method · first seen 4 Oct 2026
automated red teaming
Also: LLM red-teaming
Automatically generating adversarial prompts to find jailbreaks in language models.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Red-TTT: Test-Time Training for Automated Jailbreaking Large Language ModelsPapers · 4 Oct 2026 · Tongyan Hu, Hao Li, Xiaogeng Liu, Ruida Wang, Zhengyu Liu, Shuyao Xu, Ning Zhang…
- ASPIRE: Agentic Safety & Prompt Injection Red-teaming EnginePapers · 6 Oct 2026 · Pengfei He, Deep Mitra, Vishesh Sharma, Jiliang Tang, Vinay S Rao, Tomas Pfister…
- Defensive Sufficiency in a Stackelberg Model of AI SecurityPapers · 7 Oct 2026 · Subhabrata Majumdar, Rajlakshmi Chavan
- REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-TeamingPapers · 11 Oct 2026 · Abrar Alotaibi, Moataz Ahmed
- RedDarwin: Evolving Jailbreak Skills against Frontier LLMsPapers · 14 Oct 2026 · Zhouyuan Ma, Yutao Wu, Hanxun Huang, Xiang Zheng, Yi Liu, Xingjun Ma
- Budgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online FeedbackPapers · 19 Oct 2026 · Zhicheng Fang, Han Sun, Jiachen Lei, Xinyi Fang, Zongmin Zhang, Chenxu Fu, Sizhe…
Latest sources
- Attacker Diversity Reduction in Adaptive LLM Red TeamingPapers · 15 Nov 2026 · Chris Tava
- VAST: Compiling Grounded Vulnerability Scenarios into Verifiable, Multi-Step Environments for Evaluating LLM Red-Team AgentsPapers · 14 Nov 2026 · Zhen Wan
- GreyZone: Production-quality Agentic Application ThreatsPapers · 6 Nov 2026 · Ruoyu Zhou, Shuyao Jiang, Haifeng Ruan, Abhik Roychoudhury
- CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn JailbreakPapers · 29 Oct 2026 · Jialin Song, Xiaodong Liu, Weiwei Yang, Mingqian Feng, Chengquan Guo, Qiyao Ma,…
- The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red TeamingPapers · 26 Oct 2026 · Mintong Kang, Stephen Rawls, Melissa Kazemi Rad, Jian Ni, Bo Li
- Budgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online FeedbackPapers · 19 Oct 2026 · Zhicheng Fang, Han Sun, Jiachen Lei, Xinyi Fang, Zongmin Zhang, Chenxu Fu, Sizhe…
- RedDarwin: Evolving Jailbreak Skills against Frontier LLMsPapers · 14 Oct 2026 · Zhouyuan Ma, Yutao Wu, Hanxun Huang, Xiang Zheng, Yi Liu, Xingjun Ma
- REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-TeamingPapers · 11 Oct 2026 · Abrar Alotaibi, Moataz Ahmed
- Defensive Sufficiency in a Stackelberg Model of AI SecurityPapers · 7 Oct 2026 · Subhabrata Majumdar, Rajlakshmi Chavan
- ASPIRE: Agentic Safety & Prompt Injection Red-teaming EnginePapers · 6 Oct 2026 · Pengfei He, Deep Mitra, Vishesh Sharma, Jiliang Tang, Vinay S Rao, Tomas Pfister…
- Red-TTT: Test-Time Training for Automated Jailbreaking Large Language ModelsPapers · 4 Oct 2026 · Tongyan Hu, Hao Li, Xiaogeng Liu, Ruida Wang, Zhengyu Liu, Shuyao Xu, Ning Zhang…