mlsanityData to 14 Oct 2026

Concept-based Adversarial Attack: a Probabilistic Perspective

arXiv 2507.02965 ↗First posted 30 Jun 2025cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying a single image, our method operates on an entire concept - represented by a distribution - to generate diverse adversarial examples. Preserving the concept is essential, as it ensures that the resulting adversarial images remain identifiable as instances of the original underlying category or identity. By sampling from this concept-based adversarial distribution, we generate images that maintain the original concept but vary in pose, viewpoint, or background, thereby misleading the classifier. Mathematically, this framework remains consistent with traditional adversarial attacks in a principled manner. Our theoretical and empirical results demonstrate that concept-based adversarial attacks yield more diverse adversarial examples and effectively preserve the underlying concept, while achieving higher attack efficiency.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 51 of its 64 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

51 of 64 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  9. 2016Densely Connected Convolutional Networkscited by 6,720
  10. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  11. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  12. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
38 more
  1. 2013Intriguing properties of neural networkscited by 5,155
  2. 2024GPT-4o System Cardcited by 4,588
  3. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  6. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  10. 2016Adversarial Machine Learning at Scalecited by 936
  11. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  12. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  13. 2015Importance Weighted Autoencoderscited by 456
  14. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  15. 2017NIMA: Neural Image Assessmentcited by 389
  16. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  17. 2019Adversarial Examples Improve Image Recognitioncited by 286
  18. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  19. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  20. 2018Spatially Transformed Adversarial Examplescited by 195
  21. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 166
  22. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  23. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  24. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
  25. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 94
  26. 2019ColorFool: Semantic Adversarial Colorizationcited by 89
  27. 2023ARNIQA: Learning Distortion Manifold for Image Quality Assessmentcited by 89
  28. 2018Semantic Adversarial Examplescited by 86
  29. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  30. 2023Content-based Unrestricted Adversarial Attackcited by 73
  31. 2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Modelscited by 46
  32. 2022LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinitycited by 39
  33. 2022Natural Color Fool: Towards Boosting Black-box Unrestricted Attackscited by 38
  34. 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 37
  35. 2020Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learningcited by 33
  36. 2021Towards Understanding the Generative Capability of Adversarially Robust Classifierscited by 26
  37. 2024Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detectorcited by 11
  38. 2025NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusioncited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generationcited by 0
  2. 2026Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoderscited by 0