mlsanityData to 7 Oct 2026

Do We Really Need to Design New Byzantine-robust Aggregation Rules?

arXiv 2501.17381 ↗First posted 29 Jan 2025cs.CR cs.DC cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) allows multiple clients to collaboratively train a global machine learning model through a server, without exchanging their private training data. However, the decentralized aspect of FL makes it susceptible to poisoning attacks, where malicious clients can manipulate the global model by sending altered local model updates. To counter these attacks, a variety of aggregation rules designed to be resilient to Byzantine failures have been introduced. Nonetheless, these methods can still be vulnerable to sophisticated attacks or depend on unrealistic assumptions about the server. In this paper, we demonstrate that there is no need to design new Byzantine-robust aggregation rules; instead, FL can be secured by enhancing the robustness of well-established aggregation rules. To this end, we present FoundationFL, a novel defense mechanism against poisoning attacks. FoundationFL involves the server generating synthetic updates after receiving local model updates from clients. It then applies existing Byzantine-robust foundational aggregation rules, such as Trimmed-mean or Median, to combine clients' model updates with the synthetic ones. We theoretically establish the convergence performance of FoundationFL under Byzantine settings. Comprehensive experiments across several real-world datasets validate the efficiency of our FoundationFL method.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 35 of its 57 references that are in the map. First posted on arXiv 29 Jan 2025.

Builds on

35 of 57 references.

References · 35

  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. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2019Towards Federated Learning at Scale: System Designcited by 826
  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. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  11. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  12. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
23 more
  1. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  2. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  3. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 135
  4. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  5. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  6. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  7. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 84
  8. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  9. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  10. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 65
  11. 2020Mitigating Bias in Federated Learningcited by 56
  12. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  13. 2024Byzantine-Robust Decentralized Federated Learningcited by 47
  14. 2022FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reductioncited by 35
  15. 2022AFLGuard: Byzantine-robust Asynchronous Federated Learningcited by 29
  16. 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learningcited by 25
  17. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  18. 2024Model Poisoning Attacks to Federated Learning via Multi-Round Consistencycited by 18
  19. 2024Poisoning Federated Recommender Systems with Fake Userscited by 15
  20. 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splittingcited by 13
  21. 2024Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attackscited by 11
  22. 2024Poisoning Attacks on Federated Learning-based Wireless Traffic Predictioncited by 10
  23. 2022Securing Federated Sensitive Topic Classification against Poisoning Attackscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

By area:

  1. 2025Traceback of Poisoning Attacks to Retrieval-Augmented Generationcited by 28
  2. 2025Provably Robust Federated Reinforcement Learningcited by 8
  3. 2025Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learningcited by 4
  4. 2025Toward Malicious Clients Detection in Federated Learningcited by 4
  5. 2025Fairness-Constrained Optimization Attack in Federated Learningcited by 1
  6. 2026Beyond Denial-of-Service: The Puppeteer's Attack for Fine-Grained Control in Ranking-Based Federated Learningcited by 1
  7. 2025FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrixcited by 0
  8. 2025Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learningcited by 0
  9. 2026When the Server Steps In: Calibrated Updates for Fair Federated Learningcited by 0
  10. 2026SecureSplit: Mitigating Backdoor Attacks in Split Learningcited by 0
  11. 2026SecureAFL: Secure Asynchronous Federated Learningcited by 0
  12. 2026AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learningcited by 0
1 more
  1. 2026When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learningcited by 0