arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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 2 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 隐私与版权 2 篇

2509.02411 2025-09-03 cs.CR cs.AI 57%

A Survey: Towards Privacy and Security in Mobile Large Language Models

Honghui Xu, Kaiyang Li, Wei Chen, Danyang Zheng, Zhiyuan Li, Zhipeng Cai

机构 * Department of Information Technology, Kennesaw State University(肯纳邦大学信息科技系) Department of Computer Science, Georgia State University(佐治亚州立大学计算机科学系) Nexa AI School of Computing and Artificial Intelligence, Southwest Jiaotong University(西南交通大学计算机与人工智能学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19338 2025-09-03 cs.LG cs.CR 57%

Membership Inference Attacks on Large-Scale Models: A Survey

Hengyu Wu, Yang Cao

机构 * Institute of Science Tokyo(东京科学研究所)

专题命中 隐私与版权 :alignment(abstract);分类 cs.LG

Comments Preprint. Submitted for peer review. The final version may differ

详情

展开后加载摘要…

URL PDF HTML 收藏