Towards Differentially Private Federated Learning with Untrusted Servers

讲座名称：Towards Differentially Private Federated Learning with Untrusted Servers

讲座人：Yang Cao 副教授

讲座时间：10月27日16:00

讲座地点：腾讯会议直播（ID：125 959 637）

讲座人介绍：

Yang Cao，北海道大学副教授。他于2017年在京都大学信息学研究生院获得博士学位。他的研究兴趣在于数据库、安全和机器学习之间的交集。他在这些领域发表了许多论文，包括SIGMOD、VLDB、ICDE、AAAI、USENIX安全和TKDE等顶级场所。他的两篇论文被选为ICDE 2017和ICME 2020的最佳论文入围者之一。他是2019年IEEE计算机学会日本分会青年作家奖、2021年日本数据库学会神林青年研究员奖的获得者。

讲座内容：

Federated learning has received increasing attention in academia and industry as a new privacy-preserving machine learning paradigm. Unlike traditional machine learning, which requires data collection before training, in federated learning, the clients collaboratively train a model under the coordination of a central server. In particular, the clients only share model updates to the server, and all raw data are stored locally. However, recent studies showed that the model updates might reveal sensitive information to the server. In addition, federated learning itself does not guarantee formal privacy. This talk will review recent advances on differentially private federated learning under untrusted servers, introduce our attempts towards this goal by leveraging LDP, the shuffle model of DP and TEE, and discuss some open problems.

主办单位：计算机科学与技术学院