2021/04/16 by Bo Zhao, Peng Sun, Zhao, Bo +7 · 6 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Artificial intelligence #Byzantine architecture #Byzantine fault tolerance #Computer science #Computer security #Convergence (economics) #Cryptography and Data Security #Data mining #Distributed computing #FOS: Computer and information sciences #Federated learning #Independent and identically distributed random variables #Machine Learning (cs.LG) #Machine learning #Mathematics #Privacy-Preserving Technologies in Data #Process (computing) #cs.LG
paper · pdf · doi:10.48550/arxiv.2104.08020
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/04/16 · openalex publication_date 2021/04/16 · arxiv updated 2021/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Federated learning (FL) is a promising privacy-preserving distributed machine learning methodology that allows multiple clients (i.e., workers) to collaboratively train statistical models without disclosing private training data. Due to the characteristics of data remaining localized and the uninspected on-device training process, there may exist Byzantine workers launching data poisoning and model poisoning attacks, which would seriously deteriorate model performance or prevent the model from convergence. Most of the existing Byzantine-robust FL schemes are either ineffective against several advanced poisoning attacks or need to centralize a public validation dataset, which is intractable in FL. Moreover, to the best of our knowledge, none of the existing Byzantine-robust distributed learning methods could well exert its power in Non-Independent and Identically distributed (Non-IID) data among clients. To address these issues, we propose FedCom, a novel Byzantine-robust federated learning framework by incorporating the idea of commitment from cryptography, which could achieve both data poisoning and model poisoning tolerant FL under practical Non-IID data partitions. Specifically, in FedCom, each client is first required to make a commitment to its local training data distribution. Then, we identify poisoned datasets by comparing the Wasserstein distance among commitments submitted by different clients. Furthermore, we distinguish abnormal local model updates from benign ones by testing each local model's behavior on its corresponding data commitment. We conduct an extensive performance evaluation of FedCom. The results demonstrate its effectiveness and superior performance compared to the state-of-the-art Byzantine-robust schemes in defending against typical data poisoning and model poisoning attacks under practical Non-IID data distributions.