mlsanityData to 14 Oct 2026

SecureAFL: Secure Asynchronous Federated Learning

arXiv 2604.03862 ↗First posted 4 Apr 2026cs.CR cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables multiple clients to collaboratively train a global machine learning model via a server without sharing their private training data. In traditional FL, the system follows a synchronous approach, where the server waits for model updates from numerous clients before aggregating them to update the global model. However, synchronous FL is hindered by the straggler problem. To address this, the asynchronous FL architecture allows the server to update the global model immediately upon receiving any client's local model update. Despite its advantages, the decentralized nature of asynchronous FL makes it vulnerable to poisoning attacks. Several defenses tailored for asynchronous FL have been proposed, but these mechanisms remain susceptible to advanced attacks or rely on unrealistic server assumptions. In this paper, we introduce SecureAFL, an innovative framework designed to secure asynchronous FL against poisoning attacks. SecureAFL improves the robustness of asynchronous FL by detecting and discarding anomalous updates while estimating the contributions of missing clients. Additionally, it utilizes Byzantine-robust aggregation techniques, such as coordinate-wise median, to integrate the received and estimated updates. Extensive experiments on various real-world datasets demonstrate the effectiveness of SecureAFL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 74 references that are in the map. First posted on arXiv 4 Apr 2026.

Builds on

40 of 74 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2018How To Backdoor Federated Learningcited by 765
  6. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 664
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  8. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  9. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  10. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  11. 2019Asynchronous Federated Optimizationcited by 267
  12. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
28 more
  1. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 149
  2. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  3. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  4. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  5. 2016Asynchronous Stochastic Gradient Descent with Delay Compensationcited by 99
  6. 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
  7. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 90
  8. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  9. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
  10. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  11. 2021Provably Secure Federated Learning against Malicious Clientscited by 63
  12. 2017Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descentcited by 59
  13. 2019Zeno++: Robust Fully Asynchronous SGDcited by 53
  14. 2024Byzantine-Robust Decentralized Federated Learningcited by 48
  15. 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
  16. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 30
  17. 2022AFLGuard: Byzantine-robust Asynchronous Federated Learningcited by 29
  18. 2024Model Poisoning Attacks to Federated Learning via Multi-Round Consistencycited by 18
  19. 2024BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learningcited by 17
  20. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
  21. 2024Poisoning Federated Recommender Systems with Fake Userscited by 15
  22. 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?cited by 15
  23. 2024Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attackscited by 11
  24. 2022RFLBAT: A Robust Federated Learning Algorithm against Backdoor Attackcited by 10
  25. 2024Poisoning Attacks on Federated Learning-based Wireless Traffic Predictioncited by 10
  26. 2025Byzantine-Robust Federated Learning over Ring-All-Reduce Distributed Computingcited by 6
  27. 2025Poisoning Attacks and Defenses to Federated Unlearningcited by 5
  28. 2025Toward Malicious Clients Detection in Federated Learningcited by 4

Built on by

Not cited yet.