AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents

Excerpt

arXiv:2607.26998v4 Announce Type: replace-cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows defenders to inject deceptive observations that can mislead the agent's decision-making process. However, existing defenses rely heavily on static, isolated artifacts planted in the environment prior to an attack. Advanced agents can progressively recognize and