activity
20162026
most citedEvaluating Voice Conversion-based Privacy Protection against Informed Attackers

79 citations · 220 across the 50 of their papers we have counts for

collaborators
Showing 2026Show all

13 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run

Mathieu Dagréou, Aurélien Bellet

Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy…

cs.LG2026

Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees

Christian Janos Lebeda, David Erb, Tudor Cebere +1

Random forests are widely used in fields involving sensitive tabular data, but existing approaches to enforcing differential privacy (DP) typically degrade performance to the point…

cs.CR2026

Privacy Auditing with Zero (0) Training Run

Tudor Cebere, Mathieu Even, Linus Bleistein +1

Privacy auditing provides empirical lower bounds on the differential privacy parameters of learning algorithms. Existing methods, however, require interventional access to the trai…

cs.LG2026

Loss Gap Parity for Fairness in Heterogeneous Federated Learning

Brahim Erraji, Michaël Perrot, Aurélien Bellet

While clients may join federated learning to improve performance on data they rarely observe locally, they often remain self-interested, expecting the global model to perform well…