ICT Express · 2022 · 20 citations · 5 references
ComputingComputer ScienceDistributed SystemsInformation TheoryMachine LearningData PrivacyData ProtectionFederated LearningFederated Learning PrivacyPrivacy-preserving ProtocolsAggregationCommunication Overhead ReductionPrivacy-preserving LearningPrivate Information RetrievalPrivate Machine LearningProtectionSecure AggregationSecure Data Aggregation
We consider information-theoretic privacy in federated submodel learning, where a global server has multiple submodels. Compared to the privacy considered in the conventional federated submodel learning where secure aggregation is adopted for ensuring privacy, information-theoretic privacy provides the stronger protection on submodel selection by the local machine. We propose an achievable scheme that partially adopts the conventional private information retrieval (PIR) scheme that achieves the minimum amount of download. With respect to computation and communication overhead, we compare the achievable scheme with a naïve approach for federated submodel learning with information-theoretic privacy.
5
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Keith Bonawitz, Vladimir Ivanov, Ben Kreuter et al. · 2017 · 3.4K citations
Benny Chor, Eyal Kushilevitz, Oded Goldreich et al. · Journal of the ACM · 1998 · 1.6K citations · Full text
The Capacity of Private Information Retrieval
Hua Sun, Syed A. Jafar · IEEE Transactions on Information Theory · 2017 · 461 citations
Secure Federated Submodel Learning
Chaoyue Niu, Fan Wu, Shaojie Tang et al. · arXiv (Cornell University) · 2019 · 28 citations · Full text