mlsanityData to 14 Oct 2026

An Efficient Method for Sample Adversarial Perturbations against Nonlinear Support Vector Machines

arXiv 2206.05664 ↗First posted 12 Jun 2022cs.LG math.OCcited by 1

Not on the map. Why?

Abstract (arXiv)

Adversarial perturbations have drawn great attentions in various machine learning models. In this paper, we investigate the sample adversarial perturbations for nonlinear support vector machines (SVMs). Due to the implicit form of the nonlinear functions mapping data to the feature space, it is difficult to obtain the explicit form of the adversarial perturbations. By exploring the special property of nonlinear SVMs, we transform the optimization problem of attacking nonlinear SVMs into a nonlinear KKT system. Such a system can be solved by various numerical methods. Numerical results show that our method is efficient in computing adversarial perturbations.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 12 Jun 2022.

Builds on

17 of 24 references.

References · 17

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  4. 2016Adversarial Machine Learning at Scalecited by 936
  5. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  6. 2016Universal adversarial perturbationscited by 784
  7. 2017One pixel attack for fooling deep neural networkscited by 582
  8. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  9. 2017Recent Trends in Deep Learning Based Natural Language Processingcited by 263
  10. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  11. 2015Analysis of classifiers' robustness to adversarial perturbationscited by 76
  12. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 66
5 more
  1. 2017NAG: Network for Adversary Generationcited by 51
  2. 2017Art of singular vectors and universal adversarial perturbationscited by 49
  3. 2020CD-UAP: Class Discriminative Universal Adversarial Perturbationcited by 27
  4. 2021An Ambient Intelligence-Based Human Behavior Monitoring Framework for Ubiquitous Environmentscited by 5
  5. 2022Optimization Models and Interpretations for Three Types of Adversarial Perturbations against Support Vector Machinescited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Bilevel Models for Adversarial Learning and A Case Studycited by 0