Multi-client functional encryption for set intersection with non-monotonic access structures in federated learning

Federated learning (FL) based on cloud servers is a distributed machine learning framework which allows an aggregator and multiple clients to train collaboratively a shared model without exchanging data. Considering the confidentiality of training data, several schemes employing functional encryption (FE) have been presented. However, existing schemes cannot express complex access control policies. In this paper, to realize more flexible and fine-grained access control, we propose a multi-client functional encryption scheme for set intersection with non-monotonic access structures (MCFE-SI-NAS), where multiple clients encrypt their private data independently without any interaction. All ciphertexts are associated with a tag, which can resist “mix-and-match” attacks. Aggregator can aggregate ciphertexts and output the set intersection of any two clients’ plaintexts, but cannot learn anything else. We first formalize the definition and security model for the MCFE-SI-NAS scheme and build a concrete construction based on asymmetric prime-order pairings. The security of the designed scheme is formally proven. Furthermore, we implement our MCFE-SI-NAS scheme and provide its efficiency analysis.