mlsanityData to 14 Oct 2026

Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective

arXiv 2306.00353 ↗First posted 1 Jun 2023stat.ML cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose a probabilistic perspective on adversarial examples, allowing us to embed subjective understanding of semantics as a distribution into the process of generating adversarial examples, in a principled manner. Despite significant pixel-level modifications compared to traditional adversarial attacks, our method preserves the overall semantics of the image, making the changes difficult for humans to detect. This extensive pixel-level modification enhances our method's ability to deceive classifiers designed to defend against adversarial attacks. Our empirical findings indicate that the proposed methods achieve higher success rates in circumventing adversarial defense mechanisms, while remaining difficult for human observers to detect.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 39 of its 57 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

39 of 57 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2016Densely Connected Convolutional Networkscited by 6,720
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  11. 2013Intriguing properties of neural networkscited by 5,155
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
27 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  4. 2016Adversarial Machine Learning at Scalecited by 936
  5. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  6. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  7. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  8. 2019Adversarial Examples Improve Image Recognitioncited by 286
  9. 2021How to Train Your Energy-Based Modelscited by 274
  10. 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 243
  11. 2018Spatially Transformed Adversarial Examplescited by 195
  12. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  13. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 113
  14. 2017Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimizationcited by 97
  15. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 94
  16. 2019ColorFool: Semantic Adversarial Colorizationcited by 89
  17. 2018Semantic Adversarial Examplescited by 86
  18. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  19. 2023DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuningcited by 84
  20. 2023Content-based Unrestricted Adversarial Attackcited by 73
  21. 2017A Hitting Time Analysis of Stochastic Gradient Langevin Dynamicscited by 71
  22. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  23. 2018ADef: an Iterative Algorithm to Construct Adversarial Deformationscited by 38
  24. 2022Natural Color Fool: Towards Boosting Black-box Unrestricted Attackscited by 38
  25. 2020Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learningcited by 33
  26. 2021Towards Understanding the Generative Capability of Adversarially Robust Classifierscited by 26
  27. 2018Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastabilitycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalizationcited by 4
  2. 2025Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropoutcited by 3
  3. 2025Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defensecited by 2
  4. 2026AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensorscited by 0