Identifying the Truth of Global Model: A Generic Solution to Defend Against Byzantine and Backdoor Attacks in Federated Learning (full version)

Federated Learning (FL) enables multiple parties to train machine learning models collaboratively without sharing the raw training data. However, the federated nature of FL enables malicious clients to influence a trained model by injecting error model updates via Byzantine or backdoor attacks. To detect malicious model updates, a typical approach is to measure the distance between each model update and a textitground-truth model update. To find such textitground-truth model updates, existing defenses either require a benign root dataset on the server (e.g., FLTrust) or simply use trimmed mean or median as the threshold for clipping (e.g., FLAME). However, such benign root datasets are impractical, and the trimmed mean or median may also eliminate contributions from these underrepresented datasets. In this paper, we propose a generic solution, namely FedTruth, to defend against model poisoning attacks in FL, where the textitground-truth model update (i.e., the global model update) will be estimated among all the model updates with dynamic aggregation weights. Specifically, FedTruth does not have specific assumptions on the benign or malicious data distribution or access to a benign root dataset. Moreover, FedTruth considers the potential contributions from all benign clients. Our empirical results show that FedTruth can reduce the impacts of poisoned model updates against both Byzantine and backdoor attacks, and is also efficient in large-scale FL systems.