AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

2025-08-27 至 2025-08-27 共收录 2 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 越狱攻击 2 篇

2504.21038 2025-08-27 cs.CR cs.AI 85%

Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models

Yakai Li, Jiekang Hu, Weiduan Sang, Luping Ma, Dongsheng Nie, Weijuan Zhang, Aimin Yu, Yi Su, Qingjia Huang, Qihang Zhou

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）； Sinochem Energy High-Tech Co., Ltd.（中石化能源高科技有限公司）

专题命中越狱攻击：jailbreak(title,abstract)；alignment(abstract)；safety(abstract)；分类 cs.AI

2508.15648 2025-08-27 cs.CL 83%

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models

Peng Ding, Wen Sun, Dailin Li, Wei Zou, Jiaming Wang, Jiajun Chen, Shujian Huang

专题命中越狱攻击：safety(title,abstract)；alignment(abstract)；分类 cs.CL

Comments Accepted by EMNLP 2025 (Main Conference), 15 pages, 4 figures, 6 tables