Metraipolis › archive › dc_fbcfae531c67
AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents — arXiv:2610.02869
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02869
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:50:18.332Z
- SHA-256 of the archived text
a30690e939c5674a6c4f7ee93bc8d3a56ab736bf32a9029b045a665a3254176b- Stable URL of this page
https://metraipolis.com/documento/dc_fbcfae531c67
How to cite
AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents — arXiv:2610.02869 — arXiv, https://arxiv.org/abs/2610.02869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbcfae531c67 (Metraipolis archive dc_fbcfae531c67, sha256 a30690e939c5674a6c4f7ee93bc8d3a56ab736bf32a9029b045a665a3254176b)
BibTeX
@misc{dcfbcfae531c67,
title = {AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents — arXiv:2610.02869},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02869},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbcfae531c67; sha256 a30690e939c5674a6c4f7ee93bc8d3a56ab736bf32a9029b045a665a3254176b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autonomous penetration testing agents conduct multi-step attacks by continuously adapting their plans and actions to target responses. As a common defense, honeypots can be deployed to divert these agents from real assets by presenting decoy services, while also supporting attack tracing and active counterattacks. However, conventional honeypots rely primarily on static artifacts and predefined responses, leaving them unable to adapt to the evolving attack strategies of autonomous penetration testing agents. To this end, we present AgentTrap, the first closed-loop honeypot tailored for autonomous penetration testing agents. AgentTrap uses sentinel endpoints to avoid benign interference, stateful deception grounded in the protected application, and behavior-guided escalation to sustain engagement and collect agent-side behavioral evidence with controlled disclosures. We evaluate AgentTrap against eight autonomous penetration-testing agents in a deployed web application containing a real application endpoint and a separate honeypot endpoint configured under three defense strategies. Compared with no defense, AgentTrap reduces the aggregate real-target attack success rate from 95.8% to 79.2% and successfully elicits attacker API keys in 18.8% of the runs, outperforming static deception and fixed escalation. Furthermore, trace analysis shows that resistance to such counterattacks depends jointly on model-level recognition of deceptive requests and architecture-level isolation of sensitive resources. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.02869 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T22:45:55.803Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).