326 citations · 600 across the 23 of their papers we have counts for
3 papers · 1 filter
Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)
Wenxuan Bao, Vincent Bindschaedler
There is a flurry of recent research papers proposing novel differentially private machine learning (DPML) techniques. These papers claim to achieve new state-of-the-art (SoTA) res…
DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning
Wenxuan Bao, Francesco Pittaluga, Vijay Kumar B G +1
Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when…
Enhanced Membership Inference Attacks against Machine Learning Models
Jiayuan Ye, Aadyaa Maddi, Sasi Kumar Murakonda +2
How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper,…