Vulnerabilities in SVHFL: Toward Secure and Verifiable Hybrid Federated Learning

Federated learning (FL) emerges as a promising collaborative framework within the field of machine learning (ML), offering the potential to train ML models on sensitive real-world data while maintaining data privacy. The primary security concerns surrounding FL, particularly the protection of local gradients’ privacy and ensuring the correctness of aggregated gradients, have attracted growing attention in both industry and academia. Recently, Du <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al</i>. proposed SVHFL, a secure and verifiable hybrid FL system. In this context, the term “secure” means that SVHFL functions as a privacy-preserving federated learning (PPFL) system, capable of protecting the privacy of local gradients from being learned by the server (i.e., the aggregator) and the clients, and “verifiable” implies that SVHFL can achieve the aggregation verification, i.e., it guarantees the correctness of aggregated gradients returned by the server. However, in this article, we propose two attacks that compromise SVHFL, demonstrating that SVHFL cannot protect the privacy of local gradients from being learned by the server and the clients. We analyze the internal causes of these privacy breaches in SVHFL and propose alternative solutions to prevent such privacy leaks. We hope that the exposure of these security vulnerabilities will act as a catalyst to prevent similar incidents from occurring in the future design of PPFL systems.