5 papers
Ball Differential Privacy: How to Mitigate Data Reconstruction with Less Noise
Joseph Margaryan, Nirupam Gupta
Vector embeddings of raw records, while not human-readable, do not preserve record privacy: an adversary can reconstruct training records from a released model even when that model…
Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1
Recent work has established a fundamental trilemma between Byzantine robustness, local differential privacy (LDP), and optimization error in distributed learning. We show that this…
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1
Last-iterate convergence and generalization guarantees in first-order convex learning hinge on the monotonicity of the update operator. While linear averaging preserves the monoton…
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
Diksha Gupta, Antonio Honsell, Chuan Xu +2
Distributed learning enables scalable model training over decentralized data, but remains hindered by Byzantine faults and high communication costs. While both challenges have been…
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1
Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers. Such misbehaviors are commonly modeled as \textit{Byzantine…