DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) enables decentralized model training without sharing raw data, offering strong privacy guarantees. However, existing FL protocols struggle to defend against Byzantine participants, maintain model utility under non-independent and identically distributed (non-IID) data, and remain lightweight for edge devices. Prior work either assumes trusted hardware, uses expensive cryptographic tools, or fails to address privacy and robustness simultaneously. We propose DSFL, a Dual-Server Byzantine-Resilient Federated Learning framework that addresses these limitations using a group-based secure aggregation approach. Unlike LSFL, which assumes non-colluding semi-honest servers, DSFL removes this dependency by revealing a key vulnerability: privacy leakage through client-server collusion. DSFL introduces three key innovations: (1) a dual-server secure aggregation protocol that protects updates without encryption or key exchange, (2) a group-wise credit-based filtering mechanism to isolate Byzantine clients based on deviation scores, and (3) a dynamic reward-penalty system for enforcing fair participation. DSFL is evaluated on MNIST, CIFAR-10, and CIFAR-100 under up to 30 percent Byzantine participants in both IID and non-IID settings. It consistently outperforms existing baselines, including LSFL, homomorphic encryption methods, and differential privacy approaches. For example, DSFL achieves 97.15 percent accuracy on CIFAR-10 and 68.60 percent on CIFAR-100, while FedAvg drops to 9.39 percent under similar threats. DSFL remains lightweight, requiring only 55.9 ms runtime and 1088 KB communication per round.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 56 references that are in the map. First posted on arXiv 10 Sep 2025.
Builds on
23 of 56 references.
References · 23
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
- 2018How To Backdoor Federated Learningcited by 765
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
- 2018Local SGD Converges Fast and Communicates Littlecited by 605
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
- 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
- 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
- 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
- 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
- 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
11 more
- 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 175
- 2021MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluationcited by 88
- 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
- 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 39
- 2017Byzantine-Tolerant Machine Learningcited by 19
- 2020Secure Byzantine-Robust Machine Learningcited by 19
- 2022How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?cited by 19
- 2022A Secure and Efficient Federated Learning Framework for NLPcited by 9
- 2020Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learningcited by 7
- 2024A Model Consistency-Based Countermeasure to GAN-Based Data Poisoning Attack in Federated Learningcited by 4
- 2024Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learningcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.