Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Giskard : Byzantine Robust and Private Aggregation for Large-Scale Decentralized Learning
Ousmane Touat, César Sabater, Mohamed Maouche +1
In decentralized learning, clients train a machine learning model while keeping their data locally and share their model parameters or gradients with a set of neighbors, making it…
cs.CR2025
Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimation
César Sabater, Sonia Ben Mokhtar, Jan Ramon
Achieving differentially private computations in decentralized settings poses significant challenges, particularly regarding accuracy, communication cost, and robustness against in…