mlsanityData to 7 Oct 2026

CalFAT: Calibrated Federated Adversarial Training with Label Skewness

arXiv 2205.14926 ↗First posted 30 May 2022cs.LG cs.DCcited by 20

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that, like traditional machine learning, federated learning (FL) is also vulnerable to adversarial attacks. To improve the adversarial robustness of FL, federated adversarial training (FAT) methods have been proposed to apply adversarial training locally before global aggregation. Although these methods demonstrate promising results on independent identically distributed (IID) data, they suffer from training instability on non-IID data with label skewness, resulting in degraded natural accuracy. This tends to hinder the application of FAT in real-world applications where the label distribution across the clients is often skewed. In this paper, we study the problem of FAT under label skewness, and reveal one root cause of the training instability and natural accuracy degradation issues: skewed labels lead to non-identical class probabilities and heterogeneous local models. We then propose a Calibrated FAT (CalFAT) approach to tackle the instability issue by calibrating the logits adaptively to balance the classes. We show both theoretically and empirically that the optimization of CalFAT leads to homogeneous local models across the clients and better convergence points.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 26 of its 50 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

26 of 50 references.

References · 26

  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. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2016Adversarial Machine Learning at Scalecited by 934
  11. 2018Robustness May Be at Odds with Accuracycited by 873
  12. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
14 more
  1. 2020Long-tail learning via logit adjustmentcited by 605
  2. 2020Overfitting in adversarially robust deep learningcited by 504
  3. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  4. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  5. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  6. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  7. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 303
  8. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 258
  9. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  10. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
  11. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  12. 2021Adversarial Robustness under Long-Tailed Distributioncited by 50
  13. 2019Real-World Image Datasets for Federated Learningcited by 30
  14. 2021Imbalanced Adversarial Training with Reweightingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 6; 2025: 4; 2026: 1.

20 papers.

Sort:

  1. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
  2. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  3. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 83
  4. 2023Delving into the Adversarial Robustness of Federated Learningcited by 19
  5. 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splittingcited by 13
  6. 2023FedWon: Triumphing Multi-domain Federated Learning Without Normalizationcited by 11
  7. 2024Adversarial Training: A Surveycited by 6
  8. 2022FedCC: Robust Federated Learning against Model Poisoning Attackscited by 5
  9. 2024Towards Robust Federated Learning via Logits Calibration on Non-IID Datacited by 5
  10. 2024Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Datacited by 4
  11. 2022Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Samplingcited by 3
  12. 2024Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalizationcited by 2
8 more
  1. 2024Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networkscited by 2
  2. 2024FedStein: Enhancing Multi-Domain Federated Learning Through James-Stein Estimatorcited by 1
  3. 2025Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligencecited by 1
  4. 2022Federated Adversarial Training with Transformerscited by 0
  5. 2025Lorica: A Synergistic Fine-Tuning Framework for Advancing Personalized Adversarial Robustnesscited by 0
  6. 2025DART: A Server-side Plug-in for Resource-efficient Robust Federated Learningcited by 0
  7. 2025Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustnesscited by 0
  8. 2026Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneitycited by 0