paper-with-me

Papers

JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills

2026-08-17 · Xiaoyu Wen, Jiajia Li, Zhida He, Peng Yu, Chenxu Wang, Han Qi, Ziyuan Zhou, Cheng Jin, Ying Wen, Xingcheng Xu, Shuyue Hu, Tianhang Zheng, Chaochao Lu, Qiaosheng Zhang arxiv

Automated red-teaming has produced a growing collection of attack strategies, yet they typically remain scattered across prompts and workflows, making them difficult to systematically integrate, reuse, and improve at scale. We introduce \textsc{JailbreakSkill}, a skill-centric framework for scaling automated red-teaming through reusable and continuously evolving attack capabilities. \textsc{JailbreakSkill} packages existing attack strategies into modular, agent-ready skills that can be directly reused and adaptively selected across tasks and target models. Beyond reuse, it closes the loop between attacking and learning: attack experience is used to diagnose, refine, combine, and discover new skills, which are added back to an ever-growing skill library. This evolution lifts macro-average ASR by 17.5 percentage points on AdvBench and 13.4 points on HarmBench, including a 48.6-point gain against GPT-5.4 on AdvBench, while yielding novel attack strategies such as reframing a direct request as an unfinished document-completion task. Several evolved skills also generalize to unseen prompts and target models without further adaptation. Our code is available at https://github.com/BattleWen/JailbreakSkill.

📄 PDF Abstract BibTeX arXiv:2608.16465

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications

2023-11-14 · Bhaktipriya Radharapu, Kevin Robinson, Lora Aroyo, Preethi Lahoti

Adversarial testing of large language models (LLMs) is crucial for their safe and responsible deployment. We introduce a novel approach for automated generation of adversarial evaluation datasets to test the safety of LL…

DiversityRed Teaming

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

2026-05-10 · Monika Jotautaitė, Maria Angelica Martinez, Ollie Matthews, Tyler Tracy arxiv

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three chall…

PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI

2026-05-07 · Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim, Akshita Jha 외 arxiv

Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models, with growing emphasis on how red-teamers' backgrounds and perspectives…

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs

2025-06-25 · Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung 외 arxiv

Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone…

Code GenerationRed Teaming

PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming

2025-09-03 · Wesley Hanwen Deng, Sunnie S. Y. Kim, Akshita Jha, Ken Holstein 외 arxiv

Recent developments in AI governance and safety research have called for red-teaming methods that can effectively surface potential risks posed by AI models. Many of these calls have emphasized how the identities and bac…