Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment

作者：Yuxi Li, Yi Liu, Yuekang Li, Ling Shi, Gelei Deng, Shengquan Chen, Kailong Wang · 发表于：Lecture notes in computer science · 年份：2026 · DOI：10.1007/978-3-032-31583-0_5 · 被引用次数：4 · 研究领域：Adversarial Robustness in Machine Learning、Digital and Cyber Forensics、Digital Media Forensic Detection