#artificial intelligence
Sep 2026
CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents
CoDeL is presented, a defense that hardens agent against an attack distribution it reshapes as it trains, and reduces attack success rate (ASR) by 88.5% and outperforms other baselines largely (+38.0%).
Xiao Yang, Yangyiwen Ou, Yu-Han Gao et al.
· arXiv.org · 1 citation