Privacy-preserving Decentralized Federated Deep Learning
Deep learning has achieved the high-accuracy of state-of-the-art algorithms in long-standing AI tasks.Due to the obvious privacy issues of deep learning,Google proposes Federal Deep Learning(FDL),in which distributed participants only upload local gradi-ents and and a centralized server updates parameters based on the collected gradients.But few users are willing to participate in feder-ated learning due to the lack of contribution evaluation and reward mechanisms.So a decentralized federated deep learning,called DFDL,has been proposed by introducing blockchain to form an effective incentive mechanism for participants.However,DFDL still faces serious privacy issues as blockchain does not guarantee the privacy of training data and model.In this paper,in order to address the aforementioned issues,we propose a new Privacy-preserving DFDL scheme,called PDFDL.With PDFDL,parties can securely learn a global model with their local gradients in the assistance of blockchain,and the parties'sensitive data and the global model are well protected.Specifically,with a secure multi-party aggregation computing,all local gradients are encrypted by their owners before being sent to the smart contract,and can be directly aggregated without decryption.Detailed security analysis shows that PDFDL can resist various known security threats.Moreover,we give an implementation prototype by integrating deep learning module with a Blockchain development platform(Ethereum V1.6.4).We demonstrate the encryption performance and the training accuracy of our PDFDL on benchmark datasets.
federated deep learning privacy-preserving blockchain
Xudong Zhu Hui Li
Xi'an University of Architecture and Technology(XAUAT)Xi'an,Shaanxi,China Xidian University Xi'an,Shaanxi,China
国际会议
2021中国图灵大会(ACM Turing Celebration conference-China 2021
合肥
英文
37-42
2021-07-30（万方平台首次上网日期，不代表论文的发表时间）