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。

2025-08-18 至 2025-08-18 共收录 3 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 隐私与版权 3 篇

2508.11579 2025-08-18 cs.CY 57%

Karina LaRubbio, Alyssa Lanter, Seihyun Lee, Mahima Ramesh, Diana Freed

专题命中隐私与版权：safety(abstract)；分类 cs.CY

Comments 3 pages, poster at the Twenty-First Symposium on Usable Privacy and Security (SOUPS) at https://www.usenix.org/conference/soups2025/presentation/larubbio-poster

2508.10482 2025-08-18 cs.CL 57%

Mahdi Dhaini, Stephen Meisenbacher, Ege Erdogan, Florian Matthes, Gjergji Kasneci

专题命中隐私与版权：trustworthy(abstract)；分类 cs.CL

Comments Accepted to AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025)

2508.09186 2025-08-18 cs.CV cs.AI 57%

Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast

机构 * Department of Computer Science Texas A\&M University Corpus Christi, USA（计算机科学系德克萨斯A&M大学科罗拉多州科罗拉多市）

专题命中隐私与版权：trustworthy(abstract)；分类 cs.AI