arXiv cs.AI· Pedro Beltr\'an-L\'opez, Raul Gonzalez Jimenez, Dario Maddaloni, Manuel Gil P\'erez, Pantaleone Nespoli·· 4 小时前AI 评分38
自适应 LLM 蜜罐 vs. LLM 攻击者:叙事连贯性能否提升欺骗效果?
Adaptive LLM-Driven Honeypots vs. LLM-Driven Attackers: Does Narrative Coherence Improve Deception?
AI 导读
论文提出“叙事欺骗”策略:防御方将攻击者命令映射到 MITRE ATT&CK 技术,从基于 MITRE Engage 的场景库中选取兼容场景,在入侵过程中于仿真 Ubuntu 主机上部署相互引用的文件、进程、服务和日志。
正文 · 原文
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.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22589 [cs.CR] |
| (or arXiv:2611.22589v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22589 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pedro Beltran [view email]
[v1]
Tue, 17 Nov 2026 11:13:12 UTC (275 KB)
来源:arXiv cs.AI · arxiv.org