mlsanityData to 14 Oct 2026

Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization

arXiv 2502.02096 ↗First posted 4 Feb 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial. Existing generator-based attacks have excellent generalization and transferability due to their instance-agnostic nature. However, when training generators for multi-target tasks, the success rate of transfer attacks is relatively low due to the limitations of the model's capacity. To address these challenges, we propose a novel Dual-Flow framework for multi-target instance-agnostic adversarial attacks, utilizing Cascading Distribution Shift Training to develop an adversarial velocity function. Extensive experiments demonstrate that Dual-Flow significantly improves transferability over previous multi-target generative attacks. For example, it increases the success rate from Inception-v3 to ResNet-152 by 34.58%. Furthermore, our attack method shows substantially stronger robustness against defense mechanisms, such as adversarially trained models. The code of Dual-Flow is available at: hrefhttps://github.com/Chyxx/Dual-Flowhttps://github.com/Chyxx/Dual-Flow.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 58 of its 72 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

58 of 72 references.

References · 58

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  10. 2016Densely Connected Convolutional Networkscited by 6,720
  11. 2022Flow Matching for Generative Modelingcited by 5,702
  12. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
38 more
  1. 2013Intriguing properties of neural networkscited by 5,155
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  3. 2014Going Deeper with Convolutionscited by 4,241
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  11. 2016Universal adversarial perturbationscited by 784
  12. 2021Going deeper with Image Transformerscited by 764
  13. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  14. 2021Transformer in Transformercited by 633
  15. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 602
  16. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  17. 2022Diffusion Models for Adversarial Purificationcited by 476
  18. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  19. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  20. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  21. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  22. 2023Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Modelscited by 324
  23. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  24. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  25. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  26. 2017Generative Adversarial Perturbationscited by 153
  27. 2021Visformer: The Vision-friendly Transformercited by 137
  28. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 94
  29. 2019Cross-Domain Transferability of Adversarial Perturbationscited by 92
  30. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  31. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  32. 2023Content-based Unrestricted Adversarial Attackcited by 73
  33. 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Drivingcited by 72
  34. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  35. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  36. 2021On Generating Transferable Targeted Perturbationscited by 65
  37. 2020Understanding Adversarial Examples from the Mutual Influence of Images and Perturbationscited by 59
  38. 2019Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reductioncited by 47

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Towards Cross-Domain Multi-Targeted Adversarial Attackscited by 0