Developing Imperceptible Adversarial Patches to Camouflage Military Assets From Computer Vision Enabled Technologies
Not on the map. Why?
Abstract (arXiv)
Convolutional neural networks (CNNs) have demonstrated rapid progress and a high level of success in object detection. However, recent evidence has highlighted their vulnerability to adversarial attacks. These attacks are calculated image perturbations or adversarial patches that result in object misclassification or detection suppression. Traditional camouflage methods are impractical when applied to disguise aircraft and other large mobile assets from autonomous detection in intelligence, surveillance and reconnaissance technologies and fifth generation missiles. In this paper we present a unique method that produces imperceptible patches capable of camouflaging large military assets from computer vision-enabled technologies. We developed these patches by maximising object detection loss whilst limiting the patch's colour perceptibility. This work also aims to further the understanding of adversarial examples and their effects on object detection algorithms.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 17 Feb 2022.
Builds on
30 of 51 references.
References · 30
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 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
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
- 2016Universal adversarial perturbationscited by 784
- 2017One pixel attack for fooling deep neural networkscited by 582
- 2017Adversarial Patchcited by 517
18 more
- 2015Recent Advances in Convolutional Neural Networkscited by 360
- 2018Deep Face Recognition: A Surveycited by 276
- 2018Deep Facial Expression Recognition: A Surveycited by 270
- 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
- 2018Adversarial Robustness Toolbox v1.0.0cited by 215
- 2014Simultaneous Detection and Segmentationcited by 159
- 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
- 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
- 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 127
- 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
- 2019On Physical Adversarial Patches for Object Detectioncited by 93
- 2017A General Framework for Adversarial Examples with Objectivescited by 84
- 2019Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distancecited by 73
- 2018Deep learning in radiology: an overview of the concepts and a survey of the state of the artcited by 34
- 2018Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimizationcited by 18
- 2020Adversarial Patch Camouflage against Aerial Detectioncited by 16
- 2020Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topologycited by 11
Built on by
Citing papers per year: 2023: 1.
1 paper.