A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challenges
Not on the map. Why?
Abstract (arXiv)
Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white box and black box approaches. Practical attacks include methods to manipulate the physical world and enforce adversarial behaviour by the corresponding target neural network models. Multiple different approaches to mitigate different kinds of such attacks are available in the literature, each with their own advantages and limitations. In this survey, we present a comprehensive systematization of knowledge on adversarial defenses, focusing on two key computer vision tasks: image classification and object detection. We review the state-of-the-art adversarial defense techniques and categorize them for easier comparison. In addition, we provide a schematic representation of these categories within the context of the overall machine learning pipeline, facilitating clearer understanding and benchmarking of defenses. Furthermore, we map these defenses to the types of adversarial attacks and datasets where they are most effective, offering practical insights for researchers and practitioners. This study is necessary for understanding the scope of how the available defenses are able to address the adversarial threats, and their shortcomings as well, which is necessary for driving the research in this area in the most appropriate direction, with the aim of building trustworthy AI systems for regular practical use-cases.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 112 of its 172 references that are in the map. First posted on arXiv 1 Mar 2025.
Builds on
112 of 172 references.
References · 112
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2016Adversarial examples in the physical worldcited by 1,769
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2016Adversarial Machine Learning at Scalecited by 936
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
38 more
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
- 2016Stealing Machine Learning Models via Prediction APIscited by 619
- 2017Adversarial Patchcited by 517
- 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
- 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
- 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
- 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 293
- 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
- 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
- 2018Adversarial Attacks and Defences: A Surveycited by 259
- 2021Vision Transformers are Robust Learnerscited by 207
- 2018Physical Adversarial Examples for Object Detectorscited by 163
- 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
- 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
- 2023Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Modelscited by 154
- 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
- 2018xView: Objects in Context in Overhead Imagerycited by 146
- 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
- 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
- 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
- 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 122
- 2018LaVAN: Localized and Visible Adversarial Noisecited by 113
- 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 105
- 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
- 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 99
- 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
- 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
- 2019On Physical Adversarial Patches for Object Detectioncited by 93
- 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
- 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 87
- 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
- 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
- 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
- 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Drivingcited by 72
- 2020Opportunities and Challenges in Deep Learning Adversarial Robustness: A Surveycited by 72
- 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 70
- 2021Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detectioncited by 67
- 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
50 most cited of 112 All 112 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.