mlsanityData to 14 Oct 2026

A Review of Adversarial Attacks in Computer Vision

arXiv 2308.07673 ↗First posted 15 Aug 2023cs.CV stat.CO stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have been widely used in various downstream tasks, especially those safety-critical scenario such as autonomous driving, but deep networks are often threatened by adversarial samples. Such adversarial attacks can be invisible to human eyes, but can lead to DNN misclassification, and often exhibits transferability between deep learning and machine learning models and real-world achievability. Adversarial attacks can be divided into white-box attacks, for which the attacker knows the parameters and gradient of the model, and black-box attacks, for the latter, the attacker can only obtain the input and output of the model. In terms of the attacker's purpose, it can be divided into targeted attacks and non-targeted attacks, which means that the attacker wants the model to misclassify the original sample into the specified class, which is more practical, while the non-targeted attack just needs to make the model misclassify the sample. The black box setting is a scenario we will encounter in practice.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 53 of its 69 references that are in the map. First posted on arXiv 15 Aug 2023.

Builds on

53 of 69 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2016Pyramid Scene Parsing Networkcited by 2,479
  9. 2016Adversarial examples in the physical worldcited by 1,769
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  11. 2016Adversarial Machine Learning at Scalecited by 936
  12. 2016Practical Black-Box Attacks against Machine Learningcited by 903
38 more
  1. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  2. 2016Universal adversarial perturbationscited by 784
  3. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  4. 2017One pixel attack for fooling deep neural networkscited by 582
  5. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  6. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  7. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  8. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  9. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  10. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  11. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  12. 2018Physical Adversarial Examples for Object Detectorscited by 163
  13. 2017Generative Adversarial Perturbationscited by 153
  14. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
  15. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  16. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  17. 2018Transferable Adversarial Attacks for Image and Video Object Detectioncited by 109
  18. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 98
  19. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  20. 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
  21. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  22. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 72
  23. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 66
  24. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 62
  25. 2020Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferabilitycited by 57
  26. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  27. 2017NAG: Network for Adversary Generationcited by 51
  28. 2020Transferable Perturbations of Deep Feature Distributionscited by 51
  29. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  30. 2017Adversarial Examples that Fool Detectorscited by 40
  31. 2018Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentationcited by 40
  32. 2017Adversarial Examples for Semantic Image Segmentationcited by 33
  33. 2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
  34. 2020Augmented Lagrangian Adversarial Attackscited by 28
  35. 2018Robust Adversarial Perturbation on Deep Proposal-based Modelscited by 26
  36. 2019Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentationcited by 26
  37. 2019Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defensescited by 23
  38. 2022Proximal Splitting Adversarial Attacks for Semantic Segmentationcited by 23

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 3.

5 papers.

  1. 2024Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attackscited by 39
  2. 2025RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Frameworkcited by 7
  3. 2025StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusionscited by 6
  4. 2023Intrinsic Biologically Plausible Adversarial Robustnesscited by 1
  5. 2025VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systemscited by 0