3 papers
cs.CR2025
Sliced Rényi Pufferfish Privacy: Directional Additive Noise Mechanism and Private Learning with Gradient Clipping
Tao Zhang, Yevgeniy Vorobeychik
We study the design of a privatization mechanism and privacy accounting in the Pufferfish Privacy (PP) family. Specifically, motivated by the curse of dimensionality and lack of pr…
cs.CR2025
Residual-PAC Privacy: Automatic Privacy Control Beyond the Gaussian Barrier
Tao Zhang, Yevgeniy Vorobeychik
The Probably Approximately Correct (PAC) Privacy framework [46] provides a powerful instance-based methodology to preserve privacy in complex data-driven systems. Existing PAC Priv…
cs.CR2024
Bayes-Nash Generative Privacy Against Membership Inference Attacks
Tao Zhang, Rajagopal Venkatesaramani, Rajat K. De +2
Membership inference attacks (MIAs) pose significant privacy risks by determining whether individual data is in a dataset. While differential privacy (DP) mitigates these risks, it…