foundation
Thirteen chapters — adversary modelling, honeypotting, anonymity, forum analysis — assembled as a graduate seminar text. The first serious attempt to give the area a scientific spine.
Jajodia, S. et al. 2016 Book Paywalled Deception
Cyber Deception: Techniques, Strategies, and Human Aspects
Ten chapters across game theory, AI and cognitive science — honeyfiles, ICS deception, breach detection. Two are open; the rest are behind Springer.
Bao, T. et al. 2023 Book Paywalled Deception
Cyber expert feedback: Experiences, expectations, and opinions about cyber deception
Questionnaire study of professional attackers finding they rarely expect deception, and that those who encounter it diverge sharply, some escalating effort and some abandoning it. Useful counterweight to averaged effect sizes.
Ferguson-Walter, K. J. et al. 2023 Paper Paywalled Deception
Cyber Grand Challenge (CGC)
The 2016 competition for machines that find, patch and exploit flaws unaided. It predates LLMs entirely — which is the reason to read it before treating agentic exploitation as new.
DARPA 2016 Programme Open Attackers
Cyber Law Development and the United States Law of War Manual
Reviews the cyber chapter of the DoD Law of War Manual, noting its treatment of improper use of signs and its example that cyber attacks exploiting communications that open non-hostile relations (ceasefires, prisoner exchanges) are prohibited.
Watts, S. 2016 Paper Open Deception Law
Cyber Operations and the New Defense Department Law of War Manual: Initial Impressions
Notes the Manual permits certain deceptions, such as falsely using journalist credentials to feign civilian status for espionage or sabotage, and that such deceptions could readily be done by cyber means, with risks for journalists.
Dunlap Jr., C. J. 2015 Blog Open Deception Law
Cyber Perfidy
Argues malware that masquerades as legitimate civilian software is a form of perfidy that should be prohibited, and proposes international agreements on detection cooperation, attribution and non-perfidious attack methods.
Rowe, N. C. 2013 Paper Open Deception Law
Cyber Perfidy, Ruse, and Deception
Examines how LOAC distinguishes permitted ruses from prohibited perfidy when applied to cyber operations and where the analogy breaks down.
Roff, H. M. 2015 Paper Paywalled Deception Law
Cyber Security Active Defense: Playing with Fire or Sound Risk Management?
Beaconing legality is a gray area; honeypots risk ECPA violations and downstream liability; deception by agents can breach attorney ethics rules (Model Rules 5.3, 8.4).
Harrington, S. L. 2014 Paper Open Deception Law
Cyber threat actors: AI-assisted intrusion research
Account of terminated DPRK-linked accounts researching intrusion tooling, phishing and malware, noting the requests mostly sought publicly available information. A useful deflationary data point against autonomy narratives.
OpenAI 2025 Report Open Attackers
Cyber Weapon Reviews under International Humanitarian Law: A Critical Analysis
Uses weaponized honeypots to illustrate the blurry offensive/defensive line and asks whether adding harmful payloads to decoys makes them weapons requiring legal review.
Wallace, D. 2018 Report Open Deception Law, Deception
Cyber-Physical Deception Through Coordinated IoT Honeypots
Coordinates multiple IoT honeypots so their simulated physical and network dependencies stay consistent under multi-source probing, closing a detection channel single decoys leave open. Free PDF and talk video.
Guan, C.; Cao, G. 2025 Paper Open Deception
CyberLab honeynet dataset
Cowrie captures from ~50 nodes at EU and US universities and companies, May 2019 to February 2020.
Sedlar, U. et al. 2020 Dataset Open Deception
CyberPersistBench: Evaluating LLM-Based Cyber Attackers on Installation and Persistence
Starts agents from a restricted foothold and tests whether they can keep it: 203 tasks over 46 persistence mechanism families on Linux and Windows, scored at six prefix levels from writing the Artifact to surviving a reboot. Five frontier models reach 27.6–42.4% at pass@3, and most failures fall between writing a valid config and getting the host to register it. Native defenses on 128 tasks cut success to 5.5–13.3%, not to zero. The 44.8% scaffold figure excludes tasks refused on safety grounds. Preprint.
Chen, S. et al. 2026 Dataset Open Attackers
Data and code for "Evaluating Chinese Code LLMs for Vulnerability Detection: Realistic Splits, Prompt Strategies, and Cross-Model Comparison"
Archived evaluation of Chinese code LLMs on vulnerability detection: 3,200 raw API responses from 27 July 2026 with corrected verdicts, the JavaVulBench 200-sample probes, an October 2026 refresh grid of four models by four prompt strategies, and a corrected pipeline. This is function-level classification, not autonomous discovery, so it does not bear on zhu-2025-cve-bench numbers. Revision under review at IEEE Access.
Shen, J. et al. 2026 Dataset Open Attackers
Data and materials for: Auditing prompt-only defenses against prompt injection in LLM-assisted scientific review
Data package for an audit of prompt-only defenses against prompt injection in LLM-assisted peer review: a 56,700-row experiment matrix, a held-out bank of 20 attack templates, adaptive-attacker results against three reviewer models, defense baselines including a Prompt-Guard filter-then-review pipeline, and blinded human annotation. The target is a reviewing model, not a tool-using agent. Anonymous authors; companion paper under revision.
Anonymous 2026 Dataset Open Attackers
Deception Techniques in Computer Security: A Research Perspective
Classifies deception along four orthogonal axes: goal, unit, layer, and deployment mode. The cleanest taxonomy in the literature; the ACM version is paywalled, so the authors' copy is linked first.
Han, X. et al. 2018 Survey / SoK Open Deception
Deepfake Fight: AI-Powered Disinformation and Perfidy Under the Geneva Conventions
Analyzes how Geneva Conventions/AP I perfidy rules apply to AI-generated deception in armed conflict and recommends ways to strengthen governance of military deepfakes.
Allen, D. 2022 Paper Open Deception Law
Deepfakes and the Geneva Conventions: Does Deceptive AI-Generated Misinformation Directed at an Enemy During Armed Conflict Violate IHL? A Critical Discussion
Finds deepfakes may be perfidy under AP I art. 37 when they exploit protected status, but the ruse/perfidy line is ambiguous and IHL was not built for synthetic media; reform is needed but unlikely.
Akkuş, B. 2025 Paper Open Deception Law
Deploying AI Systems Securely: Best Practices for Deploying Secure and Resilient AI Systems
Seven-nation joint cybersecurity information sheet: governance, hardened deployment environments, access control, continuous monitoring. Written for operators. Nothing in it addresses offensive agent capability, which is worth knowing before citing it in that context.
NSA Artificial Intelligence Security Center et al. 2024 Standard Open Attackers
Deploying Honeypots and Honeynets: Issue of Privacy
Analyzes what data EU-based honeypot operators may lawfully collect and retain, distinguishing low- vs high-interaction and research vs production honeypots.
Sokol, P. et al. 2015 Paper Paywalled Deception Law, Deception
Deploying Honeypots and Honeynets: Issues of Liability
Examines civil and criminal liability of honeypot/honeynet administrators and the liability of attackers caught by them.
Sokol, P.; Andrejko, M. 2015 Paper Paywalled Deception Law, Deception
Detecting and countering misuse of AI: September 2026
Case studies of actors disrupted between December 2025 and August 2026 across seven harm categories, including cyber espionage and influence operations. Vendor-authored, and covers only misuse of one company's models.
Anthropic 2026 Report Open Attackers
Diederik Aerts
Founding director of CLEA, and the originator of the conceptuality interpretation. The Brussels group puts nearly everything on arXiv.
Aerts, D. — Person Open Quantum cognition
Disinformation and Deepfakes in Conflict: The Neglected Opportunity of the UN OEWG Report
Criticizes the 2025 UN OEWG report for not clarifying how international law (perfidy/ruse, non-intervention, human rights) applies to state disinformation and deepfakes; few states have addressed it.
Gooden, N. 2025 Blog Open Deception Law
Disrupting the first reported AI-orchestrated cyber espionage campaign
Anthropic's account of a campaign it attributes to a Chinese state-sponsored group that drove Claude Code through roughly 80-90% of an intrusion chain against about thirty targets. Vendor-authored and self-reported; no independent corroboration of the attribution.
Anthropic 2025 Report Open Attackers
Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?
AdaLCPI splits an injected instruction into two incomplete fragments buried in filler, plus a generic reconstruction cue, and evolves them with OpenEvolve against the target agent. Across seven models and 81 Email, GitHub and Slack task–objective pairs, 8k-token filler reaches 61.4% macro attack success against 32.8% for a matched explicit-instruction baseline. Fixed fragmentation scores 5.1%, and fragments without filler score 0%. Gains are uneven: GPT-5.6-Luna stays at 8.6%, and TAP does better on Ministral. Each search takes up to 129 black-box runs, and a GPT-4o judge decides success. Preprint.
Lee, M. et al. 2026 Paper Open Attackers
Effectiveness Evaluation Method for Hybrid Defense of Moving Target Defense and Cyber Deception
Combines queuing theory and evolutionary game theory to price security against reliability and overhead when deception and MTD run together. Addresses the cost side that most efficacy work ignores; evaluation is analytical.
Hou, F. et al. 2025 Paper Open Deception
Emerging Need to Regulate Deepfakes in International Law: The Russo–Ukrainian War as an Example
Deepfakes can be lawful ruses under the Geneva Conventions, but IHL is insufficient; proposes protecting 'cognitive liberty' at national and regional level for wartime and peacetime.
Kuźnicka-Błaszkowska, D.; Kostyuk, N. 2025 Paper Open Deception Law
Emerging Technology and Perfidy in Armed Conflict
Applies perfidy rules to emerging technologies including cyber, endorsing Tallinn Manual Rules 60–61 (perfidy prohibited, ruses permitted). Gives examples of cyber perfidy such as falsely claiming to be the ICRC or sending fake surrender messages, while unmarked military networks remain lawful.
Henderson, I. et al. 2015 Paper Open Deception Law
Entrapped on the Web? Applying the Entrapment Defense to Cases Involving Online Sting Operations
Identifies factors courts use for online-sting entrapment claims: persistence of officer contact, length of relationship, and suspect reluctance. Based on the abstract;
Moore, R. et al. 2007 Paper Paywalled Deception Law
Examining the Efficacy of Decoy-based and Psychological Cyber Deception
The results paper from the Tularosa data: a four-condition design finding that decoys plus telling attackers deception is present changes behaviour most. The strongest peer-reviewed evidence that deception imposes real cost.
Ferguson-Walter, K. J. et al. 2021 Paper Open Deception
Exploratory Analysis of Decision-Making Biases of Professional Red Teamers in a Cyber-Attack Dataset
Re-analysis of red-team data for confirmation bias and framing effects, reporting that framing reduced attacker interaction with the network. Exploratory by the authors' own description, and behind a subscription.
Gutzwiller, R. S. et al. 2023 Paper Paywalled Deception
Exploring the Ethics of Cyber Deception Technologies for Defensive Cyber Deception
Identifies six issues (consent, entrapment, cyber perfidy, responsibility, attacker harm, internet safety) and engages the UK Computer Misuse Act in weighing attacker data collection; proposes ethical frameworks.
Reid, I. et al. 2024 Paper Open Deception Law, Deception
First known AI-powered ransomware uncovered by ESET Research
PromptLock generates Lua payloads at runtime using a local gpt-oss-20b model. ESET states plainly it was never seen in an attack and is believed to be a proof of concept, which most coverage omitted.
Cherepanov, A.; Strýček, P. 2025 Report Open Attackers
Foreign Interference in Elections under the Non-intervention Principle: We Need to Talk about 'Coercion'
Argues fake-news and disinformation operations designed to make an electorate vote differently are coercive and therefore prohibited intervention.
Wheatley, S. 2020 Paper Open Deception Law
Foundations of Cyber Deception: Modeling, Analysis, Design, Human Factors, and Their Convergence
Twelve chapters across theory, human factors and application domains including ICS and UAV networks. Pitched at students entering the area.
Zhu, Q. et al. 2026 Book Paywalled Deception
From A2A Attacks to Envelope-Layer Defense: Red-Teaming Evaluation of LLM Agents and a Three-Layer Isomorphic Attack-Defense Model
A2A-TIBA chains indirect prompt injection with a persistent callback program delivered over the agent-to-agent protocol, so that after one implant subsequent commands bypass the agent entirely. Tested across 15 front-end x back-end combinations (900 attacks) with a four-class metric separating LLM refusal from agent-layer interception; penetration ran 12% for hermes to 45% for Claude Code. An ablation argues untrusted-source label headers on A2A, tool and memory channels sharply raise refusal. Single-author preprint submitted to IEEE TDSC; testbed only, decoy files, China-market back-ends.
Han, Y. 2026 Paper Open Attackers
From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code
Walks through an exploitable stack buffer underflow in SQLite that the agent found and existing fuzzing had missed. Vendor-authored, and a single case. The technical detail is unusually complete for this genre.
Google Big Sleep Team 2024 Blog Open Attackers
Future of AI Honeypots
Short essay predicting that agents will learn to spot honeypots and dodge fingerprinting, so traps should instead test for the mix of intelligence and speed that hiding would sacrifice. It reports no new measurements; the evidence is the author's 2024 honeypot, whose emulated Cowrie shell frontier models later saw through within seconds, plus figures cited from others. The author co-wrote pasquini-2026-shibboleth, whose fingerprinting approach this post expects to lose force. Individual blog post, not peer reviewed.
Reworr 2026 Blog Open Deception, Attackers
Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams
Combines game theory with LLM-driven conversational bots to engage phone scammers and waste their time, a form of conversational deception aimed at human adversaries. Whether it was tested on live scam calls or simulated scammers is unconfirmed, and that decides how far the result transfers. Springer LNCS chapter.
Basta, N. et al. 2026 Paper Paywalled Deception
GameSec: Conference on Game Theory and AI for Security
Where the formal game-theoretic treatment of deception and signalling gets published. Proceedings as Springer LNCS.
GameSec — Venue Open Deception
Gating Tool Calls by Where Their Arguments Came From: A Prompt-Injection defense Measured Without a Model
Prompt-injection defense that gates each tool call on where its arguments came from, rather than trying to recognise malicious text. The author reports that a text-matching rule layer catches 19.8% of a corpus of real attacks, motivating the switch. Measured on the author's own corpus with no model in the loop, so agent behaviour is untested. Single-author Zenodo preprint.
Temel, C. 2026 Paper Open Attackers
GTIG AI Threat Tracker: From Prompting to Autonomy - The Evolution of Adversarial AI
September 2026 tracker documenting a shift from prompt-assisted work to agentic workflows, including a cloud compromise and mass credential harvesting completed in under six hours. Names specific actors and malware families.
Google Threat Intelligence Group 2026 Report Open Attackers
Hackback Back: Assessing the Active Cyber Defense Certainty Act
Analyzes the ACDC Act's proposed CFAA defense, including its treatment of 'beacon' code in decoy files that phones home with forensic data when stolen.
Chesney, R. 2019 Blog Open Deception Law
Hacking Back and International Law: An Irreconcilable Pair?
Active responses beyond one's network are hard to justify as countermeasures or self-defense because they require timely state attribution; necessity is ill-suited as a legislative basis.
Lahmann, H. 2020 Blog Open Deception Law
Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks
Plants adversarial text in responses an attacking agent will read, disrupting it or compromising the attacker's own machine, with over 95% reported effectiveness. The cleanest statement of deception aimed at machines rather than people.
Pasquini, D. et al. 2024 Paper Open Attackers, Deception
HADES creates alternate reality to mislead hackers
Moves an intruder into an altered environment to induce doubt rather than ejecting them. A press release, not a paper, and dated.
Sandia National Laboratories 2017 Programme Open Deception
Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications
Self-replicating prompts that propagate between RAG-connected agents without a user clicking anything, plus a proposed guardrail. Demonstrated in a lab; no such worm has been observed operationally.
Cohen, S. et al. 2024 Paper Open Attackers
HoneyFactory: Container-Based Comprehensive Cyber Deception Honeynet Architecture
Container-based honeynet that deploys honeypots dynamically as an intrusion progresses, using a Gaussian hidden Markov model to estimate attack stage. Open access; evaluation is simulation-based.
Yu, T. et al. 2024 Paper Open Deception
Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
Twenty-one models against 174 reconnaissance queries, finding LLMs take deceptive bait far more often than humans, show no attention-diversion effect, and act on traps 73.4% of the time despite naming them in their reasoning.
Prinos, K. et al. 2026 Paper Open Attackers, Deception
HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense
Four cooperating agents divert jailbreak attempts into decoy responses, reporting a 68.77% average reduction in attack success while leaving legitimate queries intact. Preprint; the threat model is model-level, not network-level.
Li, S. et al. 2026 Paper Open Attackers, Deception
Identifying Protected Missions in the Digital Domain
Compares technical designs for a digital emblem and warns that the scale of potential misuse is far greater than for physical emblems, with weaker enforcement.
De Simone, A. et al. 2021 Blog Open Deception Law
IHL's Lighthouse: Navigating Towards a Digital Emblem
Update on the digital emblem project (IETF/ITU standardization; decentralized, covertly verifiable). Stresses it is a signaling mechanism to be integrated into IHL, including existing misuse prohibitions.
D'Cunha, S.; Vignati, M. 2026 Blog Open Deception Law
Impact of AI on cyber threat from now to 2027
UK national assessment using calibrated probability language, judging that AI will almost certainly make intrusion operations more efficient and that a widening gap will separate defended from undefended estates.
National Cyber Security Centre 2025 Report Open Attackers
Imposing a Cyber Penalty Against Attackers with Cyber Deception
Readable summary of the Tularosa findings for practitioners: 52% of attacker commands targeted decoys, and exploit failures doubled under deception. Read this before the two formal papers.
Ferguson-Walter, K. J. 2022 Blog Open Deception
Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks
Inserts a high-level attack abstraction layer between the model and the network, reaching critical assets in 37 of 40 benchmark environments where baseline agents managed 3. The clearest evidence that scaffolding, not model scale, is the constraint.
Singer, B. et al. 2025 Paper Open Attackers
Intelligent interactive honeypots: A systematization of AI-driven cyber deception
Systematizes forty studies on AI-driven interactive honeypots, mapping interaction level to attack stage and calling out unstandardised datasets and evaluation as the field's main weaknesses. Carries a 2027 issue date.
Nyamwaya, S. et al. 2027 Survey / SoK Open Deception, Attackers
International Symposium on Quantum Interaction (QI)
The dedicated venue for quantum-structure work across cognition, language and information retrieval. Nothing since QI 2018; the series looks dormant.
Springer — Venue Paywalled Quantum cognition
Introducing Aardvark: OpenAI's agentic security researcher
Announcement of a GPT-5-based agent that finds vulnerabilities, validates exploitability in a sandbox and proposes patches, claiming 92% detection on a seeded benchmark. Vendor announcement, not a paper; the benchmark is not independently reproducible.
OpenAI 2025 Report Open Attackers
Introducing CodeMender: an AI agent for code security
The defensive counterpart to the discovery agents: reports 72 security fixes upstreamed to open source over six months, including into a 4.5-million-line codebase. Vendor-authored, with no external audit of fix quality.
Google DeepMind 2025 Report Open Attackers
Introduction to Cyberdeception
The only general textbook on the subject. Impersonation, delays, fakes, camouflage, false excuses, on both offence and defense, with sustained attention to industrial control systems throughout rather than in one token chapter.
Rowe, N. C.; Rrushi, J. 2016 Book Paywalled Deception
Is Cyber Deception a Must-Have This Time?
Practitioner essay asking whether the AI era will finally make cyber deception a standard control, after earlier waves ended with standalone vendors being bought up. It brings no new data, but notes a 2026 industry briefing that ranked deception ninth of 11 recommended actions. His answer is mostly no, because attention, visible results and mandates have not changed, so he advises planting decoy credentials and MCP servers inside agent and identity projects already underway. Individual blog; compare ncsc-2025-deception-trials.
Zeltser, L. 2026 Blog Open Deception
Jennifer Trueblood
Indiana University; directs the Computational Decision Making Lab. Order effects in inference, Bayesian model comparison.
Trueblood, J. S. — Person Open Quantum cognition
Jerome Busemeyer
Indiana University. The field's most prolific author.
Busemeyer, J. R. — Person Open Quantum cognition
Journal of Mathematical Psychology, Volume 53, Issue 5: Special Issue on Quantum Cognition
The 2009 Bruza and Gabora special issue, where the field consolidated: Aerts on quantum structure, and the first empirical Markov-versus-quantum comparisons. Articles mostly paywalled.
Bruza, P. D.; Gabora, L. 2009 Venue Paywalled Quantum cognition
Know Your Enemy: Learning about Security Threats, 2nd Edition
The Honeynet Project's collective account of running honeynets and reading what walked in. Badly dated. Out of print, though two sample chapters and the CD contents are still free.
The Honeynet Project 2004 Book Free registration Deception
Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
Synthesises over 70 academic and industry sources on offensive and defensive LLM use, including AI-generated malware. Preprint and broad rather than deep; useful mainly as a bibliography.
Ahi, K.; Valizadeh, S. 2026 Survey / SoK Open Attackers
Legal Issues of Honeynet's Generations
Maps legal issues (privacy, liability, compliance) across honeynet data control, capture, collection and analysis functions under EU law.
Sokol, P. 2015 Paper Paywalled Deception Law, Deception
Liability and Ethics of Honeypots
Downstream liability if a honeypot is used to attack others is unresolved and set by state law; operators may face copyright liability if attackers distribute contraband, so operators need to filter outbound traffic.
Kabay, M. E. 2003 Blog Open Deception Law, Deception
LLM Agents can Autonomously Exploit One-day Vulnerabilities
Reports GPT-4 exploiting 87% of 15 one-day CVEs when handed the CVE description, dropping to 7% without it. The headline number is widely cited; the caveat that it needs the writeup is the part most citations omit.
Fang, R. et al. 2024 Paper Open Attackers
LLM Honeypot: Leveraging Large Language Models as Advanced Interactive Honeypot Systems
Fine-tunes an open-weights model on captured attacker sessions to generate honeypot responses, then evaluates realism and deploys it live. Preprint; evaluation is thinner than shelLM's.
Otal, H. T.; Canbaz, M. A. 2024 Paper Open Deception, Attackers
LLM in the Shell: Generative Honeypots
shelLM, an LLM-backed Linux shell honeypot reporting a 0.90 true negative rate against security experts asked to tell it from a real host. The paper that started the generative-honeypot line.
Sladić, M. et al. 2024 Paper Open Deception, Attackers
METR
Nonprofit evaluating frontier models for autonomous capability. Not cyber-specific, but its time-horizon work underpins most autonomy forecasting.
METR — Programme Open Attackers
microsoft/CyberBattleSim
Abstract simulated network for agents moving laterally, built for reinforcement learning rather than realism. MIT. The abstraction is deliberate and it does limit transfer.
Microsoft Research — Tool Open Attackers
MITRE Engage
MITRE's adversary engagement framework: prepare, operate and understand phases over a goal/approach/activity matrix, with a starter kit. Successor to MITRE Shield, and the common vocabulary most deception programmes end up using.
MITRE Corporation 2022 Framework Open Deception
mitre-atlas/atlas-data
ATLAS tactics, techniques, mitigations and case studies as versioned YAML. Easier to cite than the client-side-rendered website.
MITRE Corporation — Framework Open Attackers
mitre/engage
The Engage matrix as machine-readable data, plus the site tooling. Apache-2.0.
MITRE Corporation — Tool Open Deception
Moving Target Defense II: Application of Game Theory and Adversarial Modeling
Game-theoretic and adversarial modelling of surface randomisation. Read it with the GameSec proceedings for the formal treatment.
Jajodia, S. et al. 2012 Book Paywalled Deception
Moving Target Defense: Creating Asymmetric Uncertainty for Cyber Threats
The volume that named moving target defense as a research area. Pre-cloud; read it as an origin document.
Jajodia, S. et al. 2011 Book Paywalled Deception
Multi-service honeypot framework for high-fidelity cyber-attack data collection and machine learning-based threat detection in cloud environments
Cloud-hosted honeypot framework running several emulated services to collect attack traffic, then training machine-learning models to classify what it captured. Accuracy on traffic the same honeypot collected says little about performance elsewhere, and whether the captured data is released is unconfirmed. Scientific Reports, open access.
Sridhar, G. et al. 2026 Paper Open Deception
mushorg/conpot
ICS/SCADA honeypot emulating industrial protocol stacks. Python, GPL-2.0. The usual starting point for OT deception.
MushMush Foundation — Tool Open Deception
NeuroGuard: An Interpretable Cyber Defense Agent Through Reinforcement Learning
Reinforcement-learning agent for network defense, designed so that its decisions can be explained. RL defenders are usually trained and scored inside one simulator, so transfer beyond it is the caveat to check; see saika-2026-cyber-sim-to-real-transfer. Springer LNCS chapter.
Anser, Y. et al. 2026 Paper Paywalled Attackers
New Authorities for Military Cyber Operations and Surveillance, Including TMA
Reviews FY2019 NDAA cyber provisions, including language treating military deception and psychological operations as authorized activities and targeting Russian actors planting narratives.
Chesney, R. 2018 Blog Open Deception Law
NIST AI 100-2 E2023: Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
The reference vocabulary for adversarial ML: attacker goals, capabilities, mitigations. This page is the E2023 final, published January 2024. A later 2025 edition exists and I could not find a stable landing page for it.
Vassilev, A. et al. 2024 Standard Open Attackers
NIST SP 800-160 Vol. 2 Rev. 1: Developing Cyber-Resilient Systems: A Systems Security Engineering Approach
The cyber resiliency engineering framework. Cite this when a deception programme has to map to recognised controls.
Ross, R. et al. 2021 Standard Open Deception
No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents
All-RL and all-LLM planner–executor red agents against expert RL defenders in CybORG CAGE-4 and Cyberwheel at 100 and 1010 hosts (18 configurations, 3,600 episodes). RL wins CAGE-4 (78.5% vs 18.0%) and Cyberwheel-100 (81.0% vs 50.5%) but scores 0.0% at 1010 hosts, where Foundation-Sec-8B reaches 55.0%. Every configuration compromises a host; the failures come at escalation or root-to-impact. LLM results depend on the model (DeepHat scores 0% everywhere), and on CAGE-4 the RL planner proves not load-bearing. Simulator-only preprint.
Shaikh, A. J. et al. 2026 Paper Open Attackers
NVIDIA/garak
NVIDIA's LLM vulnerability scanner. Prompt injection, jailbreaks, training-data leakage, glitch tokens. Apache-2.0.
NVIDIA — Tool Open Attackers
Open Quantum Systems in Biology, Cognitive and Social Sciences
Extends the framework to open-system dynamics, with the decision maker coupled to an environment rather than isolated. The most current book-length treatment from this school.
Khrennikov, A. Y. 2023 Book Paywalled Quantum cognition
Operation Trojan Shield May Be Clever, but Is It Outrageous?
Asks whether the FBI's creation and control of the ANOM encrypted app crosses into 'outrageous government conduct' barring convictions under Ninth Circuit due-process precedent. Based on a summary;
Fiset, R. L.; Masys, J. 2024 Blog Paywalled Deception Law
OWASP Top 10 for Agentic Applications for 2026
Community risk list for autonomous agent systems. Practitioner-oriented, not empirical. The download page asks for your details.
OWASP Gen AI Security Project 2026 Framework Free registration Attackers
paralax/awesome-honeypots
The long-running index of honeypot software by protocol and environment, with a section on anti-honeypot detection tools. Breadth over curation.
paralax — Tool Open Deception
pasquini-dario/project_mantis
The Mantis decoys as running code: tarpitted FTP, deliberately vulnerable web apps, weak telnet, injection payloads, reverse-shell listeners.
Pasquini, D. — Tool Open Attackers, Deception
Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents
Fifteen open prompt-injection detectors, including Prompt Guard 2, and two LLM judges, tested on replayed AgentDojo and τ-bench tool outputs and on BIPIA. Rankings barely transfer: PIGuard catches 95.1% of BIPIA injections at 1% FPR, having trained on BIPIA inputs, but 2.1% on AgentDojo. False-positive rates on tool outputs (0 to over 90%) stay consistent across both agent benchmarks. Single-author, unreviewed preprint; Claude wrote the code, ran the experiments and drafted the text. Static attacks only, so detection figures are upper bounds.
Liu, Z. 2026 Paper Open Attackers
PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing
The peer-reviewed version of PentestGPT, splitting reasoning, generation and parsing into separate modules to survive context loss over long engagements. USENIX hosts the PDF and talk video free.
Deng, G. et al. 2024 Paper Open Attackers
Perfidious Warfare and AI Systems: Assessing the Capacity for Deception in an International Armed Conflict
Argues AI systems cannot form the 'belief,' 'confidence' or 'trust' that perfidy requires, so deceiving an autonomous system (e.g., abusing a white-flag signal it reads) falls outside the rule, leaving a legal gap.
Velenczei, D. V. 2025 Blog Open Deception Law
PHANTOM: polymorphic honeytoken adaptation with narrative-tailored organisational mimicry contextually convincing cyber deception at scale
Generates honeytokens carrying organisation-specific naming and technology conventions, scoring 0.778 believability against 0.576 for templates. The authors concede the evaluation is 32 tokens scored by rules, not humans.
Weinberg, A. I. 2026 Paper Open Deception
pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation
Open-source harness that composes 13 injection wordings, 16 carriers (web pages, PDF metadata, MIME headers, calendar events and others) and 9 prompt-level defenses, so each axis can be varied independently. Tested on the pi coding agent with an undisclosed model, defenses cut pooled attack success from 6.00% to 1.69% over 2,817 matched runs. The '71.8% reduction' is relative to that low baseline, on a pre-selected high-risk subset. Heuristic detectors reached at most 17.78% recall. Tencent Zhuque Lab preprint.
Ying, Z. et al. 2026 Paper Open Attackers
Planning and Integrating Deception into Computer Security Defenses
Three-phase model for planning deception that makes attacker bias an explicit design input and carries Bell and Whaley's six techniques into computer security. Widely borrowed from, rarely credited.
Almeshekah, M. H.; Spafford, E. H. 2014 Paper Open Deception
Proactive Detection of Security Incidents: Honeypots
EU agency study of honeypot tools with a short legal section flagging liability if a honeypot is used in attacks and advising CERTs to obtain jurisdiction-specific legal advice.
CERT Polska (NASK) 2012 Report Open Deception Law, Deception
process-aware-verification-mfg: code and data for Process-Aware Verification Against Prompt Injection in Manufacturing Cells
Code and data for a study of prompt injection against LLM task planners in a robot-tended finish-turning cell, defended by checking planned actions against process constraints rather than filtering text. Includes a discrete-event simulation of the cell. The cell, attacks and defense are all the authors' own, in simulation. Companion manuscript under review.
Koliada, A. et al. 2026 Dataset Open Attackers
Professor Emmanuel Pothos
Co-author of the BBS target article and the Annual Review survey. The free full texts are in City Research Online, not on this page.
Pothos, E. M. — Person Open Quantum cognition
Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models
Argues that poor benchmark scores reflect bad scaffolding rather than model limits, and shows CyberSecEval 2 buffer-overflow scores moving from 0.05 to 1.00 once the tooling improved. The methodology post behind Big Sleep.
Glazunov, S.; Brand, M. 2024 Blog Open Attackers
Quantum Approaches to Consciousness
Last revised May 2024. Section 4 separates quantum cognition from quantum-consciousness claims, making the case for quantum mind without quantum brain. The cleanest statement of what the field is not claiming.
Atmanspacher, H. 2024 Survey / SoK Open Quantum cognition
Quantum Cognition
Free-to-read review covering contextual inference, belief updating and interference effects, with an explicit section on limitations. The single best orientation piece if you read only one thing here.
Pothos, E. M.; Busemeyer, J. R. 2022 Survey / SoK Open Quantum cognition
Quantum cognition (Wikipedia)
Reasonably sourced overview, roughly 48 citations spanning 1953 to 2022. It is here as an orientation link despite the general exclusion of secondary coverage. It has no criticism section and reads as advocacy, so pair it with Boyer-Kassem.
Wikipedia contributors — Blog Open Quantum cognition
Quantum Cognition and Decision Notes
Busemeyer's own page: tutorial chapters, free preprints of most of his papers, Hilbert Space Model code. Plain HTML, no index, and the full texts really are here.
Busemeyer, J. R. — Course Open Quantum cognition
Quantum cognition: a new theoretical approach to psychology
Short, readable introduction aimed at psychologists rather than mathematicians. The author's copy is free; the Elsevier version is paywalled. Ten pages, and the fastest way into the vocabulary.
Bruza, P. D. et al. 2015 Paper Open Quantum cognition
Quantum Models of Cognition
Chapter 7 of Ron Sun's handbook, which places quantum cognition among the other modelling paradigms instead of defending it in isolation. The most useful framing available if you already know Bayesian cognitive modelling.
Busemeyer, J. R.; Pothos, E. M. 2023 Book Paywalled Quantum cognition
Quantum Models of Cognition and Decision
The field's standard monograph. Builds the Hilbert-space machinery from scratch, then applies it to judgment, decision and memory. Assumes linear algebra. A second edition exists — check which you are citing.
Busemeyer, J. R.; Bruza, P. D. 2012 Book Paywalled Quantum cognition
Quantum principles in psychology: The debate, the evidence, and the future
The authors' reply to the BBS commentaries, and the most concentrated place to see the objections stated and answered. Free full text via City's repository; read it immediately after the target article.
Pothos, E. M.; Busemeyer, J. R. 2013 Paper Open Quantum cognition
Quantum Structure in Cognition
Proves that classical models cannot reproduce measured membership weights for conceptual conjunctions and disjunctions, and derives superposition and interference from that failure. The founding paper of the Brussels line of work.
Aerts, D. 2009 Paper Open Quantum cognition
Quantum Structure in Cognition: Fundamentals and Applications
Compact statement of the Brussels position: quantum conceptual thought running alongside classical reasoning, with implications drawn for information retrieval and artificial intelligence. Shorter than the journal papers.
Aerts, D. et al. 2011 Paper Open Quantum cognition
Quantum-Like Bayesian Networks for Modeling Decision Making
Replaces classical probabilities with amplitudes inside a Bayesian network and adds a similarity heuristic so the quantum parameters are computed rather than fitted. Addresses the standard overfitting objection directly.
Moreira, C.; Wichert, A. 2016 Paper Open Quantum cognition
Quantum-like models cannot account for the conjunction fallacy
The strongest published attack on the programme: experiments on question-order effects produce results the quantum account of the conjunction fallacy predicts wrongly. Read it before citing any quantum explanation of Linda.
Boyer-Kassem, T. et al. 2016 Paper Open Quantum cognition
ReSCIND: Reimagining Security with Cyberpsychology-Informed Network Defenses
US intelligence-community programme funding defenses that exploit attacker cognitive biases. Began 2023, three phases; solicitation closed.
IARPA 2023 Programme Open Deception
Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks
Proposes honeypot services that hand an attacking agent credentials only after it names its model and writes free-text notes, plus probes that read the harness from how it masks secrets, enforces timeouts and schedules tool calls. Across about 800 lab runs it names the right model among 15 about 90% of the time and the right harness among four in 92% of runs. Those runs used containers on a private network, and agents told to give a fake name cut accuracy to 8%. Unreviewed v0.1 preprint extending pasquini-2024-mantis.
Pasquini, D. et al. 2026 Paper Open Deception, Attackers
scadastrangelove/awesome-ai-security-tools
Curated index of AI security tools covering finding triage, agent security, pentest agents, LLM-driven fuzzing, SOC triage, reverse engineering and red teaming, with a section on LLM honeypots and deception. It catalogs tools rather than measuring them, and the page gives no figures on whether listed tools work. Entries are described, not tested, so use it for discovery and judge tools elsewhere. Single-maintainer list under a CC0 license, broader than awesome-ai-agent-security.
scadastrangelove — Tool Open Attackers
Self-Evolving Defense: Continual Security Policy Learning for LLM Agents
Training-free defense in which an LLM judge scores each completed agent trajectory, distils harmful ones into a tree of retrievable security policies, and injects the closest matches into later system prompts. On DeepSeek-V4-Flash it cuts AgentDojo targeted injection from 49.0% to 0.42% (DRIFT: 3.7%) and adaptive X-Teaming from 50% to 7.8%. Memory is learned online from each benchmark's own episode stream, with the agent's base model as judge, and poisoning of that memory is not tested. Unreviewed preprint.
Le, M. N. et al. 2026 Paper Open Attackers
Shadowkube: enhancing Kubernetes security with behavioral monitoring and honeypot integration
Converts compromised Kubernetes nodes into shadow honeypots in place, reporting 97.7% true-positive detection over 43 CVEs and 635 real attack attempts during public deployment. Open access, with live-deployment numbers rather than simulation.
Chen, Q. et al. 2025 Paper Open Deception
Simon Willison: Prompt injection
Twenty-five posts, September 2022 to November 2025, by the person who named the attack class. Tracks it from first description through multi-modal variants to defensive design patterns. Has a feed.
Willison, S. — Blog Open Attackers
SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned
Camera-ready systematization of AIxCC by participants and organizers, covering competition design, the finalist architectures, and execution traces. The single best account of what autonomous cyber reasoning systems could and could not do by 2025.
Zhang, C. et al. 2026 Survey / SoK Open Attackers
SoK: Honeypots & LLMs, More Than the Sum of Their Parts?
Systematizes both directions at once: LLMs used to build honeypots, and honeypots built for LLM attackers. Includes a taxonomy of honeypot detection vectors and a critique of how the area evaluates itself.
Bridges, R. A. et al. 2025 Survey / SoK Open Attackers, Deception
Spoiling for a Fight: Hacking Back with the Active Cyber Defense Certainty Act
Assesses ACDC's benefits and risks; dedicates a section to honeypots and discusses the Act's 'attributional technology' (beacon) carve-out and collateral-damage concerns.
Porch, A. M. 2020 Paper Open Deception Law
Staying ahead of threat actors in the age of AI
The first joint Microsoft and OpenAI disclosure, naming five state-linked groups using models for reconnaissance, scripting and social engineering, and finding no new AI-enabled attack. The baseline everything since is measured against.
Microsoft Threat Intelligence 2024 Report Open Attackers
Stinging the Swarm: Extracting Attacker Intelligence from a Twin-Controller OT Honeypot
Describes Talos, an inline gate that screens each agent request to an industrial controller and reroutes agents it judges hostile to a mirror twin, where their attacks are mined for intelligence. Against 2,400 attacker agents in four concealment tiers of 600, no write reached the plant. The gate sent only 8% to 55% of each tier to the mirror and let 1,427 writes through, which a device-level check rejected, and every agent ran one abliterated Llama model against one simulated pump line. Unreviewed preprint with no repository link.
Dell'Omo, C. G.; Joao Pedro de Carvalho Voltani 2026 Paper Open Deception, Attackers
Strong Entropy, Weak Guarantees: Governance Failures in Distributed Moving Target defense
Examines distributed moving target defense, where, as the title puts it, high entropy fails to yield strong guarantees because of governance failures across nodes. If empirical, it is a counterweight to the efficacy framing in hou-2025-mtd-deception-evaluation and cho-2019-mtd-survey. Springer LNCS chapter.
Saunders, Z. et al. 2026 Paper Paywalled Deception
Tactical Level PSYOP and MILDEC Information Operations: How to Smartly and Lawfully Prime the Battlefield
Argues tactical PSYOP and military deception must respect the perfidy ban, distinction and proportionality, but deserve liberal legal interpretation because they aim to influence rather than kill.
Kastenberg, J. E. 2007 Paper Open Deception Law
Technical Blog: Strengthening AI Agent Hijacking Evaluations
Hijacking success against one model rose from 11% to 81% once the red team adapted its attacks. That gap is the methodological warning for anyone quoting a single injection-resistance number, including the good ones.
NIST Center for AI Standards and Innovation 2025 Blog Open Attackers
telekom-security/tpotce
Around thirty honeypot daemons bundled with Elasticsearch, Kibana and Suricata behind one installer. GPL-3.0.
Deutsche Telekom Security — Tool Open Deception
The Deception Delta: Artifact for Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics
Artifact for a paper testing whether adversarially crafted smart-contract bytecode misleads LLMs used as forensic analysts: frozen model responses, judge outputs, bytecode and source inputs, gold labels and analysis scripts. It inverts this directory's usual direction, with the deceived machine on the defending side; read with prinos-2026-honeyquest-llms. CCS 2026 acceptance is claimed.
Schefold, T. 2026 Dataset Open Deception, Attackers
The Honeynet Project
501(c)(3) running since 1999. Institutional home of most of the open honeypot software listed here.
The Honeynet Project — Programme Open Deception
The Legal Boundaries of (Digital) Information or Psychological Operations Under International Humanitarian Law
Misinformation aimed at enemy forces is a lawful ruse if non-perfidious, but IHL bars digital IO that encourage violations, spread terror, cause displacement or harm protected persons and facilities, whatever deceptive method is used.
Rodenhäuser, T. 2023 Paper Open Deception Law
The Misuse of Protected Indicators in Cyberspace: Defending a Core Aspect of International Humanitarian Law
Argues IHL bans on misusing protective emblems and enemy indicators extend to domain names, email addresses and graphical symbols in cyberspace. Flags gaps (e.g., IP addresses lack recognized protected status) that adversaries could exploit to erode trust in humanitarian actors.
Biller, J. 2017 Paper Open Deception Law
The New Era of Disinformation Wars: Does IHL Sufficiently Regulate the Use of Deepfakes?
Deepfakes can be lawful ruses or prohibited perfidy, but panic-inducing deepfakes aimed at civilians escape regulation because they are not 'attacks' causing physical harm.
Cohen, L. M. 2020 Blog Open Deception Law
The Rise of the 'Fifth Fight' in Cyberspace: A New Legal Framework and Implications for Great Power Competition
Examines Title 10/Title 50 lines after Congress defined clandestine cyber activities as 'traditional military activities,' including Pentagon concerns over strategic deception and peacetime psychological operations.
West, L. B. 2021 Paper Open Deception Law
The Road to Top 1: How XBOW Did It
Vendor account of reaching the top of HackerOne's US leaderboard with roughly 1,060 validated findings from an autonomous system. Marketing-adjacent and entirely self-reported. The discussion of deduplication and validation is the substantive part, and it is the part most coverage of this left out.
XBOW 2025 Blog Open Attackers
The Tularosa Study: An Experimental Design and Implementation to Quantify the Effectiveness of Cyber Deception
Over 130 red-team professionals in a two-day penetration task, with presence and disclosure of deception manipulated independently, plus questionnaires and physiological measures. The design paper that most later efficacy claims trace back to.
Ferguson-Walter, K. J. et al. 2019 Paper Open Deception
thinkst/opencanary
Multi-protocol honeypot daemon light enough for a Raspberry Pi. BSD-3-Clause. The open counterpart to Thinkst's commercial Canary.
Thinkst Applied Research — Tool Open Deception
Threat Intelligence (Anthropic)
Index of Anthropic's dated misuse reports, March 2025 onward. No feed, so it needs checking by hand.
Anthropic — Newsletter Open Attackers
Threat-Actors-use-of-Artificial-Intelligence
Documented threat-actor AI use mapped to ATT&CK, from Microsoft, OpenAI, Anthropic, GTIG and Kaspersky reporting. Narrower than it looks: attacks on AI systems and influence operations are excluded by design.
cybershujin — Tool Open Attackers
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Across 28,904 runs on ASB, MCPTox and AgentDojo, renaming tools while holding task, harmful action and scorer fixed shifts attack success. Neutral names on ASB's attacker tools raise committed ASR by 11.67–13.21 points; threat-explicit names on MCPTox lower it by 11.00 (GPT-5-mini) and 4.11 (Haiku 4.5); AgentDojo barely moves (−0.50). A form-matched neutral name reproduces 8.54 of MCPTox's 11 points, so threat vocabulary is not the main driver. Unreviewed preprint covering three small models.
Karamchandani, N. et al. 2026 Paper Open Attackers
tl;dr sec
Weekly security newsletter, free, with steady AI-security coverage. The feed avoids the signup.
Gibler, C. — Newsletter Free registration Attackers
Toward Proactive, Adaptive Defense: A Survey on Moving Target Defense
The standard MTD survey: design principles, classifications, algorithms, evaluation metrics and applications in one place. Free on arXiv and thorough, though it predates the cloud-native and agentic work entirely.
Cho, J.-H. et al. 2019 Survey / SoK Open Deception
Towards a 'Digital Emblem'? Five Questions on Law, Tech, and Policy
Proposes a digital emblem for medical/humanitarian assets and acknowledges the risk of falsely marking military infrastructure; says misuse is already prohibited and perfidious misuse may be a war crime (Rome Statute art. 8(2)(b)).
Rodenhäuser, T.; Vignati, M. 2022 Blog Open Deception Law
Towards Hierarchical Cyber Defense with Large Language Models: From Planning to Execution
Frozen LLMs replace PPO policies as planner, executor or both in a hierarchical defender in ORNL's Cyberwheel, facing a scripted Atomic Red Team attacker on 15-, 100- and 1,010-host networks. Llama-3.3-70B at both levels holds compromise near 1% and impact near 0% at every scale. The per-scale-retrained RL baseline reaches 17.95% and 15.20% on the large network. An LLM planner over a PPO executor barely helps (10.75–13.05% compromise). Preprint, with one seed, 20 episodes and three actions.
Doppalapudi, H. et al. 2026 Paper Open Attackers
tracebit-com/awesome-deception
Curated list of deception articles, papers, talks and tools, CC0. Maintained by a deception vendor, so weigh the selection accordingly. Still the best jumping-off point.
Tracebit — Blog Open Deception
Ubiquitous Quantum Structure: From Psychology to Finance
Develops the Växjö contextual probability model, arguing non-Kolmogorov probability is the general case rather than a quantum peculiarity. Mathematically heavier than Busemeyer and Bruza and much less tied to experiments.
Khrennikov, A. Y. 2010 Book Paywalled Quantum cognition
UKGovernmentBEIS/inspect_ai
The UK AI Security Institute's evaluation framework. CVE-Bench and several other cyber evals are written against it. MIT.
UK AI Security Institute — Tool Open Attackers
Update: Evidence Obtained via Operation Trojan Shield (ANOM) Not Inadmissible on Constitutional Grounds
Discusses Germany's Federal Constitutional Court upholding use of ANOM evidence and criticizes its limited scrutiny of foreign law-enforcement deception and data-location findings.
Hoppe, M. 2025 Paper Open Deception Law
Upholding IHL in the Use of ICTs During Armed Conflicts – Workstream 6 Background Paper
State-consultation paper noting IO spreading terror are prohibited and that false information deliberately obstructing medical or humanitarian activities violates IHL; links to digital-emblem work.
ICRC 2025 Standard Open Deception Law
Use a Honeypot, Go to Prison?
Reports DOJ attorney Richard Salgado's view that honeypot monitoring can be interception under the Wiretap Act; banners, the computer-trespasser exception and provider exception may help, but a honeypot built to be attacked may not qualify.
Poulsen, K. 2003 Blog Open Deception Law, Deception
Using Cyber Decoys to Strengthen Detection and Response
CISA's 22-page guide for critical infrastructure, aimed at intruders using valid credentials and living-off-the-land techniques. It follows MITRE Engage: start with tripwires on the EDR and identity tools already in place, and leave intelligence-gathering operations to teams that can handle the operational and legal risk.
Cybersecurity and Infrastructure Security Agency 2026 Standard Open Deception
VirNetMTD: Programmable Moving Target Defense for Virtualized Networks
Moving target defense framework for virtualized networks that, per its title, lets defenders program how the network shifts. Check whether results report attacker outcomes or only system overhead on the authors' own testbed. Springer CCIS chapter.
Dang, T. et al. 2026 Paper Paywalled Deception
We leaked LLM gateway api keys for 35 days. Here's what happened.
A vendor planted 179 working LLM gateway keys in code examples across more than 40 GitHub organizations and logged their use at two decoy gateways, one mimicking LiteLLM. All 64 keys with a timed first request were tried within six hours, but only 18 keys sent prompts, and six of them drew 98.9% of 9,375 prompt requests. The figures come from one snapshot, the gateways ran 36 and 9 days rather than the headline's 35, and no data are released. Pairs with amazon-2026-artex-madpot.
InferTrail Research 2026 Report Open Deception
What Is Quantum Cognition, and How Is It Applied to Psychology?
Seven pages built around two ideas, complementarity and superposition, and explicit that the claim is mathematical rather than a claim about quantum brains. That disclaimer is the most misquoted thing in the field.
Busemeyer, J. R.; Wang, Z. 2015 Paper Paywalled Quantum cognition
What we learned mapping a year's worth of AI-enabled cyber threats
Maps 832 banned accounts from March 2025 to March 2026 onto MITRE ATT&CK, concluding AI use concentrated in post-compromise operations and that ATT&CK lacks categories for agentic orchestration.
Anthropic 2026 Report Open Attackers
Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance
Activation patching across five dense models (4B–32B) finds injection presence decodable from layer 1, but causal leverage over compliance only in the final third of the network. Patching there reverses 77–92% of compliant cases in a synthetic single-turn customer-service setup, about 12% on naturalistic benchmarks. In InjecAgent and AgentDojo rollouts no single-token patch beats a random control. A probe at the causal peak reaches 0.993 AUROC, and a white-box suffix halves its recall. Unreviewed preprint.
Wen, R. et al. 2026 Paper Open Attackers
Workshop on Active Defense and Deception (AD&D)
Fifth edition, Rome, 18 September 2026, co-located with ESORICS. Note that it explicitly excludes offensive counter-attack work.
AD&D Workshop — Venue Open Deception
Zheng (Joyce) Wang
Ohio State, School of Communication. Co-authored the question-order studies; comes at the field from communication rather than mathematical psychology.
Wang, Z. — Person Open Quantum cognition