A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow

Summary

An LLM defender plans a static honeypot from an application's source code, and a router sends confirmed attackers, including those with working exploits, to an isolated shadow copy. On 40 critical CVE-Bench tasks, the static plan reduced real-target compromise from 26/40 to 5/40 for Claude Opus 4.8 and from 20/40 to 0/40 (31 valid runs) for the ARTEX attack framework. In about half of deception-arm runs, ARTEX's exploit still succeeded on the shadow copy, and ARTEX treated a planted fake secret as genuine on 30 of 120 deception-arm tasks.

Related items

• InfoPerplexity launches its own take on AI agents for workSame vendor · The Verge (AI)
• MediumFake OpenAI, SpaceX events used to steal Microsoft, Google accountsSame vendor · BleepingComputer
• InfoFedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated LearningSame vendor · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoClaude AI can plug directly into your bank accountSame vendor · The Verge (AI)
• InfoIndependent Assessment of AI R&D Acceleration at Anthropic in October 2026Same vendor · METR