mlsanityData to 7 Oct 2026

Randomized Adversarial Training via Taylor Expansion

arXiv 2303.10653 ↗First posted 19 Mar 2023cs.LG cs.AIcited by 28

Not on the map. Why?

Abstract (arXiv)

In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples. Adversarial training appears as one of the most successful methods. To deal with both the robustness against adversarial examples and the accuracy over clean examples, many works develop enhanced adversarial training methods to achieve various trade-offs between them. Leveraging over the studies that smoothed update on weights during training may help find flat minima and improve generalization, we suggest reconciling the robustness-accuracy trade-off from another perspective, i.e., by adding random noise into deterministic weights. The randomized weights enable our design of a novel adversarial training method via Taylor expansion of a small Gaussian noise, and we show that the new adversarial training method can flatten loss landscape and find flat minima. With PGD, CW, and Auto Attacks, an extensive set of experiments demonstrate that our method enhances the state-of-the-art adversarial training methods, boosting both robustness and clean accuracy. The code is available at https://github.com/Alexkael/Randomized-Adversarial-Training.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 67 of its 85 references that are in the map. First posted on arXiv 19 Mar 2023.

Builds on

67 of 85 references.

References · 67

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2016Wide Residual Networkscited by 3,057
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  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. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  11. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  12. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
38 more
  1. 2019When Does Label Smoothing Help?cited by 985
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  3. 2018Robustness May Be at Odds with Accuracycited by 873
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  5. 2017Exploring Generalization in Deep Learningcited by 595
  6. 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 527
  7. 2019Fantastic Generalization Measures and Where to Find Themcited by 507
  8. 2020Overfitting in adversarially robust deep learningcited by 504
  9. 2017Sharp Minima Can Generalize For Deep Netscited by 462
  10. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  11. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  12. 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 357
  13. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  14. 2018Adversarially Robust Generalization Requires More Datacited by 318
  15. 2017Information-theoretic analysis of generalization capability of learning algorithmscited by 299
  16. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  17. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  18. 2021Improving Robustness using Generated Datacited by 233
  19. 2018Adversarial Logit Pairingcited by 224
  20. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  21. 2020Bag of Tricks for Adversarial Trainingcited by 199
  22. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  23. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  24. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  25. 2018Robustness via curvature regularization, and vice versacited by 174
  26. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  27. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  28. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  29. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 148
  30. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  31. 2019Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimatescited by 118
  32. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
  33. 2017Fisher-Rao Metric, Geometry, and Complexity of Neural Networkscited by 99
  34. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  35. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 94
  36. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  37. 2018Hessian-based Analysis of Large Batch Training and Robustness to Adversariescited by 87
  38. 2020Adversarial Distributional Training for Robust Deep Learningcited by 79

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 13; 2025: 8; 2026: 1.

28 papers.

Sort:

By area:

  1. 2024Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspectivecited by 28
  2. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  3. 2024Towards Fairness-Aware Adversarial Learningcited by 10
  4. 2025Towards Model Resistant to Transferable Adversarial Examples via Trigger Activationcited by 10
  5. 2023TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Modelscited by 8
  6. 2024TASAR: Transfer-based Attack on Skeletal Action Recognitioncited by 7
  7. 2023Reward Certification for Policy Smoothed Reinforcement Learningcited by 6
  8. 2024Adversarial Training: A Surveycited by 6
  9. 2023Indirect Gradient Matching for Adversarial Robust Distillationcited by 5
  10. 2023Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Trainingcited by 5
  11. 2024Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-offcited by 5
  12. 2025Long-tailed Adversarial Training with Self-Distillationcited by 5
16 more
  1. 2024Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustnesscited by 3
  2. 2024Privacy-preserving Universal Adversarial Defense for Black-box Modelscited by 3
  3. 2024Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectorscited by 3
  4. 2024Artificial Immune System of Secure Face Recognition Against Adversarial Attackscited by 2
  5. 2023Post-train Black-box Defense via Bayesian Boundary Correctioncited by 1
  6. 2024Adversarial Robustness Overestimation and Instability in TRADEScited by 1
  7. 2025Gradient-Free Adversarial Purification with Diffusion Modelscited by 1
  8. 2025D2R: dual regularization loss with collaborative adversarial generation for model robustnesscited by 1
  9. 2025Parameter Interpolation Adversarial Training for Robust Image Classificationcited by 1
  10. 2024Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscapecited by 0
  11. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
  12. 2024Standard-Deviation-Inspired Regularization for Improving Adversarial Robustnesscited by 0
  13. 2025Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classificationcited by 0
  14. 2025Revisiting Adversarial Training under Hyperspectral Imagecited by 0
  15. 2025Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillationcited by 0
  16. 2026S2O: Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 0