mlsanityData to 7 Oct 2026

FedRDF: A Robust and Dynamic Aggregation Function against Poisoning Attacks in Federated Learning

arXiv 2402.10082 ↗First posted 15 Feb 2024cs.LG cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine behaviors and poisoning attacks, which can significantly degrade model performance and hinder convergence. The effectiveness of existing approaches to mitigate complex attacks, such as median, trimmed mean, or Krum aggregation functions, has been only partially demonstrated in the case of specific attacks. Our study introduces a novel robust aggregation mechanism utilizing the Fourier Transform (FT), which is able to effectively handling sophisticated attacks without prior knowledge of the number of attackers. Employing this data technique, weights generated by FL clients are projected into the frequency domain to ascertain their density function, selecting the one exhibiting the highest frequency. Consequently, malicious clients' weights are excluded. Our proposed approach was tested against various model poisoning attacks, demonstrating superior performance over state-of-the-art aggregation methods.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 51 references that are in the map. First posted on arXiv 15 Feb 2024.

Builds on

19 of 51 references.

References · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018LEAF: A Benchmark for Federated Settingscited by 780
  3. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  4. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  5. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  6. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  7. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  8. 2019Robust Aggregation for Federated Learningcited by 314
  9. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  10. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  11. 2020Survey of Personalization Techniques for Federated Learningcited by 144
  12. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
7 more
  1. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  2. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  3. 2018Poisoning Attacks to Graph-Based Recommender Systemscited by 52
  4. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
  5. 2021Federated Learning for Malware Detection in IoT Devicescited by 36
  6. 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 29
  7. 2021Evaluating Federated Learning for Intrusion Detection in Internet of Things: Review and Challengescited by 16

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024Federated Learning for Misbehaviour Detection with Variational Autoencoders and Gaussian Mixture Modelscited by 2
  2. 2025FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attackscited by 1
  3. 2024Robust Federated Learning for Wireless Networks: A Demonstration with Channel Estimationcited by 0