Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) shows great promise in large-scale machine learning but introduces new privacy and security challenges. We propose ByITFL and LoByITFL, two novel FL schemes that enhance resilience against Byzantine users while keeping the users' data private from eavesdroppers. To ensure privacy and Byzantine resilience, our schemes build on having a small representative dataset available to the federator and crafting a discriminator function allowing the mitigation of corrupt users' contributions. ByITFL employs Lagrange coded computing and re-randomization, making it the first Byzantine-resilient FL scheme with perfect Information-Theoretic (IT) privacy, though at the cost of a significant communication overhead. LoByITFL, on the other hand, achieves Byzantine resilience and IT privacy at a significantly reduced communication cost, but requires a Trusted Third Party, used only in a one-time initialization phase before training. We provide theoretical guarantees on privacy and Byzantine resilience, along with convergence guarantees and experimental results validating our findings.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 77 references that are in the map. First posted on arXiv 16 Jun 2025.
Builds on
31 of 77 references.
References · 31
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2019Deep Leakage from Gradientscited by 1,021
- 2018LEAF: A Benchmark for Federated Settingscited by 792
- 2018How To Backdoor Federated Learningcited by 765
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
- 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
- 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
19 more
- 2020Byzantine-Resilient Secure Federated Learningcited by 93
- 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 78
- 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
- 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
- 2021EIFFeL: Ensuring Integrity for Federated Learningcited by 28
- 2021RoFL: Robustness of Secure Federated Learningcited by 25
- 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
- 2020Secure Byzantine-Robust Machine Learningcited by 19
- 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
- 2021Secure Byzantine-Robust Distributed Learning via Clusteringcited by 12
- 2022ScionFL: Efficient and Robust Secure Quantized Aggregationcited by 8
- 2024Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromisescited by 7
- 2025Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Associationcited by 7
- 2023DP-BREM: Differentially-Private and Byzantine-Robust Federated Learning with Client Momentumcited by 6
- 2023ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitmentcited by 4
- 2024LoByITFL: Low Communication Secure and Private Federated Learningcited by 3
- 2024No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learningcited by 3
- 2024PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learningcited by 3
- 2025Resource Allocation Driven by Large Models in Future Semantic-Aware Networkscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.