Buxin Su — accepted AI-conference papers

2025

Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy

Xiang Li, Chendi Wang, Buxin Su, Qi Long, Weijie J Su

NeurIPS 2025spotlight

Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifying the privacy budget of private FL algorithms is challenging due to the co-existence of complex algorithmic components s…

Cited by 0 Source ↗Scholar ↗

2023

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy

Chendi Wang, Buxin Su, Jiayuan Ye, Reza Shokri, Weijie J Su

NeurIPS 2023poster

Differentially private (DP) machine learning algorithms incur many sources of randomness, such as random initialization, random batch subsampling, and shuffling. However, such randomness is difficult to take into account when proving differential privacy bounds because it induces mixture distributio…

Cited by 7 Source ↗PDF ↗Scholar ↗