English

Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning

Cryptography and Security 2024-04-30 v1 Artificial Intelligence

Abstract

Decentralized learning (DL) offers a novel paradigm in machine learning by distributing training across clients without central aggregation, enhancing scalability and efficiency. However, DL's peer-to-peer model raises challenges in protecting against inference attacks and privacy leaks. By forgoing central bottlenecks, DL demands privacy-preserving aggregation methods to protect data from 'honest but curious' clients and adversaries, maintaining network-wide privacy. Privacy-preserving DL faces the additional hurdle of client dropout, clients not submitting updates due to connectivity problems or unavailability, further complicating aggregation. This work proposes three secret sharing-based dropout resilience approaches for privacy-preserving DL. Our study evaluates the efficiency, performance, and accuracy of these protocols through experiments on datasets such as MNIST, Fashion-MNIST, SVHN, and CIFAR-10. We compare our protocols with traditional secret-sharing solutions across scenarios, including those with up to 1000 clients. Evaluations show that our protocols significantly outperform conventional methods, especially in scenarios with up to 30% of clients dropout and model sizes of up to 10610^6 parameters. Our approaches demonstrate markedly high efficiency with larger models, higher dropout rates, and extensive client networks, highlighting their effectiveness in enhancing decentralized learning systems' privacy and dropout robustness.

Keywords

Cite

@article{arxiv.2404.17984,
  title  = {Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning},
  author = {Ali Reza Ghavamipour and Benjamin Zi Hao Zhao and Fatih Turkmen},
  journal= {arXiv preprint arXiv:2404.17984},
  year   = {2024}
}
R2 v1 2026-06-28T16:08:38.111Z