mlsanityData to 14 Oct 2026

Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learning

arXiv 2208.10273 ↗First posted 14 Aug 2022cs.CR cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Federated learning offers a framework of training a machine learning model in a distributed fashion while preserving privacy of the participants. As the server cannot govern the clients' actions, nefarious clients may attack the global model by sending malicious local gradients. In the meantime, there could also be unreliable clients who are benign but each has a portion of low-quality training data (e.g., blur or low-resolution images), thus may appearing similar as malicious clients. Therefore, a defense mechanism will need to perform a three-fold differentiation which is much more challenging than the conventional (two-fold) case. This paper introduces MUD-HoG, a novel defense algorithm that addresses this challenge in federated learning using long-short history of gradients, and treats the detected malicious and unreliable clients differently. Not only this, but we can also distinguish between targeted and untargeted attacks among malicious clients, unlike most prior works which only consider one type of the attacks. Specifically, we take into account sign-flipping, additive-noise, label-flipping, and multi-label-flipping attacks, under a non-IID setting. We evaluate MUD-HoG with six state-of-the-art methods on two datasets. The results show that MUD-HoG outperforms all of them in terms of accuracy as well as precision and recall, in the presence of a mixture of multiple (four) types of attackers as well as unreliable clients. Moreover, unlike most prior works which can only tolerate a low population of harmful users, MUD-HoG can work with and successfully detect a wide range of malicious and unreliable clients - up to 47.5% and 10%, respectively, of the total population. Our code is open-sourced at https://github.com/LabSAINT/MUD-HoG_Federated_Learning.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 14 Aug 2022.

Builds on

26 of 37 references.

References · 26

  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. 2018How To Backdoor Federated Learningcited by 765
  4. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  5. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  6. 2014SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectivescited by 402
  7. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  8. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  9. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  10. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  11. 2019Can You Really Backdoor Federated Learning?cited by 255
  12. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 149
14 more
  1. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
  2. 2020FedVision: An Online Visual Object Detection Platform Powered by Federated Learningcited by 124
  3. 2018Generalized Byzantine-tolerant SGDcited by 95
  4. 2018Federated Learning for Keyword Spottingcited by 95
  5. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  6. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 88
  7. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  8. 2019Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attackscited by 79
  9. 2021Provably Secure Federated Learning against Malicious Clientscited by 63
  10. 2021Game of Gradients: Mitigating Irrelevant Clients in Federated Learningcited by 35
  11. 2018New Convergence Aspects of Stochastic Gradient Algorithmscited by 30
  12. 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
  13. 2021Untargeted Poisoning Attack Detection in Federated Learning via Behavior Attestationcited by 13
  14. 2021Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Designcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 3.

7 papers.

  1. 2024Tackling Selfish Clients in Federated Learningcited by 3
  2. 2025Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learningcited by 2
  3. 2024Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learningcited by 0
  4. 2025Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learningcited by 0
  5. 2026Can Quantum Federated Learning Withstand Circuit-Level Backdoors?cited by 0
  6. 2026When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defensecited by 0
  7. 2026Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunitiescited by 0