Ball Differential Privacy: Less Noise, Stronger Reconstruction Defense

Jul 15, 2026

Ball Differential Privacy (Ball-DP) modifies standard differential privacy by enforcing indistinguishability only for substitutions within a bounded ball in embedding space, rather than over all possible records. This approach allows for reduced noise addition while still providing robustness against reconstruction attacks. The paper introduces noise calibrations for convex learning and Ball-ReRo certificates that bound reconstruction success, and demonstrates through experiments on seven benchmarks that Ball-DP achieves improved utility compared to standard DP, particularly at high privacy levels.

Why it matters: Ball-DP provides a practical method to reduce the accuracy cost of differential privacy in machine learning, making privacy-preserving models more feasible when defending against reconstruction attacks.

Full story at: arXiv Cryptography and Security ↗