mlsanityData to 14 Oct 2026

Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols

arXiv 2410.22680 ↗First posted 30 Oct 2024cs.LG cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) paradigms enable large numbers of clients to collaboratively train Machine Learning models on private data. However, due to their multi-party nature, traditional FL schemes are left vulnerable to Byzantine attacks that attempt to hurt model performance by injecting malicious backdoors. A wide variety of prevention methods have been proposed to protect frameworks from such attacks. This paper provides a exhaustive and updated taxonomy of existing methods and frameworks, before zooming in and conducting an in-depth analysis of the strengths and weaknesses of the Robustness of Federated Learning (RoFL) protocol. From there, we propose two novel Sybil-based attacks that take advantage of vulnerabilities in RoFL. Finally, we conclude with comprehensive proposals for future testing, describe and detail implementation of the proposed attacks, and offer direction for improvements in the RoFL protocol as well as Byzantine-robust frameworks as a whole.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 30 Oct 2024.

Builds on

25 of 40 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2020Extracting Training Data from Large Language Modelscited by 2,189
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  6. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  7. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  8. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  9. 2019Robust Aggregation for Federated Learningcited by 317
  10. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  11. 2019Can You Really Backdoor Federated Learning?cited by 255
  12. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
13 more
  1. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 149
  2. 2018Generalized Byzantine-tolerant SGDcited by 95
  3. 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 75
  4. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  5. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 47
  6. 2019Abnormal Client Behavior Detection in Federated Learningcited by 40
  7. 2020Decentralized Federated Learning via SGD over Wireless D2D Networkscited by 33
  8. 2021RoFL: Robustness of Secure Federated Learningcited by 25
  9. 2022Shielding Federated Learning: Robust Aggregation with Adaptive Client Selectioncited by 18
  10. 2019Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasetscited by 8
  11. 2024No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learningcited by 3
  12. 2022Shielding Federated Learning: Mitigating Byzantine Attacks with Less Constraintscited by 2
  13. 2024Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025FedGuard: A Diverse-Byzantine-Robust Mechanism for Federated Learning with Major Malicious Clients ↗
  2. 2021FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning
  3. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
  4. 2026BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
  5. 2026Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learning
  6. 2022An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
  7. 2025Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
  8. 2026FAROS: Robust Federated Learning with Adaptive Scaling against Backdoor Attacks