Vulnerability-Aware Instance Reweighting For Adversarial Training
Not on the map. Why?
Abstract (arXiv)
Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most variants of AT algorithms treat every training example equally. However, recent works have shown that better performance is achievable by treating them unequally. In addition, it has been observed that AT exerts an uneven influence on different classes in a training set and unfairly hurts examples corresponding to classes that are inherently harder to classify. Consequently, various reweighting schemes have been proposed that assign unequal weights to robust losses of individual examples in a training set. In this work, we propose a novel instance-wise reweighting scheme. It considers the vulnerability of each natural example and the resulting information loss on its adversarial counterpart occasioned by adversarial attacks. Through extensive experiments, we show that our proposed method significantly improves over existing reweighting schemes, especially against strong white and black-box attacks.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 47 references that are in the map. First posted on arXiv 14 Jul 2023.
Builds on
36 of 47 references.
References · 36
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2018Robustness May Be at Odds with Accuracycited by 880
24 more
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
- 2017Countering Adversarial Images using Input Transformationscited by 520
- 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
- 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2018Adversarial Logit Pairingcited by 224
- 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
- 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
- 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
- 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 172
- 2019Are Labels Required for Improving Adversarial Robustness?cited by 163
- 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
- 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
- 2019Adversarially Robust Generalization Just Requires More Unlabeled Datacited by 76
- 2021Probabilistic Margins for Instance Reweighting in Adversarial Trainingcited by 57
- 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
- 2021Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Modelcited by 37
- 2020Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustnesscited by 11
- 2021Data Quality Matters For Adversarial Training: An Empirical Studycited by 6
- 2023Improving Adversarial Robustness with Hypersphere Embedding and Angular-based Regularizationscited by 5
Built on by
Citing papers per year: 2024: 2.
2 papers.