Borja Balle

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction

Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD

Scaling Laws for Differentially Private Language Models

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD