Efficient Vertical Federated Learning with Secure Aggregation
It addresses privacy and efficiency issues in vertical federated learning for applications like financial fraud and disease detection, representing an incremental improvement over existing methods.
The paper tackles the problem of privacy leakage in vertical federated learning by proposing a secure aggregation method, achieving a speedup of 9.1e2 to 3.8e4 compared to homomorphic encryption without impacting training performance.
The majority of work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can train complete models independently. However, in many interesting problems, such as financial fraud detection and disease detection, individual data points are scattered across different clients/organizations in vertical federated learning. Solutions for this type of FL require the exchange of gradients between participants and rarely consider privacy and security concerns, posing a potential risk of privacy leakage. In this work, we present a novel design for training vertical FL securely and efficiently using state-of-the-art security modules for secure aggregation. We demonstrate empirically that our method does not impact training performance whilst obtaining 9.1e2 ~3.8e4 speedup compared to homomorphic encryption (HE).