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 $10^6$ 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.

翻译：去中心化学习（DL）提供了一种新颖的机器学习范式，通过在没有中心聚合的情况下在客户端之间分布训练过程，从而增强可扩展性和效率。然而，去中心化学习的点对点模式在防范推理攻击和隐私泄露方面带来了挑战。通过消除中心瓶颈，去中心化学习需要隐私保护的聚合方法来保护数据免受"诚实但好奇"的客户端和攻击者的侵害，并维护网络范围内的隐私。隐私保护去中心化学习还面临客户端退出这一额外障碍——由于连接问题或不可用性，客户端无法提交更新，这使聚合问题更加复杂。本文提出了三种基于秘密共享的抗退出方案，用于隐私保护的去中心化学习。我们的研究通过在MNIST、Fashion-MNIST、SVHN和CIFAR-10等数据集上的实验，评估了这些协议的效率、性能和准确性。我们在多种场景下（包括多达1000个客户端的情况）将我们的协议与传统的秘密共享解决方案进行了比较。评估结果表明，我们的方法显著优于传统方法，特别是在客户端退出率高达30%且模型规模达到$10^6$个参数的情况下。我们的方法在更大模型、更高退出率和更广泛的客户端网络中展现出明显的高效率，突显了它们在增强去中心化学习系统隐私和抗退出鲁棒性方面的有效性。