Privacy and Efficiency of Communications in Federated Split Learning
Privacy and Efficiency of Communications in Federated Split Learning
复制标题
DOI：
10.1109/tbdata.2023.3280405
复制
发表时间：
2023-01
影响因子：
7.2
通讯作者：
Zongshun Zhang;Andrea Pinto;Valeria Turina;Flavio Esposito;I. Matta
中科院分区：
文献类型：
--
作者：
Zongshun Zhang;Andrea Pinto;Valeria Turina;Flavio Esposito;I. Matta
每天，大量敏感数据分布在移动的手机、可穿戴设备和其他传感器上。传统上，这些庞大的数据集是在一个系统上处理的，复杂的模型被训练来做出有价值的预测。最近开发了分布式机器学习技术，如联合学习和分裂学习，以更好地保护用户数据和隐私，同时确保高性能。这两种分布式学习架构各有优缺点。在本文中，我们研究了这些权衡，并提出了一种新的混合联合分裂学习架构，该架构结合了两者的效率和隐私优势。我们的评估展示了我们的混合联合分裂学习方法如何降低运行分布式学习系统的每个客户端所需的处理能力，并减少训练和推理时间，同时保持类似的准确性。我们还讨论了我们的方法对深度学习隐私推断攻击的弹性，并将我们的解决方案与其他最近提出的基准进行了比较。
Every day, large amounts of sensitive data are distributed across mobile phones, wearable devices, and other sensors. Traditionally, these enormous datasets have been processed on a single system, with complex models being trained to make valuable predictions. Distributed machine learning techniques such as Federated and Split Learning have recently been developed to protect user data and privacy better while ensuring high performance. Both of these distributed learning architectures have advantages and disadvantages. In this article, we examine these tradeoffs and suggest a new hybrid Federated Split Learning architecture that combines the efficiency and privacy benefits of both. Our evaluation demonstrates how our hybrid Federated Split Learning approach can lower the amount of processing power required by each client running a distributed learning system, and reduce training and inference time while keeping a similar accuracy. We also discuss the resiliency of our approach to deep learning privacy inference attacks and compare our solution to other recently proposed benchmarks.