mlsanityData to 7 Oct 2026

Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation

arXiv 2409.01435 ↗First posted 2 Sep 2024cs.LG cs.CR cs.DCcited by 13

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables multiple clients to collaboratively train a model without sharing their local data. Yet the FL system is vulnerable to well-designed Byzantine attacks, which aim to disrupt the model training process by uploading malicious model updates. Existing robust aggregation rule-based defense methods overlook the diversity of magnitude and direction across different layers of the model updates, resulting in limited robustness performance, particularly in non-IID settings. To address these challenges, we propose the Layer-Adaptive Sparsified Model Aggregation (LASA) approach, which combines pre-aggregation sparsification with layer-wise adaptive aggregation to improve robustness. Specifically, LASA includes a pre-aggregation sparsification module that sparsifies updates from each client before aggregation, reducing the impact of malicious parameters and minimizing the interference from less important parameters for the subsequent filtering process. Based on sparsified updates, a layer-wise adaptive filter then adaptively selects benign layers using both magnitude and direction metrics across all clients for aggregation. We provide the detailed theoretical robustness analysis of LASA and the resilience analysis for the FL integrated with LASA. Extensive experiments are conducted on various IID and non-IID datasets. The numerical results demonstrate the effectiveness of LASA. Code is available at urlhttps://github.com/JiiahaoXU/LASA.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 41 of its 60 references that are in the map. First posted on arXiv 2 Sep 2024.

Builds on

41 of 60 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2020Adaptive Federated Optimizationcited by 1,036
  5. 2018LEAF: A Benchmark for Federated Settingscited by 780
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  9. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  10. 2019Why gradient clipping accelerates training: A theoretical justification for adaptivitycited by 335
  11. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  12. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
29 more
  1. 2019Robust Aggregation for Federated Learningcited by 314
  2. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  3. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  4. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  5. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  6. 2020Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropoutcited by 199
  7. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 188
  8. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  9. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  10. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  11. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 95
  12. 2018Generalized Byzantine-tolerant SGDcited by 94
  13. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  14. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 64
  15. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  16. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  17. 2020Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)cited by 54
  18. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  19. 2021Layer-wise Adaptive Model Aggregation for Scalable Federated Learningcited by 35
  20. 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 32
  21. 2023L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learningcited by 29
  22. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 28
  23. 2021Approximate Byzantine Fault-Tolerance in Distributed Optimizationcited by 27
  24. 2020Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarmscited by 26
  25. 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 25
  26. 2018Universal Multi-Party Poisoning Attackscited by 17
  27. 2019Layer-wise Adaptive Gradient Sparsification for Distributed Deep Learning with Convergence Guaranteescited by 8
  28. 2023Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacycited by 8
  29. 2021LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 2.

13 papers.

Sort:

By area:

  1. 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspectioncited by 13
  2. 2024Identify Backdoored Model in Federated Learning via Individual Unlearningcited by 4
  3. 2024Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilitiescited by 3
  4. 2025Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacycited by 1
  5. 2025Heterogeneity-Oblivious Robust Federated Learningcited by 1
  6. 2025Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environmentscited by 1
  7. 2026Safe-FedLLM: Delving into the Safety of Federated Large Language Modelscited by 1
  8. 2024FedSECA: Sign Election and Coordinate-wise Aggregation of Gradients for Byzantine Tolerant Federated Learningcited by 0
  9. 2025Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learningcited by 0
  10. 2025Traceable Black-box Watermarks for Federated Learningcited by 0
  11. 2025Autonomous Cyber Resilience via a Co-Evolutionary Arms Race within a Fortified Digital Twin Sandboxcited by 0
  12. 2025Trade-off in Estimating the Number of Byzantine Clients in Federated Learningcited by 0
1 more
  1. 2026Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learningcited by 0