期刊
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
卷 18, 期 5, 页码 2438-2455出版社
IEEE COMPUTER SOC
DOI: 10.1109/TDSC.2019.2952332
关键词
Deep learning; Training; Servers; Blockchain; Collaboration; Training data; Data models; Deep learning; privacy-preserving training; blockchain; incentive
类别
资金
- National Natural Science Foundation of China [61872153, 61825203, U1736203, 61732021, 61877029, 61972177]
- Guangdong Provincial Special Funds for Applied Technology Research and Development and Transformation of Key Scientific and Technological Achievements [2017B010124002, 2016B010124009]
- Science and Technology Program of Guangzhou of China [201802010061]
- Guangdong Provincial Basic and Applied Research Major Programme [2019B030302008]
- National Key R&D Program of China [2018YFB1402600, 2018YFB1003701]
- Communication and Computer Network Lab of Guangdong [CCNL201903]
- National Key Research and Development Plan of China [2017YFB0802203]
- Graduate School of Jinan University
Deep learning achieves higher accuracy than traditional machine learning algorithms in various tasks, while privacy-preserving deep learning has recently gained significant attention. Federated learning, a popular mechanism, may neglect security issues such as incorrect behavior from participants or malicious actions from the server. In this article, a distributed, secure, and fair deep learning framework named DeepChain is introduced to address these problems, with a focus on incentive mechanisms and data privacy.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据