大模型对齐与安全

Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review

可解释人工智能中的隐私风险与保护方法：一项综述

Sonal Allana, Mohan Kankanhalli, Rozita Dara

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

AI总结 本文通过综述现有文献，探讨了可解释人工智能中隐私风险与保护方法，分析了隐私与可解释性之间的冲突及平衡策略。

Comments Published in Transactions on Machine Learning Research: https://openreview.net/forum?id=q9nykJfzku

Journal ref Transactions on Machine Learning Research, 10/2025, ISSN=2835-8856