mlsanityData to 7 Oct 2026

Adversarial training in communication constrained federated learning

arXiv 2103.01319 ↗First posted 1 Mar 2021cs.LG cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Federated learning enables model training over a distributed corpus of agent data. However, the trained model is vulnerable to adversarial examples, designed to elicit misclassification. We study the feasibility of using adversarial training (AT) in the federated learning setting. Furthermore, we do so assuming a fixed communication budget and non-iid data distribution between participating agents. We observe a significant drop in both natural and adversarial accuracies when AT is used in the federated setting as opposed to centralized training. We attribute this to the number of epochs of AT performed locally at the agents, which in turn effects (i) drift between local models; and (ii) convergence time (measured in number of communication rounds). Towards this end, we propose FedDynAT, a novel algorithm for performing AT in federated setting. Through extensive experimentation we show that FedDynAT significantly improves both natural and adversarial accuracy, as well as model convergence time by reducing the model drift.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 1 Mar 2021.

Builds on

28 of 38 references.

References · 28

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  8. 2019Advances and Open Problems in Federated Learningcited by 3,021
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  11. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  12. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
16 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2013Network In Networkcited by 600
  3. 2020Federated Learning with Matched Averagingcited by 564
  4. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  5. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  6. 2018Certified Defenses against Adversarial Examplescited by 305
  7. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  8. 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
  9. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  10. 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 178
  11. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 158
  12. 2019Overcoming Forgetting in Federated Learning on Non-IID Datacited by 120
  13. 2018Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGDcited by 76
  14. 2020FAT: Federated Adversarial Trainingcited by 23
  15. 2020Local SGD With a Communication Overhead Depending Only on the Number of Workerscited by 13
  16. 2020Improving the affordability of robustness training for DNNscited by 8

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 3; 2024: 5; 2025: 3.

17 papers.

Sort:

By area:

  1. 2023Delving into the Adversarial Robustness of Federated Learningcited by 19
  2. 2021Federated Robustness Propagation: Sharing Robustness in Heterogeneous Federated Learningcited by 9
  3. 2021Certified Federated Adversarial Trainingcited by 6
  4. 2024Towards Robust Federated Learning via Logits Calibration on Non-IID Datacited by 5
  5. 2022Certified Robustness in Federated Learningcited by 4
  6. 2023Combating Exacerbated Heterogeneity for Robust Models in Federated Learningcited by 4
  7. 2024Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Datacited by 4
  8. 2024Identify Backdoored Model in Federated Learning via Individual Unlearningcited by 4
  9. 2022Characterizing Internal Evasion Attacks in Federated Learningcited by 1
  10. 2023Improving Machine Learning Robustness via Adversarial Trainingcited by 1
  11. 2025FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Modelscited by 1
  12. 2022Federated Adversarial Training with Transformerscited by 0
5 more
  1. 2022FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devicescited by 0
  2. 2024FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learningcited by 0
  3. 2024How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?cited by 0
  4. 2025Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approachcited by 0
  5. 2025Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustnesscited by 0