IEEE Security & Privacy · 2019 · 36 citations · 20 references
ComputingComputer ScienceCryptographyMachine LearningPrivacy EngineeringData ProtectionDifferential PrivacyHomomorphic EncryptionInformation-theoretic CryptographyPrivacy-preserving AnalyticsPrivacy-preserving ProtocolsDifferentially Private Deep LearningDifferentially Private Machine LearningPersonal DataPrivacy-preserving ComputationPrivacy-preserving CryptographyPrivacy-preserving LearningPrivacy-preserving Machine LearningPrivate Machine Learning
Emerging complex deep neural networks require vast amounts of data to achieve high precision. However, the information is often collected from user logs and personal data. In this article, we summarize recent cryptographic methodologies for provably privacy-preserving deep learning and inference.
20
Fully homomorphic encryption using ideal lattices
Craig Gentry · 2009 · 6.6K citations
Membership Inference Attacks Against Machine Learning Models
Reza Shokri, Marco Stronati, Congzheng Song et al. · 2017 · 4.2K citations
How to generate and exchange secrets
Andrew Chi-Chih Yao · 1986 · 3.7K citations
Oded Goldreich, Silvio Micali, Avi Wigderson · 1987 · 3.5K citations
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Keith Bonawitz, Vladimir Ivanov, Ben Kreuter et al. · 2017 · 3.4K citations