arXiv Computation and Language November 2, 2026 By Jialin Song, Xiaodong Liu, Weiwei Yang, Mingqian Feng, Chengquan Guo, Qiyao Ma, Carolyn Buractaon, Anson Ho, Wuyang Chen, Christopher White

CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn Jailbreak

Read the original on arXiv Computation and Language →

CoFiBreak introduces a coarse‑to‑fine diversity reward for Group Relative Policy Optimization (GRPO) that enhances the variety of attack strategies in automated red‑teaming of large language models while maintaining high attack success and low inference cost. The coarse reward encourages underrepresented strategies within each GRPO group, and the fine reward discourages reuse of personas, framings, and output formats after harmful‑intent information is removed from prompt embeddings. Trained against Llama3.1‑8B‑Instruct, CoFiBreak achieves 1.6–2.0× more distinct successful strategies than the strongest baseline, attains 98.8% ASR@10 on AdvBench, and transfers effectively to unseen frontier LLMs such as Claude‑Opus‑4.6.

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 Computation and Language.

arXiv Machine Learning

Aug 4

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models

arXiv:2506. 07121v2 Announce Type: replace Abstract: Ensuring the safety and robustness of large language models (LLMs) is a fundamental challenge and a critical prerequisite for the responsible deployment of artificial intelligence.

By Ren-Jian Wang, Ke Xue, Zeyu Qin, Ziniu Li, Sheng Tang, Hao-Tian Li, Shengcai Liu, Zhi Yu, Yuanpeng Tan, Chao Qian

llms rag safety

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

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 15

REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming

arXiv:2610.15513v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teamin...

By Abrar Alotaibi, Moataz Ahmed

llms multimodal benchmarks safety

arXiv AI

Jun 9

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO

arXiv:2606. 09701v1 Announce Type: cross Abstract: AI red teaming must continually adapt to evolving attackers and defenders.

By Blake Bullwinkel, Eugenia Kim, Amanda Minnich, Mark Russinovich

llms reinforcement-learning 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

One email a morning, machine-written

Related stories

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models

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

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

REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO

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