Communication Dans Un Congrès Année : 2025

Noiseless Privacy-Preserving Decentralized Learning

Résumé

Decentralized learning (DL) enables collaborative learning without a server and without training data leaving the users' devices. However, the models shared in DL can still be used to infer training data. Conventional defenses such as differential privacy and secure aggregation fall short in effectively safeguarding user privacy in DL, either sacrificing model utility or efficiency. We introduce Shatter, a novel DL approach in which nodes create virtual nodes (VNs) to disseminate chunks of their full model on their behalf. This enhances privacy by (i) preventing attackers from collecting full models from other nodes, and (ii) hiding the identity of the original node that produced a given model chunk. We theoretically prove the convergence of Shatter and provide a formal analysis demonstrating how Shatter reduces the efficacy of attacks compared to when exchanging full models between nodes. We evaluate the convergence and attack resilience of Shatter with existing DL algorithms, with heterogeneous datasets, and against three standard privacy attacks. Our evaluation shows that Shatter not only renders these privacy attacks infeasible when each node operates 16 VNs but also exhibits a positive impact on model utility compared to standard DL. In summary, Shatter enhances the privacy of DL while maintaining the utility and efficiency of the model.
Fichier principal
Vignette du fichier
popets-2025-0043.pdf (2.55 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04920384 , version 1 (30-01-2025)

Licence

Identifiants

Citer

Sayan Biswas, Mathieu Even, Anne-Marie Kermarrec, Laurent Massoulié, Rafael Pires, et al.. Noiseless Privacy-Preserving Decentralized Learning. PETS 2025 - 25th Privacy Enhancing Technologies Symposium, Jul 2024, Bristol, United Kingdom. pp.824 - 844, ⟨10.56553/popets-2025-0043⟩. ⟨hal-04920384⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More