most citedTowards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)

2 citations · 3 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2025★ 2 cited

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…

cs.LG2023★ 1 cited

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…