AI & ML
Adaptive LLM-Driven Honeypots vs. LLM-Driven Attackers: Does Narrative Coherence Improve Deception?
arXiv cs.CR0 views
arXiv:2611.22589v1 Announce Type: new Abstract: Large Language Models (LLMs) enable honeypots to generate responses and deceptive artefacts on demand, yet existing approaches evaluate generated content one reply at a time and leave open whether artefacts that jointly describe a coherent event retain an attacker better than unrelated ones. This question becomes pressing as autonomous LLM-driven offensive agents emerge as realistic adversaries. This paper proposes narrative deception, a reactive strategy in which the defender maps each observed attacker command to a MITRE ATT&CK technique, selects a compatible scenario from a curated catalogue based on MITRE Engage, and deploys mutually referential artefacts (files, processes, services, and logs) on an emulated Ubuntu host while the intrusion is under way. An LLM-powered defender and an autonomous LLM attacker interact through a real SSH session, and the attacker's termination policy distinguishes abandonment due to suspected deception from abandonment due to loss of interest. A campaign of 1,150 sessions compares four conditions of increasing sophistication (Static, Same-TTP, Multi-TTP, and Chain) across four open-weight attacker models, four defender models, and three attacker skill levels. Engagement increases significantly at every step. With the same artefact budget per reaction, coherent scenarios raise the median session length of advanced attackers from 40 to 165 commands and reduce their abandonment from 86% to 52%. The effect grows with attacker skill, holds across all sixteen model pairs, and comes at comparable inference cost. Nearly all sessions ended through loss of interest rather than detection, which suggests that deception should sustain meaningful findings, not only emulator fidelity.
Source:https://arxiv.org/abs/2611.22589PreviousEvolution Under Fire: Evolving Agent Safety Harnesses with Adaptive Injection StressorsNextOn Improving the Adoption, Usability, and Retention of Static Application Security Testing (SAST) Tools
Related posts
The AI Hype Index: AI is everywhere
0MIT Technology Review
‘Just Ridiculous’: A Famed Philosopher Takes on AI Consciousness
0Wired

Rivian spinoff Also pauses e-bike deliveries over battery and software bugs
0The Verge

The Verge’s 2026 holiday gift guide for travelers
0The Verge
Who owns your AI agent when something goes wrong?
0dev.to
A regra dos três modelos: por que um agente não audita a si mesmo
0dev.to