mlsanityData to 14 Oct 2026

Adversarial Detection by Approximation of Ensemble Boundary

arXiv 2211.10227 ↗First posted 18 Nov 2022cs.LG cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite being effective in many application areas, Deep Neural Networks (DNNs) are vulnerable to being attacked. In object recognition, the attack takes the form of a small perturbation added to an image, that causes the DNN to misclassify, but to a human appears no different. Adversarial attacks lead to defences that are themselves subject to attack, and the attack/ defence strategies provide important information about the properties of DNNs. In this paper, a novel method of detecting adversarial attacks is proposed for an ensemble of Deep Neural Networks (DNNs) solving two-class pattern recognition problems. The ensemble is combined using Walsh coefficients which are capable of approximating Boolean functions and thereby controlling the decision boundary complexity. The hypothesis in this paper is that decision boundaries with high curvature allow adversarial perturbations to be found, but change the curvature of the decision boundary, which is then approximated in a different way by Walsh coefficients compared to the clean images. Besides controlling boundary complexity, the coefficients also measure the correlation with class labels, which may aid in understanding the learning and transferability properties of DNNs. While the experiments here use images, the proposed approach of modelling two-class ensemble decision boundaries could in principle be applied to any application area.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 62 references that are in the map. First posted on arXiv 18 Nov 2022.

Builds on

24 of 62 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  8. 2016Universal adversarial perturbationscited by 784
  9. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  10. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  11. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  12. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
12 more
  1. 2018Adversarially Robust Generalization Requires More Datacited by 318
  2. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  3. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
  4. 2018Are adversarial examples inevitable?cited by 113
  5. 2016Robustness of classifiers: from adversarial to random noisecited by 88
  6. 2021A Survey On Universal Adversarial Attackcited by 59
  7. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  8. 2017Adversarial Example Defenses: Ensembles of Weak Defenses are not Strongcited by 32
  9. 2020Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustnesscited by 28
  10. 2020Adversarial Examples on Object Recognition: A Comprehensive Surveycited by 23
  11. 2020FADER: Fast Adversarial Example Rejectioncited by 9
  12. 2021Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approachescited by 3

Built on by

Not cited yet.