mlsanityData to 14 Oct 2026

Improving the Transferability of Adversarial Examples via Direction Tuning

arXiv 2303.15109 ↗First posted 27 Mar 2023cs.CV cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although considerable efforts have been developed on improving the transferability of adversarial examples generated by transfer-based adversarial attacks, our investigation found that, the big deviation between the actual and steepest update directions of the current transfer-based adversarial attacks is caused by the large update step length, resulting in the generated adversarial examples can not converge well. However, directly reducing the update step length will lead to serious update oscillation so that the generated adversarial examples also can not achieve great transferability to the victim models. To address these issues, a novel transfer-based attack, namely direction tuning attack, is proposed to not only decrease the update deviation in the large step length, but also mitigate the update oscillation in the small sampling step length, thereby making the generated adversarial examples converge well to achieve great transferability on victim models. In addition, a network pruning method is proposed to smooth the decision boundary, thereby further decreasing the update oscillation and enhancing the transferability of the generated adversarial examples. The experiment results on ImageNet demonstrate that the average attack success rate (ASR) of the adversarial examples generated by our method can be improved from 87.9% to 94.5% on five victim models without defenses, and from 69.1% to 76.2% on eight advanced defense methods, in comparison with that of latest gradient-based attacks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 39 of its 45 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

39 of 45 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  10. 2016Adversarial examples in the physical worldcited by 1,769
  11. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  12. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
27 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  2. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  3. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  4. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  5. 2019Adversarial Training for Free!cited by 643
  6. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  7. 2017Countering Adversarial Images using Input Transformationscited by 520
  8. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  9. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  10. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  11. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  12. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  13. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  14. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  15. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 167
  16. 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 156
  17. 2021Feature Importance-aware Transferable Adversarial Attackscited by 127
  18. 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 99
  19. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
  20. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  21. 2021On Improving Adversarial Transferability of Vision Transformerscited by 70
  22. 2022Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbationcited by 68
  23. 2020Methods for Pruning Deep Neural Networkscited by 49
  24. 2022LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinitycited by 39
  25. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  26. 2023Boosting Adversarial Transferability using Dynamic Cuescited by 5
  27. 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reductioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 1; 2026: 2.

9 papers.

  1. 2024Securely Fine-tuning Pre-trained Encoders Against Adversarial Examplescited by 21
  2. 2025Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferabilitycited by 4
  3. 2024Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examplescited by 2
  4. 2024GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformationcited by 2
  5. 2024Adversarial Examples are Misaligned in Diffusion Model Manifoldscited by 1
  6. 2024SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledgecited by 1
  7. 2024On the Adversarial Transferability of Generalized "Skip Connections"cited by 1
  8. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0
  9. 2026Frame the adversary: a structure-aware attack methodologycited by 0