SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios
This work addresses privacy and efficiency challenges in federated learning for cross-device applications, representing an incremental improvement over existing selective encryption methods.
The paper tackles the problem of high overhead and client straggling in Homomorphic Encryption for Federated Learning in cross-device scenarios by proposing SenseCrypt, a sensitivity-guided selective encryption framework, which reduces training time by 58.4%-88.7% compared to traditional methods while maintaining security and accuracy.
Homomorphic Encryption (HE) prevails in securing Federated Learning (FL), but suffers from high overhead and adaptation cost. Selective HE methods, which partially encrypt model parameters by a global mask, are expected to protect privacy with reduced overhead and easy adaptation. However, in cross-device scenarios with heterogeneous data and system capabilities, traditional Selective HE methods deteriorate client straggling, and suffer from degraded HE overhead reduction performance. Accordingly, we 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, we first design a privacy-preserving method to respectively cluster the clients with similar data distributions. Then, we develop a scoring mechanism to deduce the straggler-free ratio of model parameters that can be encrypted by each client per cluster. Finally, for each client, we 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 the 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.