arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Machine Learning · 会议 · Machine Learning

2026-01-22 至 2026-01-22 共收录 1
2410.08864 2026-01-22 cs.LG cs.AI cs.CR

The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses

好坏与丑:水印、可转移攻击和对抗防御的元分析

Grzegorz Głuch, Berkant Turan, Sai Ganesh Nagarajan, Sebastian Pokutta

AI总结 本文通过元分析探讨了水印、可转移攻击和对抗防御之间的权衡,证明了三者中至少存在其一,并利用全同态加密构建了可转移攻击的实例。

Comments 47 pages, 3 figures, 4 tables, preliminary version published in ICML 2024 (Workshop on Theoretical Foundations of Foundation Models) and , see https://openreview.net/pdf?id=WMaFRiggwV

详情

展开后加载摘要…

URL PDF HTML 收藏