Calibrated Adversarial Training
Not on the map. Why?
Abstract (arXiv)
Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient perturbation in the example to flip the model's output while not making severe changes in the example's semantical content. Exuberant change in the semantical content could also change the true label of the example. Adding such examples to the training set results in adverse effects. In this paper, we present the Calibrated Adversarial Training, a method that reduces the adverse effects of semantic perturbations in adversarial training. The method produces pixel-level adaptations to the perturbations based on novel calibrated robust error. We provide theoretical analysis on the calibrated robust error and derive an upper bound for it. Our empirical results show a superior performance of the Calibrated Adversarial Training over a number of public datasets.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 1 Oct 2021.
Builds on
31 of 42 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2016Wide Residual Networkscited by 3,057
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
19 more
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2020Overfitting in adversarially robust deep learningcited by 504
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
- 2018Adversarial Logit Pairingcited by 224
- 2020Understanding and Improving Fast Adversarial Trainingcited by 213
- 2018Robustness via curvature regularization, and vice versacited by 174
- 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
- 2018Curriculum Adversarial Trainingcited by 89
- 2018Improving DNN Robustness to Adversarial Attacks using Jacobian Regularizationcited by 88
- 2018Low Frequency Adversarial Perturbationcited by 80
- 2018Excessive Invariance Causes Adversarial Vulnerabilitycited by 66
- 2020CAT: Customized Adversarial Training for Improved Robustnesscited by 61
- 2019On the Effectiveness of Low Frequency Perturbationscited by 56
- 2019Instance adaptive adversarial training: Improved accuracy tradeoffs in neural netscited by 55
- 2020Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbationscited by 55
- 2020Bridging the Performance Gap between FGSM and PGD Adversarial Trainingcited by 9
- 2021Direction-Aggregated Attack for Transferable Adversarial Examplescited by 6
Built on by
Citing papers per year: 2023: 1.
1 paper.