arXiv Machine Learning

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%.

arXiv Machine Learning

Sep 10

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

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.

By Boyang Zhang, Qingxin Xiao, Lingwei Dang, Qingyao Wu

agents reinforcement-learning fine-tuning multimodal benchmarks safety

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.

llms rag agents reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 16

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

arXiv:2606. 15441v1 Announce Type: cross Abstract: Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution.

By Lipeng He, Yihan Wang, Jiawen Zhang, N. Asokan

llms rag agents reinforcement-learning multimodal benchmarks safety

arXiv Machine Learning

Jul 24

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.

By Chenlong Yin, Runpeng Geng, Yanting Wang, Jinyuan Jia

llms agents reinforcement-learning efficiency benchmarks safety

arXiv AI

Oct 7

Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks

arXiv:2603.04364v2 Announce Type: replace-cross Abstract: Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet th...

By Haoyu Liu, Dingcheng Li, Lukas Rutishauser, Zeyu Zheng

agents reinforcement-learning fine-tuning multimodal safety

arXiv AI

Jun 16

AutoDojo: Adaptive Attacks Expose Superficial Defenses and User-Underspecification Limits in LLM Agents

arXiv:2606. 15057v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents.

By Xinhang Ma, Taoran Li, Chaowei Xiao, Zhiyuan Yu, Ning Zhang, Yevgeniy Vorobeychik

llms agents multimodal benchmarks

arXiv AI

Sep 30

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...

By Mark Russinovich

llms agents robotics fine-tuning benchmarks

arXiv AI

Jun 11

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

arXiv:2602. 05746v2 Announce Type: replace-cross Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still rely on human red-teamers and hand-crafted prompts.

By Xin Chen, Jie Zhang, Florian Tram\`er

llms agents reinforcement-learning fine-tuning safety

arXiv Machine Learning

Oct 8

RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents

arXiv:2610.06401v2 Announce Type: replace-cross Abstract: Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing tr...

By Mohamed Dhouib, Clement Elliker, Alexi Canesse, Ma\"el Jenny, Lucas-Andrei Thil, Mahammed El Sharkawy, Sonia Vanier, Elie Bursztein

llms agents efficiency benchmarks

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

llms agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 30

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

arXiv:2607. 26998v1 Announce Type: cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools.

By Ruoyu Wang, Heng Zhao, Renjie Wu, Mengnan Zhao, Zhixuan Chu, Wanyu Lin, Tianhang Zheng

llms agents

arXiv AI

Oct 16

INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems

INFUSE is a new benchmark that tests indirect prompt injection (IPI) in large‑language‑model agents performing long‑horizon workflows. It contains 40 realistic tasks and 56 attack scenarios across five threat categories, with attacks injected through realistic interaction surfaces rather than just initial prompts. The study evaluated 19 LLMs, generating over 41,000 adversarial trajectories and found mean attack success rates of 19.6% (LLM evaluation) and 15.4% (heuristic verification), while prompt‑level hardening reduced success from 58.2% to 14.3%.

By Thuy Dung Nguyen, Jingyi Guo, Rana Seda Dubauskas, Sreepriya Damuluru, Taylor T. Johnson, Kevin Leach

llms agents multimodal benchmarks safety

Related stories