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。

2025-09-03 至 2025-09-03 共收录 4 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 越狱攻击 4 篇

2412.05892 2025-09-03 cs.CR cs.AI 80%

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization

Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Ranjie Duan, Xiaoshuang Jia, Shaowei Yuan, Simeng Qin, Zhiqiang Wang, Xiaojun Jia

机构 * Alibaba Group（阿里巴巴集团）； Beijing Electronic Science and Technology Institute（北京电子科技研究所）； Nanjing University（南京大学）； Renmin University of China（中国人民大学）； Northeastern University（东北大学）； BraneMatrix AI ； Nanyang Technological University（南洋理工大学）

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

Comments Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization

2509.00391 2025-09-03 cs.CL cs.AI cs.CR cs.LG 67%

The Resurgence of GCG Adversarial Attacks on Large Language Models

Yuting Tan, Xuying Li, Zhuo Li, Huizhen Shu, Peikang Hu

机构 * HydroX AI San Jose CA USA（HydroX AI）

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

Comments 12 pages, 5 figures

2408.10722 2025-09-03 cs.CL cs.AI 62%

MEGen: Generative Backdoor into Large Language Models via Model Editing

Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang, Hai Zhao, Yun Li, Qianren Wang

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）； Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University（上海交通大学智能交互与认知工程重点实验室）； Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3（上海Web3可信数据流通与治理重点实验室）； Cognitive AI Lab（认知人工智能实验室）

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

Comments ACL 2025 Findings

2408.11727 2025-09-03 cs.CR cs.AI cs.CL cs.SE 62%

Efficient Detection of Toxic Prompts in Large Language Models

Yi Liu, Junzhe Yu, Huijia Sun, Ling Shi, Gelei Deng, Yuqi Chen, Yang Liu

机构 * Nanyang Technological University（南洋理工大学）； ShanghaiTech University（上海科技大学）

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

Comments Accepted by the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024)