mlsanityData to 14 Oct 2026

StyLess: Boosting the Transferability of Adversarial Examples

arXiv 2304.11579 ↗First posted 23 Apr 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to attack black-box DNNs with unknown architectures or parameters, which poses threats to many real-world applications. We find that existing transferable attacks do not distinguish between style and content features during optimization, limiting their attack transferability. To improve attack transferability, we propose a novel attack method called style-less perturbation (StyLess). Specifically, instead of using a vanilla network as the surrogate model, we advocate using stylized networks, which encode different style features by perturbing an adaptive instance normalization. Our method can prevent adversarial examples from using non-robust style features and help generate transferable perturbations. Comprehensive experiments show that our method can significantly improve the transferability of adversarial examples. Furthermore, our approach is generic and can outperform state-of-the-art transferable attacks when combined with other attack techniques.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 47 of its 55 references that are in the map. First posted on arXiv 23 Apr 2023.

Builds on

47 of 55 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2016Densely Connected Convolutional Networkscited by 6,720
  8. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  9. 2016Layer Normalizationcited by 5,669
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  11. 2013Intriguing properties of neural networkscited by 5,155
  12. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
35 more
  1. 2016Wide Residual Networkscited by 3,070
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2018Group Normalizationcited by 1,524
  7. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  8. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  9. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  10. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  11. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  12. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  13. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
  14. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  15. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  16. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  17. 2017Universal Style Transfer via Feature Transformscited by 354
  18. 2016A Learned Representation For Artistic Stylecited by 341
  19. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  20. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 167
  21. 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 156
  22. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 140
  23. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  24. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  25. 2022Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfercited by 78
  26. 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 70
  27. 2022Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbationcited by 68
  28. 2020Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferabilitycited by 57
  29. 2020Revisiting Batch Normalization for Improving Corruption Robustnesscited by 55
  30. 2020Transferable Perturbations of Deep Feature Distributionscited by 51
  31. 2020Yet Another Intermediate-Level Attackcited by 35
  32. 2020Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspectivecited by 35
  33. 2020Encoding Robustness to Image Style via Adversarial Feature Perturbationscited by 18
  34. 2020Stylized Adversarial Defensecited by 5
  35. 2020Adversarial Defense by Latent Style Transformationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 1; 2026: 1.

11 papers.

  1. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
  2. 2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Modelscited by 46
  3. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  4. 2024Adversarial Example Soups: Improving Transferability and Stealthiness for Freecited by 6
  5. 2023Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatnesscited by 5
  6. 2024Improving the Transferability of Adversarial Examples by Feature Augmentationcited by 5
  7. 2024Artificial Immune System of Secure Face Recognition Against Adversarial Attackscited by 2
  8. 2025Information-Geometric Inverse Distillation for Enhancing Adversarial Transferabilitycited by 2
  9. 2024Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learningcited by 1
  10. 2024Transferable 3D Adversarial Shape Completion using Diffusion Modelscited by 0
  11. 2026Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examplescited by 0