mlsanityData to 7 Oct 2026

NAG: Network for Adversary Generation

arXiv 1712.03390 ↗First posted 9 Dec 2017cs.CV cs.AI cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present optimization approaches that solve for a fooling objective with an imperceptibility constraint to craft the perturbations. However, for a given classifier, they generate one perturbation at a time, which is a single instance from the manifold of adversarial perturbations. Also, in order to build robust models, it is essential to explore the manifold of adversarial perturbations. In this paper, we propose for the first time, a generative approach to model the distribution of adversarial perturbations. The architecture of the proposed model is inspired from that of GANs and is trained using fooling and diversity objectives. Our trained generator network attempts to capture the distribution of adversarial perturbations for a given classifier and readily generates a wide variety of such perturbations. Our experimental evaluation demonstrates that perturbations crafted by our model (i) achieve state-of-the-art fooling rates, (ii) exhibit wide variety and (iii) deliver excellent cross model generalizability. Our work can be deemed as an important step in the process of inferring about the complex manifolds of adversarial perturbations.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 20; 2022: 8; 2023: 9; 2024: 9; 2025: 5.

51 papers.

Sort:

By area:

  1. 2021On Generating Transferable Targeted Perturbationscited by 65
  2. 2021A Survey On Universal Adversarial Attackcited by 59
  3. 2021Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNscited by 57
  4. 2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
  5. 2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Modelscited by 39
  6. 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 36
  7. 2023Downstream-agnostic Adversarial Examplescited by 32
  8. 2024DarkSAM: Fooling Segment Anything Model to Segment Nothingcited by 32
  9. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  10. 2021Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformationscited by 28
  11. 2021Robust Feature-Level Adversaries are Interpretability Toolscited by 27
  12. 2022OPOM: Customized Invisible Cloak towards Face Privacy Protectioncited by 22
38 more
  1. 2023Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregationcited by 22
  2. 2021Generative Dynamic Patch Attackcited by 19
  3. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  4. 2021Stereoscopic Universal Perturbations across Different Architectures and Datasetscited by 17
  5. 2021Universal Spectral Adversarial Attacks for Deformable Shapescited by 14
  6. 2021ADC: Adversarial attacks against object Detection that evade Context consistency checkscited by 12
  7. 2021A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Trackingcited by 9
  8. 2021Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defensescited by 9
  9. 2024Texture Re-scalable Universal Adversarial Perturbationcited by 9
  10. 2021Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashingcited by 8
  11. 2021Semantically Stealthy Adversarial Attacks against Segmentation Modelscited by 7
  12. 2024Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Modelscited by 6
  13. 2021Realizable Universal Adversarial Perturbations for Malwarecited by 5
  14. 2022Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attackscited by 5
  15. 2023A Review of Adversarial Attacks in Computer Visioncited by 5
  16. 2022FG-UAP: Feature-Gathering Universal Adversarial Perturbationcited by 4
  17. 2023SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbationcited by 4
  18. 2025ETA: Energy-based Test-time Adaptation for Depth Completioncited by 4
  19. 2023AdaptGuard: Defending Against Universal Attacks for Model Adaptationcited by 3
  20. 2024Investigating Deep Watermark Security: An Adversarial Transferability Perspectivecited by 3
  21. 2025Data-free Universal Adversarial Perturbation with Pseudo-semantic Priorcited by 3
  22. 2025Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimizationcited by 3
  23. 2021You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queriescited by 2
  24. 2022Optimization Models and Interpretations for Three Types of Adversarial Perturbations against Support Vector Machinescited by 2
  25. 2024Perturbation Towards Easy Samples Improves Targeted Adversarial Transferabilitycited by 2
  26. 2024Joint Universal Adversarial Perturbations with Interpretationscited by 2
  27. 2021Dominant Patterns: Critical Features Hidden in Deep Neural Networkscited by 1
  28. 2021Improving Adversarial Robustness for Free with Snapshot Ensemblecited by 1
  29. 2021On Distinctive Properties of Universal Perturbationscited by 1
  30. 2022An Efficient Method for Sample Adversarial Perturbations against Nonlinear Support Vector Machinescited by 1
  31. 2023FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Maskscited by 1
  32. 2024Sparse and Transferable Universal Singular Vectors Attackcited by 1
  33. 2025Democratic Training Against Universal Adversarial Perturbationscited by 1
  34. 2021On Procedural Adversarial Noise Attack And Defensecited by 0
  35. 2022Potential Auto-driving Threat: Universal Rain-removal Attackcited by 0
  36. 2023Decision-BADGE: Decision-based Adversarial Batch Attack with Directional Gradient Estimationcited by 0
  37. 2023Robust Deep Learning Models Against Semantic-Preserving Adversarial Attackcited by 0
  38. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0

50 most cited of 51 All 51 (JSON)