一作ICML 2026Poster· Social Aspects / Security
Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
XIANGLIN YANG · Bryan Hooi · Gelei Deng · Tianwei Zhang · Jin Song Dong
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
XIANGLIN YANG · Bryan Hooi · Gelei Deng · Tianwei Zhang · Jin Song Dong
Xiaoyue Lu · XIANGLIN YANG · Haijun Liu · Jiahao Liu · Kuntai Cai · Yan Xiao · Jin Song Dong
The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effect...