mlsanityData to 7 Oct 2026

On The Relationship Between Universal Adversarial Attacks And Sparse Representations

arXiv 2311.08265 ↗First posted 14 Nov 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at explaining this vulnerability through the framework of sparsity. We show the connection between adversarial attacks and sparse representations, with a focus on explaining the universality and transferability of adversarial examples in neural networks. To this end, we show that sparse coding algorithms, and the neural network-based learned iterative shrinkage thresholding algorithm (LISTA) among them, suffer from this sensitivity, and that common attacks on neural networks can be expressed as attacks on the sparse representation of the input image. The phenomenon that we observe holds true also when the network is agnostic to the sparse representation and dictionary, and thus can provide a possible explanation for the universality and transferability of adversarial attacks. The code is available at https://github.com/danawr/adversarial_attacks_and_sparse_representations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 49 references that are in the map. First posted on arXiv 14 Nov 2023.

Builds on

40 of 49 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Wide Residual Networkscited by 3,057
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  11. 2016Adversarial Machine Learning at Scalecited by 934
  12. 2016Universal adversarial perturbationscited by 774
28 more
  1. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  2. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  3. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  4. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  5. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  6. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  7. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  8. 2018Adversarially Robust Generalization Requires More Datacited by 318
  9. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  10. 2021Improving Robustness using Generated Datacited by 233
  11. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  12. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  13. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  14. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
  15. 2018Are adversarial examples inevitable?cited by 113
  16. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
  17. 2018Adversarial examples from computational constraintscited by 79
  18. 2018Adversarial vulnerability for any classifiercited by 78
  19. 2018On the Geometry of Adversarial Examplescited by 43
  20. 2018Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressionscited by 31
  21. 2017Learned Convolutional Sparse Codingcited by 26
  22. 2019Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defensescited by 22
  23. 2020Adversarial Robustness of Supervised Sparse Codingcited by 22
  24. 2017Blocking Transferability of Adversarial Examples in Black-Box Learning Systemscited by 19
  25. 2018With Friends Like These, Who Needs Adversaries?cited by 18
  26. 2019Simple iterative method for generating targeted universal adversarial perturbationscited by 13
  27. 2022Adversarial robustness of sparse local Lipschitz predictorscited by 11
  28. 2018Adversarial Noise Attacks of Deep Learning Architectures -- Stability Analysis via Sparse Modeled Signalscited by 9

Built on by

Not cited yet.