mlsanityData to 7 Oct 2026

Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability

arXiv 2412.20807 ↗First posted 30 Dec 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

With much longer optimization time than that of untargeted attacks notwithstanding, the transferability of targeted attacks is still far from satisfactory. Recent studies reveal that fine-tuning an existing adversarial example (AE) in feature space can efficiently boost its targeted transferability. However, existing fine-tuning schemes only utilize the endpoint and ignore the valuable information in the fine-tuning trajectory. Noting that the vanilla fine-tuning trajectory tends to oscillate around the periphery of a flat region of the loss surface, we propose averaging over the fine-tuning trajectory to pull the crafted AE towards a more centered region. We compare the proposed method with existing fine-tuning schemes by integrating them with state-of-the-art targeted attacks in various attacking scenarios. Experimental results uphold the superiority of the proposed method in boosting targeted transferability. The code is available at github.com/zengh5/Avg_FT.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 39 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

33 of 39 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2014Conditional Generative Adversarial Netscited by 2,152
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
21 more
  1. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  2. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  3. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  4. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  5. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  6. 2014Learning with Pseudo-Ensemblescited by 241
  7. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  8. 2021Visformer: The Vision-friendly Transformercited by 137
  9. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  10. 2018There Are Many Consistent Explanations of Unlabeled Data: Why You Should Averagecited by 82
  11. 2020Patch-wise Attack for Fooling Deep Neural Networkcited by 78
  12. 2021On Generating Transferable Targeted Perturbationscited by 65
  13. 2020Transferable Perturbations of Deep Feature Distributionscited by 51
  14. 2020Yet Another Intermediate-Level Attackcited by 35
  15. 2021A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attackscited by 33
  16. 2021Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networkscited by 31
  17. 2022Enhancing the Self-Universality for Transferable Targeted Attackscited by 30
  18. 2023Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibrationcited by 18
  19. 2023Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixupcited by 17
  20. 2023LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbationscited by 8
  21. 2024Enhancing targeted transferability via feature space fine-tuningcited by 7

Built on by

Not cited yet.