Fooling Polarization-based Vision using Locally Controllable Polarizing Projection
Not on the map. Why?
Abstract (arXiv)
Polarization is a fundamental property of light that encodes abundant information regarding surface shape, material, illumination and viewing geometry. The computer vision community has witnessed a blossom of polarization-based vision applications, such as reflection removal, shape-from-polarization, transparent object segmentation and color constancy, partially due to the emergence of single-chip mono/color polarization sensors that make polarization data acquisition easier than ever. However, is polarization-based vision vulnerable to adversarial attacks? If so, is that possible to realize these adversarial attacks in the physical world, without being perceived by human eyes? In this paper, we warn the community of the vulnerability of polarization-based vision, which can be more serious than RGB-based vision. By adapting a commercial LCD projector, we achieve locally controllable polarizing projection, which is successfully utilized to fool state-of-the-art polarization-based vision algorithms for glass segmentation and color constancy. Compared with existing physical attacks on RGB-based vision, which always suffer from the trade-off between attack efficacy and eye conceivability, the adversarial attackers based on polarizing projection are contact-free and visually imperceptible, since naked human eyes can rarely perceive the difference of viciously manipulated polarizing light and ordinary illumination. This poses unprecedented risks on polarization-based vision, both in the monochromatic and trichromatic domain, for which due attentions should be paid and counter measures be considered.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 31 Mar 2023.
Builds on
23 of 42 references.
References · 23
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Adversarial examples in the physical worldcited by 1,762
- 2016Universal adversarial perturbationscited by 774
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
- 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
- 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
- 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
- 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
11 more
- 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
- 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
- 2020Polarized Reflection Removal with Perfect Alignment in the Wildcited by 69
- 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
- 2021Deep Polarization Imaging for 3D shape and SVBRDF Acquisitioncited by 56
- 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
- 2021Optical Adversarial Attackcited by 43
- 2020Polarimetric Multi-View Inverse Renderingcited by 28
- 2021Adversarial Examples on Segmentation Models Can be Easy to Transfercited by 15
- 2021Human Pose and Shape Estimation from Single Polarization Imagescited by 13
- 2022Adversarial Color Projection: A Projector-based Physical Attack to DNNscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.