3 papers
cs.CR2024
DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
Jianxin Wei, Ergute Bao, Xiaokui Xiao +1
Nowadays, differential privacy (DP) has become a well-accepted standard for privacy protection, and deep neural networks (DNN) have been immensely successful in machine learning. T…
cs.LG2024
Feature Inference Attack on Shapley Values
Xinjian Luo, Yangfan Jiang, Xiaokui Xiao
As a solution concept in cooperative game theory, Shapley value is highly recognized in model interpretability studies and widely adopted by the leading Machine Learning as a Servi…
cs.LG2024
Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy
Ergute Bao, Yizheng Zhu, Xiaokui Xiao +4
Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern. An effective solution to this problem is to train…