mlsanityData to 7 Oct 2026

FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning

arXiv 2312.04432 ↗First posted 7 Dec 2023cs.CR cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a collaborative learning paradigm allowing multiple clients to jointly train a model without sharing their training data. However, FL is susceptible to poisoning attacks, in which the adversary injects manipulated model updates into the federated model aggregation process to corrupt or destroy predictions (untargeted poisoning) or implant hidden functionalities (targeted poisoning or backdoors). Existing defenses against poisoning attacks in FL have several limitations, such as relying on specific assumptions about attack types and strategies or data distributions or not sufficiently robust against advanced injection techniques and strategies and simultaneously maintaining the utility of the aggregated model. To address the deficiencies of existing defenses, we take a generic and completely different approach to detect poisoning (targeted and untargeted) attacks. We present FreqFed, a novel aggregation mechanism that transforms the model updates (i.e., weights) into the frequency domain, where we can identify the core frequency components that inherit sufficient information about weights. This allows us to effectively filter out malicious updates during local training on the clients, regardless of attack types, strategies, and clients' data distributions. We extensively evaluate the efficiency and effectiveness of FreqFed in different application domains, including image classification, word prediction, IoT intrusion detection, and speech recognition. We demonstrate that FreqFed can mitigate poisoning attacks effectively with a negligible impact on the utility of the aggregated model.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 38 of its 78 references that are in the map. First posted on arXiv 7 Dec 2023.

Builds on

38 of 78 references.

References · 38

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  7. 2018On the Spectral Bias of Neural Networkscited by 1,321
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  9. 2018How To Backdoor Federated Learningcited by 745
  10. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  11. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  12. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
26 more
  1. 2017Residual Gated Graph ConvNetscited by 341
  2. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  3. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  4. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  5. 2019Can You Really Backdoor Federated Learning?cited by 250
  6. 2020Learning in the Frequency Domaincited by 196
  7. 2018Training behavior of deep neural network in frequency domaincited by 174
  8. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 155
  9. 2017Accelerated Hierarchical Density Clusteringcited by 100
  10. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  11. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  12. 2018D"IoT: A Federated Self-learning Anomaly Detection System for IoTcited by 89
  13. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  14. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  15. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  16. 2020Backdoor Attack against Speaker Verificationcited by 62
  17. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  18. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 52
  19. 2015End-to-End Text-Dependent Speaker Verificationcited by 49
  20. 2019Eavesdrop the Composition Proportion of Training Labels in Federated Learningcited by 27
  21. 2022CrowdGuard: Federated Backdoor Detection in Federated Learningcited by 26
  22. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  23. 2021Backdoor Attack through Frequency Domaincited by 18
  24. 2022More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networkscited by 15
  25. 2023FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attackscited by 4
  26. 2023FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 14; 2026: 9.

25 papers.

Sort:

By area:

  1. 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?cited by 13
  2. 2025SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)cited by 7
  3. 2025Toward Malicious Clients Detection in Federated Learningcited by 4
  4. 2024BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learningcited by 3
  5. 2024Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoningcited by 1
  6. 2025Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attackscited by 1
  7. 2025Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learningcited by 1
  8. 2025A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learningcited by 1
  9. 2025Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMscited by 1
  10. 2025DEFEND: Poisoned Model Detection and Malicious Client Exclusion Mechanism for Secure Federated Learning-based Road Condition Classificationcited by 1
  11. 2026Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglementcited by 1
  12. 2026Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMscited by 1
13 more
  1. 2025Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Bufferingcited by 0
  2. 2025TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Datacited by 0
  3. 2025Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learningcited by 0
  4. 2025Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updatescited by 0
  5. 2025Hammer and Anvil: Toward a Theory of Backdoors in Federated Learningcited by 0
  6. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinctioncited by 0
  7. 2026TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learningcited by 0
  8. 2026FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learningcited by 0
  9. 2026XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifierscited by 0
  10. 2026Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learningcited by 0
  11. 2026Color Matters: Trigger Color Affects Success in Federated Backdoor Attackscited by 0
  12. 2026Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missionscited by 0
  13. 2026Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learningcited by 0