Privacy-preserving federated learning based on multi-key homomorphic encryption

dc.contributorAalto Universityen
dc.contributor.authorMa, Jing
dc.contributor.authorNaas, Si-Ahmed
dc.contributor.authorSigg, Stephan
dc.contributor.authorLyu, Xixiang
dc.contributor.departmentXidian University
dc.contributor.departmentAmbient Intelligence
dc.contributor.departmentDepartment of Communications and Networking
dc.descriptionFunding Information: We would like to acknowledge partial funding by the Academy of Finland in the project ABACUS (ICT 2023). The support provided by China Scholarship Council (CSC) during a visit of Jing Ma to Aalto University is acknowledged (file No.201906960151). This study is partially supported by China National Science Foundation under grant number 62072356, and the National Key Research and Development Program of Shaanxi under grant number 2019ZDLGY12‐08. Publisher Copyright: © 2022 Wiley Periodicals LLC
dc.description.abstractWith the advance of machine learning and the Internet of Things (IoT), security and privacy have become critical concerns in mobile services and networks. Transferring data to a central unit violates the privacy of sensitive data. Federated learning mitigates this need to transfer local data by sharing model updates only. However, privacy leakage remains an issue. This paper proposes xMK-CKKS, an improved version of the MK-CKKS multi-key homomorphic encryption protocol, to design a novel privacy-preserving federated learning scheme. In this scheme, model updates are encrypted via an aggregated public key before sharing with a server for aggregation. For decryption, a collaboration among all participating devices is required. Our scheme prevents privacy leakage from publicly shared model updates in federated learning and is resistant to collusion between k < N - 1 participating devices and the server. The evaluation demonstrates that the scheme outperforms other innovations in communication and computational cost while preserving model accuracy.en
dc.description.versionPeer revieweden
dc.identifier.citationMa , J , Naas , S-A , Sigg , S & Lyu , X 2022 , ' Privacy-preserving federated learning based on multi-key homomorphic encryption ' , International Journal of Intelligent Systems , vol. 37 , no. 9 , pp. 5880-5901 .
dc.identifier.otherPURE UUID: b0cdc338-9c07-4552-9918-6c2216d69590
dc.identifier.otherPURE ITEMURL:
dc.identifier.otherPURE LINK:
dc.identifier.otherPURE FILEURL:
dc.publisherJOHN WILEY & SONS
dc.relation.ispartofseriesInternational Journal of Intelligent Systemsen
dc.relation.ispartofseriesVolume 37, issue 9en
dc.titlePrivacy-preserving federated learning based on multi-key homomorphic encryptionen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi