差别隐私
计算机科学
信息隐私
隐私保护
差异(会计)
数据挖掘
计算机安全
会计
业务
作者
Baocang Wang,Yange Chen,Hang Jiang,Zhen Zhao
出处
期刊:IEEE Internet of Things Journal
[Institute of Electrical and Electronics Engineers]
日期:2023-09-01
卷期号:10 (17): 15488-15500
被引量:6
标识
DOI:10.1109/jiot.2023.3264259
摘要
Since traditional federated learning (FL) algorithms cannot provide sufficient privacy guarantees, an increasing number of approaches apply local differential privacy (LDP) techniques to FL to provide strict privacy guarantees. However, the privacy budget heavily increases proportionally with the dimension of the parameters, and the large variance generated by the perturbation mechanisms leads to poor performance of the final model. In this article, we propose a novel privacy-preserving edge FL framework based on LDP (PPeFL). Specifically, we present three LDP mechanisms to address the privacy problems in the FL process. The proposed filtering and screening with exponential mechanism (FS-EM) filters out the better parameters for global aggregation based on the contribution of weight parameters to the neural network. Thus, we can not only solve the problem of fast growth of privacy budget when applying perturbation mechanism locally but also greatly reduce the communication costs. In addition, the proposed data perturbation mechanism with stronger privacy (DPM-SP) allows a secondary scrambling of the original data of participants and can provide strong security. Further, a data perturbation mechanism with enhanced utility (DPM-EU) is proposed in order to reduce the variance introduced by the perturbation. Finally, extensive experiments are performed to illustrate that the PPeFL scheme is practical and efficient, providing stronger privacy protection while ensuring utility.
科研通智能强力驱动
Strongly Powered by AbleSci AI