【Author】
Weng, Jiasi; Weng, Jian; Zhang, Jilian; Li, Ming; Zhang, Yue; Luo, Weiqi
【Source】IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
【Abstract】Deep learning can achieve higher accuracy than traditional machine learning algorithms in a variety of machine learning tasks. Recently, privacy-preserving deep learning has drawn tremendous attention from information security community, in which neither training data nor the training model is expected to be exposed. Federated learning is a popular learning mechanism, where multiple parties upload local gradients to a server and the server updates model parameters with the collected gradients. However, there are many security problems neglected in federated learning, for example, the participants may behave incorrectly in gradient collecting or parameter updating, and the server may be malicious as well. In this article, we present a distributed, secure, and fair deep learning framework named DeepChain to solve these problems. DeepChain provides a value-driven incentive mechanism based on Blockchain to force the participants to behave correctly. Meanwhile, DeepChain guarantees data privacy for each participant and provides auditability for the whole training process. We implement a prototype of DeepChain and conduct experiments on a real dataset for different settings, and the results show that our DeepChain is promising.
【Keywords】Deep learning; Training; Servers; Blockchain; Collaboration; Training data; Data models; Deep learning; privacy-preserving training; blockchain; incentive
【标题】DeepChain：具有基于区块链的激励的可审计和保护隐私的深度学习
【摘要】在各种机器学习任务中，深度学习可以达到比传统机器学习算法更高的准确率。最近，隐私保护深度学习引起了信息安全界的极大关注，其中训练数据和训练模型预计都不会暴露。联邦学习是一种流行的学习机制，多方将本地梯度上传到服务器，服务器使用收集的梯度更新模型参数。然而，联邦学习中忽略了许多安全问题，例如，参与者可能在梯度收集或参数更新中表现不正确，服务器也可能是恶意的。在本文中，我们提出了一个名为 DeepChain 的分布式、安全和公平的深度学习框架来解决这些问题。 DeepChain 提供基于区块链的价值驱动激励机制，强制参与者正确行为。同时，DeepChain 保证每个参与者的数据隐私，并为整个训练过程提供可审计性。我们实现了 DeepChain 的原型，并对不同设置的真实数据集进行了实验，结果表明我们的 DeepChain 很有前景。
【关键词】深度学习；训练;服务器；区块链；合作;训练数据；数据模型；深度学习；隐私保护培训；区块链；激励
评论