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。

2025-09-09 至 2025-09-09 共收录 3 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 越狱攻击 3 篇

2509.06338 2025-09-09 cs.CR cs.LG 88%

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift

Shuai Yuan, Zhibo Zhang, Yuxi Li, Guangdong Bai, Wang Kailong

机构 * University of Electronic Science and Technology of China（电子科技大学）； Huazhong University of Science and Technology（华中科技大学）； The University of Queensland（昆士兰大学）

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

Comments 16 pages,9 figures

2508.03864 2025-09-09 cs.AI 84%

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety

Zhenyu Pan, Yiting Zhang, Yutong Zhang, Jianshu Zhang, Haozheng Luo, Yuwei Han, Dennis Wu, Hong-Yu Chen, Philip S. Yu, Manling Li, Han Liu

机构 * Northwestern University（西北大学）； University of Illinois at Chicago（伊利诺伊大学香槟分校）

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

Comments accepted by the Trustworthy FMs workshop in ICCV 2025

2509.05471 2025-09-09 cs.CR cs.AI 70%

Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models

Youjia Zheng, Mohammad Zandsalimy, Shanu Sushmita

机构 * Northeastern University（东北大学）； Stevens Institute of Technology（斯蒂文斯理工学院）

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