mlsanityData to 14 Oct 2026

FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning

arXiv 2404.11905 ↗First posted 18 Apr 2024cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space; however, these methods fail to accurately represent the functionality and structure of local models, resulting in inconsistent performance. Here, we present a new paradigm to defend against poisoning attacks in federated learning using functional mappings of local models based on intermediate outputs. Experiments show that our mechanism is robust under a broad range of computing conditions and advanced attack scenarios, enabling safer collaboration among data-sensitive participants via federated learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

37 of 49 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  7. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  8. 2019Towards Federated Learning at Scale: System Designcited by 832
  9. 2021Model-Contrastive Federated Learningcited by 766
  10. 2018How To Backdoor Federated Learningcited by 765
  11. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  12. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
25 more
  1. 2020Federated Learning with Matched Averagingcited by 564
  2. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  4. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  5. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  6. 2019Robust Aggregation for Federated Learningcited by 317
  7. 2017Certified Defenses for Data Poisoning Attackscited by 303
  8. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  9. 2019Can You Really Backdoor Federated Learning?cited by 255
  10. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  11. 2020Threats to Federated Learning: A Surveycited by 178
  12. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 163
  13. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  14. 2020Self-Knowledge Distillation with Progressive Refinement of Targetscited by 107
  15. 2018Generalized Byzantine-tolerant SGDcited by 95
  16. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 67
  17. 2021Mutual Contrastive Learning for Visual Representation Learningcited by 42
  18. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  19. 2022FedX: Unsupervised Federated Learning with Cross Knowledge Distillationcited by 40
  20. 2021Layer-wise Adaptive Model Aggregation for Scalable Federated Learningcited by 36
  21. 2021Distill on the Go: Online knowledge distillation in self-supervised learningcited by 22
  22. 2023FedDefender: Client-Side Attack-Tolerant Federated Learningcited by 12
  23. 2023Towards Attack-tolerant Federated Learning via Critical Parameter Analysiscited by 7
  24. 2022Knowledge Sharing via Domain Adaptation in Customs Fraud Detectioncited by 5
  25. 2022Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Surveycited by 5

Built on by

Not cited yet.