← Back to all news
arXiv Machine Learning By Boyang Zhang, Qingxin Xiao, Lingwei Dang, Qingyao Wu

CoRL: Co-Evolutionary Reinforcement Learning for Adaptive Indirect Prompt-Injection Attacks and Defenses

Read the original on arXiv Machine Learning →

The paper introduces CoRL, a co-evolutionary reinforcement learning framework designed to defend against adaptive indirect prompt-injection attacks on tool-augmented language agents. CoRL operates in three stages—attacker fine‑tuning, bilateral Co‑PPO training, and defender fine‑tuning—using verifier‑grounded repairs to adapt to changing attack strategies. Experiments on 1,514 executions show that CoRL reduces attack success rates to 0% while improving task utility, demonstrating its effectiveness against adaptive adversaries.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
2d ago

CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement

The paper introduces CoER, a framework that defends language‑model agents against adaptive indirect prompt injection (IPI) by employing attacker‑defender co‑evolution and refinement. CoER models IPI as a general‑sum Markov game, uses Co‑PPO to maintain historical opponent populations, and fine‑tunes defenders only on verified safe demonstrations. In experiments across seven domains, CoER cuts attack success from 38.5% to 0.2% while boosting task utility from 63.2% to 76.3%.

By Boyang Zhang, Qingxin Xiao, Lingwei Dang, Qingyao Wu
agentsreinforcement-learningfine-tuningbenchmarkssafety
More like this →
arXiv Machine Learning
Jul 7

Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models

arXiv:2506. 07468v4 Announce Type: replace Abstract: Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities.

By Mickel Liu, Liwei Jiang, Yancheng Liang, Simon Shaolei Du, Yejin Choi, Tim Althoff, Natasha Jaques
llmsagentsreinforcement-learningbenchmarkssafety
More like this →
Hugging Face Trending Papers
Jun 13

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense.

llmsragagentsreinforcement-learningmultimodalbenchmarkssafety
More like this →