Revocable Federated Learning: A Benchmark of Federated Forest
This addresses a critical security issue in federated learning for company-level collaborations, preventing conflicts of interest when participants leave, though it is incremental as it builds on existing federated and encryption methods.
The paper tackles the problem of participant revocation in federated learning, where existing frameworks retain data from revoked participants, and proposes RevFRF, a revocable federated random forest framework that securely removes such data using homomorphic encryption, with experimental validation of its security and efficiency.
A learning federation is composed of multiple participants who use the federated learning technique to collaboratively train a machine learning model without directly revealing the local data. Nevertheless, the existing federated learning frameworks have a serious defect that even a participant is revoked, its data are still remembered by the trained model. In a company-level cooperation, allowing the remaining companies to use a trained model that contains the memories from a revoked company is obviously unacceptable, because it can lead to a big conflict of interest. Therefore, we emphatically discuss the participant revocation problem of federated learning and design a revocable federated random forest (RF) framework, RevFRF, to further illustrate the concept of revocable federated learning. In RevFRF, we first define the security problems to be resolved by a revocable federated RF. Then, a suite of homomorphic encryption based secure protocols are designed for federated RF construction, prediction and revocation. Through theoretical analysis and experiments, we show that the protocols can securely and efficiently implement collaborative training of an RF and ensure that the memories of a revoked participant in the trained RF are securely removed.