mlsanityData to 14 Oct 2026

Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning

arXiv 2208.09894 ↗First posted 21 Aug 2022cs.LG cs.AI cs.CRcited by 8

Not on the map. Why?

Abstract (arXiv)

The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of particular concern, which refers to the possibility of malicious clients participating in the learning process. Hence, a crucial objective in FL is to neutralize the potential impact of Byzantine attacks and to ensure that the final model is trustable. It has been observed that the higher the variance among the clients' models/updates, the more space there is for Byzantine attacks to be hidden. As a consequence, by utilizing momentum, and thus, reducing the variance, it is possible to weaken the strength of known Byzantine attacks. The centered clipping (CC) framework has further shown that the momentum term from the previous iteration, besides reducing the variance, can be used as a reference point to neutralize Byzantine attacks better. In this work, we first expose vulnerabilities of the CC framework, and introduce a novel attack strategy that can circumvent the defences of CC and other robust aggregators and reduce their test accuracy up to %33 on best-case scenarios in image classification tasks. Then, we propose a new robust and fast defence mechanism that is effective against the proposed and other existing Byzantine attacks.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 45 of its 72 references that are in the map. First posted on arXiv 21 Aug 2022.

Builds on

45 of 72 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  8. 2019Advances and Open Problems in Federated Learningcited by 3,046
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  10. 2018Group Normalizationcited by 1,524
  11. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  12. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
33 more
  1. 2018How To Backdoor Federated Learningcited by 765
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  3. 2020The Future of Digital Health with Federated Learningcited by 633
  4. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  5. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  6. 2019Hidden Trigger Backdoor Attackscited by 371
  7. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  8. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  9. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  10. 2019Robust Aggregation for Federated Learningcited by 317
  11. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  12. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  13. 2019Can You Really Backdoor Federated Learning?cited by 255
  14. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  15. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  16. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  17. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  18. 2019SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentumcited by 121
  19. 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 118
  20. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
  21. 2020Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNscited by 104
  22. 2018Generalized Byzantine-tolerant SGDcited by 95
  23. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  24. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  25. 2019Abnormal Client Behavior Detection in Federated Learningcited by 40
  26. 2019The intriguing role of module criticality in the generalization of deep networkscited by 40
  27. 2019Data Poisoning Attacks to Local Differential Privacy Protocolscited by 26
  28. 2020Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcarecited by 18
  29. 2021Dopamine: Differentially Private Federated Learning on Medical Datacited by 18
  30. 2020Towards an Adversarially Robust Normalization Approachcited by 9
  31. 2021Escaping Saddle Points Faster with Stochastic Momentumcited by 8
  32. 2022Towards Communication-Learning Trade-off for Federated Learning at the Network Edgecited by 5
  33. 2021LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 3.

8 papers.

  1. 2023Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Ratescited by 12
  2. 2023Can Decentralized Learning be more robust than Federated Learning?cited by 6
  3. 2025Smoothed Normalization for Efficient Distributed Private Optimizationcited by 3
  4. 2024On the Conflict of Robustness and Learning in Collaborative Machine Learningcited by 1
  5. 2024Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learningcited by 0
  6. 2024FedSECA: Sign Election and Coordinate-wise Aggregation of Gradients for Byzantine Tolerant Federated Learningcited by 0
  7. 2025Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learningcited by 0
  8. 2025Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updatescited by 0