面向跨设备联邦学习的敏感性导向选择性同态加密框架

同态加密 (HE) 在 securing Federated Learning (FL) 中占据主导地位，但 suffers from high overhead and adaptation cost。Selective HE methods，which partially encrypt model parameters by global mask，are expected to protect privacy with reduced overhead and easy adaptation。However，在 cross-device scenarios with heterogeneous data and system capabilities 中，traditional Selective HE methods deteriorate client straggling，and suffer from degraded HE overhead reduction performance. Accordingly，我们 propose SenseCrypt，a Sensitivity-guided selective Homomorphic EnCryption framework，to adaptively balance security and HE overhead per cross-device FL client。Given the observation that model parameter sensitivity is effective for measuring clients' data distribution similarity，我们 first design privacy-preserving method to respectively cluster clients with similar data distributions。Then，我们 develop scoring mechanism to deduce straggler-free ratio of model parameters that can be encrypted by each client per cluster。Finally，for each client，我们 formulate and solve a multi-objective model parameter selection optimization problem，which minimizes HE overhead while maximizing model security without causing straggling。Experiments demonstrate that SenseCrypt ensures security against state-of-the-art inversion attacks，while achieving normal model accuracy as on IID data，and reducing training time by 58.4%-88.7% as compared to traditional HE methods。