ABRACADABRA Labs Resource directory

Intersections · 29 links

Where the topics meet

The four topics on this site connect in interesting ways. This page collects the 29 links that make a real contribution to more than one of them. AI attackers and deception is where the most is happening. As attackers start using AI, defenders are asking whether their traps still work. Early research suggests AI attackers may fall for traps more easily than people do, and AI is also being used to build more convincing traps. Quantum cognition and deception meet in the question of how people make judgments when someone is trying to mislead them. Deception works by shaping what an attacker sees and in what order, and quantum cognition studies how that order changes decisions. Quantum cognition and AI attackers is the newest connection. One recent study tested whether AI models show the same decision patterns as people, and found this harder to measure than expected. Deception law meets cyber deception wherever a defender sets a trap. Watching an intruder in a honeypot may count as interception, data-protection law limits what a decoy may record, and a trap that goes too far can look like entrapment. The ethics of defensive deception sits on the same boundary. Much is still unexplored. No one has yet used quantum cognition to model what an AI attacker believes, or tested whether traps built around human thinking habits work on AI. If you know of work that fills these gaps, let us know.

The pairings

Attackers + Deception 17

17 entries that belong to both literatures, not just to one that mentions the other.

  • 0x4D31/galah

    LLM-powered web honeypot: generates a plausible HTTP response to whatever arrives instead of emulating fixed applications. Go, Apache-2.0.

    living
  • 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.

    living
  • 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.

    contestedpreprint
  • 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.

    vendor-authored
  • 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.

    livingvendor-authoredopen version
  • 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.

  • 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.

    preprintseminalopen version
  • 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.

    preprint
  • 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.

    preprint
  • 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.

  • 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.

    preprint
  • 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.

  • pasquini-dario/project_mantis

    The Mantis decoys as running code: tarpitted FTP, deliberately vulnerable web apps, weak telnet, injection payloads, reverse-shell listeners.

    living
  • 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.

    preprint
  • 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.

    preprint
  • 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.

    preprint
  • 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.

Attackers + Quantum cognition 2

2 entries that belong to both literatures, not just to one that mentions the other.

Deception + Quantum cognition 1

1 entry that belong to both literatures, not just to one that mentions the other.

  • 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.

    paywalled

Deception + Deception Law 9

9 entries that belong to both literatures, not just to one that mentions the other.

  • 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.

  • 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.

  • 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.

    paywalled
  • Deploying Honeypots and Honeynets: Issues of Liability

    Examines civil and criminal liability of honeypot/honeynet administrators and the liability of attackers caught by them.

    paywalled
  • 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.

  • Legal Issues of Honeynet's Generations

    Maps legal issues (privacy, liability, compliance) across honeynet data control, capture, collection and analysis functions under EU law.

    paywalled
  • 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.

    dated
  • 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.

    dated
  • 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.

    dated