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。

2025-11-03 至 2025-11-03 共收录 5 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 越狱攻击 5 篇

2510.27172 2025-11-03 cs.LG cs.AI 73%

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Zixuan Hu, Li Shen, Zhenyi Wang, Yongxian Wei, Dacheng Tao

机构 * Nanyang Technological University（南洋理工大学）； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）； University of Central Florida（佛罗里达大学）； Tsinghua University（清华大学）

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

2510.27062 2025-11-03 cs.LG cs.AI 73%

Consistency Training Helps Stop Sycophancy and Jailbreaks

Alex Irpan, Alexander Matt Turner, Mark Kurzeja, David K. Elson, Rohin Shah

机构 * Google（谷歌）

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

Comments 19 pages

2510.26981 2025-11-03 cs.LG cs.AI 73%

Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget

Zhichao Hou, Weizhi Gao, Xiaorui Liu

机构 * North Carolina State University（北卡罗来纳州立大学）

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

2510.26847 2025-11-03 cs.CR cs.AI cs.CL cs.IT math.IT 73%

Broken-Token: Filtering Obfuscated Prompts by Counting Characters-Per-Token

Shaked Zychlinski, Yuval Kainan

机构 * JFrog

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

Comments 16 pages, 9 figures

2508.00943 2025-11-03 cs.CR cs.AI 57%

LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring

Chloe Li, Mary Phuong, Noah Y. Siegel

机构 * University College London（伦敦大学学院）

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

Comments Accepted to IJCNLP-AACL 2025 (Main Conference)