mlsanityData to 7 Oct 2026

Adversarial Learning with Cost-Sensitive Classes

arXiv 2101.12372 ↗First posted 29 Jan 2021cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning together to train a model that can distinguish between protected and unprotected classes, such that the protected classes are less vulnerable to adversarial examples. We find in this framework an interesting phenomenon during the training of deep neural networks, called Min-Max property, that is, the absolute values of most parameters in the convolutional layer approach zero while the absolute values of a few parameters are significantly larger becoming bigger. Based on this Min-Max property which is formulated and analyzed in a view of random distribution, we further build a new defense model against adversarial examples for adversarial robustness improvement. An advantage of the built model is that it performs better than the standard one and can combine with adversarial training to achieve an improved performance. It is experimentally confirmed that, regarding the average accuracy of all classes, our model is almost as same as the existing models when an attack does not occur and is better than the existing models when an attack occurs. Specifically, regarding the accuracy of protected classes, the proposed model is much better than the existing models when an attack occurs.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 64 references that are in the map. First posted on arXiv 29 Jan 2021.

Builds on

35 of 64 references.

References · 35

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2016Adversarial Machine Learning at Scalecited by 934
  9. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  11. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  12. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
23 more
  1. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  2. 2019Adversarial Training for Free!cited by 638
  3. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  4. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  5. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  6. 2018Certified Defenses against Adversarial Examplescited by 305
  7. 2017Generating Natural Adversarial Examplescited by 182
  8. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  9. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  10. 2019Adversarial Robustness through Local Linearizationcited by 146
  11. 2019Learning Graph Embedding with Adversarial Training Methodscited by 84
  12. 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
  13. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  14. 2015Learning with a Strong Adversarycited by 68
  15. 2020CAT: Customized Adversarial Training for Improved Robustnesscited by 61
  16. 2017Robustness to Adversarial Examples through an Ensemble of Specialistscited by 21
  17. 2019Improving Adversarial Robustness via Guided Complement Entropycited by 15
  18. 2019ROSA: Robust Salient Object Detection against Adversarial Attackscited by 10
  19. 2018Cost-Sensitive Robustness against Adversarial Examplescited by 9
  20. 2020Using Single-Step Adversarial Training to Defend Iterative Adversarial Examplescited by 9
  21. 2019Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examplescited by 8
  22. 2019Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applicationscited by 3
  23. 2020A Study on the Uncertainty of Convolutional Layers in Deep Neural Networkscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 1.

6 papers.

  1. 2024DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillationcited by 8
  2. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  3. 2023Exploring Robust Features for Improving Adversarial Robustnesscited by 4
  4. 2023Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddingscited by 1
  5. 2023Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradationcited by 1
  6. 2022Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentationcited by 0