IEEE Security & Privacy · 2020 · 215 citations · 17 references
ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningSecurity ArchitectureAdversary TechniquesDeep LearningDifferential PrivacyFederated LearningPrivacy Threat ModelingSecure Multi-party ComputationAdaptive Federated LearningAsynchronous Federated LearningFederated Training ArchitectureGradient Leakage AttacksHierarchical Federated LearningPrivacy-by-designPrivacy-by-design RequirementsPrivacy-preserving Learning
Federated learning is a privacy-by-design framework that enables training deep neural networks from decentralized sources of data, but it is fraught with innumerable attack surfaces. We provide a taxonomy of recent attacks on federated learning systems and detail the need for more robust threat modeling in federated learning environments.
17
Membership Inference Attacks Against Machine Learning Models
Reza Shokri, Marco Stronati, Congzheng Song et al. · 2017 · 4.2K citations
Briland Hitaj, Giuseppe Ateniese, Fernando Pérez‐Cruz · 2017 · 1.3K citations · Full text
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
Samuel Yeom, Irene Giacomelli, Matt Fredrikson et al. · 2018 · 904 citations