ShuffleFL
Yuhui Zhang, Zhi-wei Wang, Jiangfeng Cao, Rui Hou, Dan Meng
Abstract
Federated Learning (FL) is a promising approach to privacy-preserving machine learning. However, recent works reveal that gradients can leak private data. Using trusted SGX-processors for this task yields gradient-preserving but requires to prevent exploitation of any side-channel attacks.
Topics & Concepts
Computer scienceTask (project management)Side channel attackComputer securityLeakArtificial intelligenceCryptographyEngineeringSystems engineeringEnvironmental engineeringPrivacy-Preserving Technologies in DataAdversarial Robustness in Machine LearningCryptography and Data Security