Blockchain-based Secure Client Selection in Federated Learning
This addresses privacy vulnerabilities in FL systems for distributed learning applications, though it is incremental as it builds on existing secure aggregation methods.
The paper tackles the problem of privacy leakage in Federated Learning (FL) by showing that secure aggregation alone is insufficient, as servers can manipulate client selection to learn local models; it proposes a blockchain-based verifiable client selection protocol to enforce random selection, with security proofs and experiments on an Ethereum-like blockchain demonstrating feasibility.
Despite the great potential of Federated Learning (FL) in large-scale distributed learning, the current system is still subject to several privacy issues due to the fact that local models trained by clients are exposed to the central server. Consequently, secure aggregation protocols for FL have been developed to conceal the local models from the server. However, we show that, by manipulating the client selection process, the server can circumvent the secure aggregation to learn the local models of a victim client, indicating that secure aggregation alone is inadequate for privacy protection. To tackle this issue, we leverage blockchain technology to propose a verifiable client selection protocol. Owing to the immutability and transparency of blockchain, our proposed protocol enforces a random selection of clients, making the server unable to control the selection process at its discretion. We present security proofs showing that our protocol is secure against this attack. Additionally, we conduct several experiments on an Ethereum-like blockchain to demonstrate the feasibility and practicality of our solution.