Privacy-preserving Weighted Federated Learning within Oracle-Aided MPC Framework
It addresses privacy concerns in federated learning for machine learning developers by providing a flexible security framework, though it is incremental as it builds on existing MPC and federated learning concepts.
This paper tackles the problem of privacy-preserving weighted federated learning by introducing a new formalization within an oracle-aided MPC framework, resulting in a decoupled security model that allows developers to choose security tools and a concrete implementation with security guarantees against honest-but-curious adversaries.
This paper studies privacy-preserving weighted federated learning within the oracle-aided multi-party computation (MPC) framework. The contribution of this paper mainly comprises the following three-fold: In the first fold, a new notion which we call weighted federated learning (wFL) is introduced and formalized inspired by McMahan et al.'s seminal paper. The weighted federated learning concept formalized in this paper differs from that presented in McMahan et al.'s paper since both addition and multiplication operations are executed over ciphers in our model while these operations are executed over plaintexts in McMahan et al.'s model. In the second fold, an oracle-aided MPC solution for computing weighted federated learning is formalized by decoupling the security of federated learning systems from that of underlying multi-party computations. Our decoupling formulation may benefit machine learning developers to select their best security practices from the state-of-the-art security tool sets; In the third fold, a concrete solution to the weighted federated learning problem is presented and analysed. The security of our implementation is guaranteed by the security composition theorem assuming that the underlying multiplication algorithm is secure against honest-but-curious adversaries.