The primary challenge in deploying Large Language Model (LLM) is ensuring its harmlessness. Red team can identify vulnerabilities by attacking LLM to attain safety. However, current efforts heavily rely on single-round prompt designs and unilateral red team optimizations against fixed blue teams. These static approaches lead to significant reductions in generation diversity, known as the mode collapse, which makes it difficult to discover the potential risks in the increasingly complex human-LLM interactions. Here we introduce dynamic Red Team Game (RTG) to comprehensively analyze the multi-round offensive and defensive interactions between red team and blue team. Furthermore, we develop a Gamified Red Team Solver (GRTS) with diversity measures to mitigate mode collapse and theoretically guarantee the convergence of approximate Nash equilibrium which results in better strategies for both teams. Empirical results demonstrate that GRTS explore diverse and implicit attacks to adaptively exploit various LLMs, surpassing the constraints of specific modes. Insightfully, the geometrical structure we unveil of the red team task aligns with the spinning top hypothesis, confirming the necessity of constructing a diverse LLM population as a promising proxy for heterogeneous human expert red-teamers. This paves the way for scalable toxicity detection and safe alignment for LLMs.
Red Teaming LLMs as Socio-Technical Practice: From Exploration and Data Creation to Evaluation
Responsible Tech Research IBM Research Yorktown Heights New York USA(负责技术研究 IBM 研究 Yorktown Heights 新 York 美国);IBM Research(IBM 研究);The Pennsylvania State University(宾夕法尼亚州立大学);University of Notre Dame(诺特达美大学)
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Center for AI Safety(人工智能安全中心);Carnegie Mellon University(卡内基梅隆大学);UC Berkeley(加州大学伯克利分校);Microsoft(微软)
RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models
Fudan University(复旦大学);City University of Hong Kong(香港城市大学);Deakin University(德克萨斯大学);Hon Hai Research Institute(鸿海研究室);Hong Kong University of Science and Technology(香港理工大学)
Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming
Paul G. Allen School of Computer Science & Engineering(保罗·G·艾伦计算机科学与工程学院);IT University of Copenhagen(哥本哈根信息技术大学);Berkeley Center for Human-Compatible AI, UC Berkeley(加州大学伯克利分校伯克利人类兼容人工智能中心);NVIDIA Corporation(英伟达公司)
Capability-Based Scaling Trends for LLM-Based Red-Teaming
ELLIS Institute Tübingen(图宾根ELLIS研究所);Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究所);Tübingen AI Center(图宾根人工智能中心);Foundation AI – Cisco Systems Inc.(AI基础研究机构——思科系统公司);EPFL(苏黎世联邦理工学院)
SocialNLP EmotionGIF 2020 Challenge Overview: Predicting Reaction GIF Categories on Social Media
Taiwan International Graduate Program(台湾国际研究生学程);Institute of Information Science, Academia Sinica(中央研究院资讯科学研究所);Institute of Service Science, National Tsing Hua University(国立清华大学服务科学研究所)