mlsanityData to 14 Oct 2026

Byzantine-Robust Decentralized Federated Learning

arXiv 2406.10416 ↗First posted 14 Jun 2024cs.CR cs.DC cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables multiple clients to collaboratively train machine learning models without revealing their private training data. In conventional FL, the system follows the server-assisted architecture (server-assisted FL), where the training process is coordinated by a central server. However, the server-assisted FL framework suffers from poor scalability due to a communication bottleneck at the server, and trust dependency issues. To address challenges, decentralized federated learning (DFL) architecture has been proposed to allow clients to train models collaboratively in a serverless and peer-to-peer manner. However, due to its fully decentralized nature, DFL is highly vulnerable to poisoning attacks, where malicious clients could manipulate the system by sending carefully-crafted local models to their neighboring clients. To date, only a limited number of Byzantine-robust DFL methods have been proposed, most of which are either communication-inefficient or remain vulnerable to advanced poisoning attacks. In this paper, we propose a new algorithm called BALANCE (Byzantine-robust averaging through local similarity in decentralization) to defend against poisoning attacks in DFL. In BALANCE, each client leverages its own local model as a similarity reference to determine if the received model is malicious or benign. We establish the theoretical convergence guarantee for BALANCE under poisoning attacks in both strongly convex and non-convex settings. Furthermore, the convergence rate of BALANCE under poisoning attacks matches those of the state-of-the-art counterparts in Byzantine-free settings. Extensive experiments also demonstrate that BALANCE outperforms existing DFL methods and effectively defends against poisoning attacks.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 14 Jun 2024.

Builds on

38 of 58 references.

References · 38

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  6. 2018LEAF: A Benchmark for Federated Settingscited by 792
  7. 2018How To Backdoor Federated Learningcited by 765
  8. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  9. 2020The Future of Digital Health with Federated Learningcited by 633
  10. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  11. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  12. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
26 more
  1. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  2. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  3. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  4. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 197
  5. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  6. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  7. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
  8. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 108
  9. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  10. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  11. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  12. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
  13. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
  14. 2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 58
  15. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 57
  16. 2020Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)cited by 54
  17. 2021Consensus Control for Decentralized Deep Learningcited by 49
  18. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  19. 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 30
  20. 2022AFLGuard: Byzantine-robust Asynchronous Federated Learningcited by 29
  21. 2020Byzantine-resilient Decentralized Stochastic Gradient Descentcited by 28
  22. 2024Poisoning Federated Recommender Systems with Fake Userscited by 15
  23. 2022NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Datacited by 12
  24. 2024Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attackscited by 11
  25. 2024Poisoning Attacks on Federated Learning-based Wireless Traffic Predictioncited by 10
  26. 2023Backdoor Attacks in Peer-to-Peer Federated Learningcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 25; 2026: 20.

48 papers.

Sort:

By area:

  1. 2025Traceback of Poisoning Attacks to Retrieval-Augmented Generationcited by 28
  2. 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?cited by 15
  3. 2025Provably Robust Federated Reinforcement Learningcited by 8
  4. 2024Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learningcited by 6
  5. 2025Byzantine-Robust Federated Learning over Ring-All-Reduce Distributed Computingcited by 6
  6. 2025Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainablecited by 6
  7. 2025Poisoning Attacks and Defenses to Federated Unlearningcited by 5
  8. 2025From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challengescited by 4
  9. 2025Toward Malicious Clients Detection in Federated Learningcited by 4
  10. 2024On the Hardness of Decentralized Multi-Agent Policy Evaluation under Byzantine Attackscited by 3
  11. 2025On Model Protection in Federated Learning against Eavesdropping Attackscited by 2
  12. 2026Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learningcited by 2
36 more
  1. 2024ROSS: RObust decentralized Stochastic learning based on Shapley valuescited by 1
  2. 2025Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcarecited by 1
  3. 2025Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learningcited by 1
  4. 2025Screen Before You Fetch: Compressed Byzantine Screening for Decentralized Learning on the Edge-Cloud Continuumcited by 1
  5. 2025Fairness-Constrained Optimization Attack in Federated Learningcited by 1
  6. 2025FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learningcited by 1
  7. 2026Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missionscited by 1
  8. 2025Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learningcited by 0
  9. 2025GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Frameworkcited by 0
  10. 2025Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulatorcited by 0
  11. 2025Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updatescited by 0
  12. 2025ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learningcited by 0
  13. 2025Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learningcited by 0
  14. 2025Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approachcited by 0
  15. 2025FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learningcited by 0
  16. 2025Delta Sum Learning: an approach for fast and global convergence in Gossip Learningcited by 0
  17. 2025DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learningcited by 0
  18. 2025Evidential Trust-Aware Model Personalization in Decentralized Federated Learning for Wearable IoTcited by 0
  19. 2026When the Server Steps In: Calibrated Updates for Fair Federated Learningcited by 0
  20. 2026SecureSplit: Mitigating Backdoor Attacks in Split Learningcited by 0
  21. 2026Trustworthy Blockchain-based Federated Learning for Electronic Health Records: Securing Participant Identity with Decentralized Identifiers and Verifiable Credentialscited by 0
  22. 2026Decentralized Orchestration Architecture for Fluid Computing: A Secure Distributed AI Use Casecited by 0
  23. 2026Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learningcited by 0
  24. 2026Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropoutcited by 0
  25. 2026SecureAFL: Secure Asynchronous Federated Learningcited by 0
  26. 2026AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learningcited by 0
  27. 2026Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learningcited by 0
  28. 2026Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregationcited by 0
  29. 2026Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learningcited by 0
  30. 2026BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learningcited by 0
  31. 2026Optimizing Byzantine Node Placement in Decentralized Federated Learningcited by 0
  32. 2026Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaborationcited by 0
  33. 2026Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaborationcited by 0
  34. 2026DecoyTrace: Toxic Decoys for Active Defense in Decentralized Federated Learningcited by 0
  35. 2026Backdoor Mitigation in Decentralized LLM Fine-Tuningcited by 0
  36. 2026PoCoFL: POlicy-COmpliant Federated Learningcited by 0