#成员推断

2 stories · 0 in 7 days · 1 in 30 days

Membership Inference Attacks 1 OP-Print 1 权重谱 1 自蒸馏 1 蒸馏 1 隐私 1 隐私泄露 1

Stories, products and papers tagged "成员推断", newest first.

Oct 23

Papers Builders11:28

Chinese contentOP-Print：针对在线自蒸馏模型的成员推断攻击研究

一篇隐私方向的新论文：自蒸馏模型原来会留下可被攻击的训练数据痕迹，OP-Print 用残差信号和重启稳定性就能把成员识别出来，基线全都失效。

#成员推断 #自蒸馏 #OP-Print #隐私

arXiv cs.LG@Qi Li, Xinchao WangSource

Sep 11

Papers BuildersSelected11:22

Predicting Privacy Leakage from Weight Spectral Density

This research provides a new method for evaluating privacy risks in machine learning models, which is important for developers and researchers working on AI systems.

#membership inference attacks #privacy leakage #spectral analysis #machine learning

arXiv cs.LG@Richard J. Preen, Jim SmithSource