mlsanityData to 7 Oct 2026

Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection

arXiv 2503.07978 ↗First posted 11 Mar 2025cs.LG cs.CR cs.DCcited by 13

Not on the map. Why?

Abstract (arXiv)

The distributed nature of training makes Federated Learning (FL) vulnerable to backdoor attacks, where malicious model updates aim to compromise the global model's performance on specific tasks. Existing defense methods show limited efficacy as they overlook the inconsistency between benign and malicious model updates regarding both general and fine-grained directions. To fill this gap, we introduce AlignIns, a novel defense method designed to safeguard FL systems against backdoor attacks. AlignIns looks into the direction of each model update through a direction alignment inspection process. Specifically, it examines the alignment of model updates with the overall update direction and analyzes the distribution of the signs of their significant parameters, comparing them with the principle sign across all model updates. Model updates that exhibit an unusual degree of alignment are considered malicious and thus be filtered out. We provide the theoretical analysis of the robustness of AlignIns and its propagation error in FL. Our empirical results on both independent and identically distributed (IID) and non-IID datasets demonstrate that AlignIns achieves higher robustness compared to the state-of-the-art defense methods. The code is available at https://github.com/JiiahaoXU/AlignIns.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

34 of 58 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  6. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  7. 2018How To Backdoor Federated Learningcited by 745
  8. 2019Why gradient clipping accelerates training: A theoretical justification for adaptivitycited by 335
  9. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  10. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  11. 2019Robust Aggregation for Federated Learningcited by 314
  12. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
22 more
  1. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  2. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  3. 2021Federated Learning for Open Bankingcited by 138
  4. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  5. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  6. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  7. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  8. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 64
  9. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  10. 2020Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)cited by 54
  11. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  12. 2022Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learningcited by 33
  13. 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 32
  14. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 28
  15. 2023On the Vulnerability of Backdoor Defenses for Federated Learningcited by 27
  16. 2020Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarmscited by 26
  17. 2022CrowdGuard: Federated Backdoor Detection in Federated Learningcited by 26
  18. 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 25
  19. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  20. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 13
  21. 2022PerDoor: Persistent Non-Uniform Backdoors in Federated Learning using Adversarial Perturbationscited by 5
  22. 2024Identify Backdoored Model in Federated Learning via Individual Unlearningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

13 papers.

Sort:

By area:

  1. 2025Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learningcited by 1
  2. 2025Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacycited by 1
  3. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learningcited by 1
  4. 2025Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMscited by 1
  5. 2025On the Out-of-Distribution Backdoor Attack for Federated Learningcited by 1
  6. 2026FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacementcited by 1
  7. 2026Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learningcited by 1
  8. 2025Traceable Black-box Watermarks for Federated Learningcited by 0
  9. 2025FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learningcited by 0
  10. 2026Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learningcited by 0
  11. 2026FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devicescited by 0
  12. 2026Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learningcited by 0
1 more
  1. 2026Backdoor Mitigation in Decentralized LLM Fine-Tuningcited by 0