mlsanityData to 14 Oct 2026

DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples

arXiv 2508.13309 ↗First posted 18 Aug 2025cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to align well with human perception, and only a few methods specifically explore perceptually aligned adversarial examples. Moreover, it remains unclear whether insights from Lp-constrained attacks can be effectively leveraged to improve perceptual efficacy. In this paper, we introduce DASH, a fully differentiable meta-attack framework that generates effective and perceptually aligned adversarial examples by strategically composing existing Lp-based attack methods. DASH operates in a multi-stage fashion: at each stage, it aggregates candidate adversarial examples from multiple base attacks using learned, adaptive weights and propagates the result to the next stage. A novel meta-loss function guides this process by jointly minimizing misclassification loss and perceptual distortion, enabling the framework to dynamically modulate the contribution of each base attack throughout the stages. We evaluate DASH on adversarially trained models across CIFAR-10, CIFAR-100, and ImageNet. Despite relying solely on Lp-constrained based methods, DASH significantly outperforms state-of-the-art perceptual attacks such as AdvAD, achieving higher attack success rates (e.g., 20.63% improvement) and superior visual quality, as measured by SSIM, LPIPS, and FID (improvements ≈ of 11, 0.015, and 5.7, respectively). Furthermore, DASH generalizes well to unseen defenses, making it a practical and strong baseline for evaluating robustness without requiring handcrafted adaptive attacks for each new defense.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

38 of 49 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  12. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
26 more
  1. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  3. 2017Countering Adversarial Images using Input Transformationscited by 520
  4. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  5. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  6. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  7. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 316
  8. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
  9. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  10. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 158
  11. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  12. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 96
  13. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 94
  14. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 77
  15. 2019Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distancecited by 73
  16. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  17. 2022A Light Recipe to Train Robust Vision Transformerscited by 64
  18. 2018On the Suitability of Lp-norms for Creating and Preventing Adversarial Examplescited by 58
  19. 2023Decoupled Kullback-Leibler Divergence Losscited by 58
  20. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 56
  21. 2022Efficient and Effective Augmentation Strategy for Adversarial Trainingcited by 43
  22. 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studiescited by 38
  23. 2019Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queriescited by 33
  24. 2020Composite Adversarial Attackscited by 29
  25. 2020Patch-wise++ Perturbation for Adversarial Targeted Attackscited by 19
  26. 2025AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attackscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attackscited by 0
  2. 2026Architectural Design and Performance Analysis of FPGA based AI Accelerators: A Comprehensive Reviewcited by 0