RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation

Jiawei Zhou, Linye Lyu, Daojing He, Yu Li
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62076-62087, 2024.

Abstract

Adversarial camouflage is a widely used physical attack against vehicle detectors for its superiority in multi-view attack performance. One promising approach involves using differentiable neural renderers to facilitate adversarial camouflage optimization through gradient back-propagation. However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle, resulting in suboptimal attack performance. Moreover, these approaches neglect diverse weather conditions, reducing the efficacy of generated camouflage across varying weather scenarios. To tackle these challenges, we propose a robust and accurate camouflage generation method, namely RAUCA. The core of RAUCA is a novel neural rendering component, Neural Renderer Plus (NRP), which can accurately project vehicle textures and render images with environmental characteristics such as lighting and weather. In addition, we integrate a multi-weather dataset for camouflage generation, leveraging the NRP to enhance the attack robustness. Experimental results on six popular object detectors show that RAUCA consistently outperforms existing methods in both simulation and real-world settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-zhou24n, title = {{RAUCA}: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation}, author = {Zhou, Jiawei and Lyu, Linye and He, Daojing and Li, Yu}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {62076--62087}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/zhou24n/zhou24n.pdf}, url = {https://proceedings.mlr.press/v235/zhou24n.html}, abstract = {Adversarial camouflage is a widely used physical attack against vehicle detectors for its superiority in multi-view attack performance. One promising approach involves using differentiable neural renderers to facilitate adversarial camouflage optimization through gradient back-propagation. However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle, resulting in suboptimal attack performance. Moreover, these approaches neglect diverse weather conditions, reducing the efficacy of generated camouflage across varying weather scenarios. To tackle these challenges, we propose a robust and accurate camouflage generation method, namely RAUCA. The core of RAUCA is a novel neural rendering component, Neural Renderer Plus (NRP), which can accurately project vehicle textures and render images with environmental characteristics such as lighting and weather. In addition, we integrate a multi-weather dataset for camouflage generation, leveraging the NRP to enhance the attack robustness. Experimental results on six popular object detectors show that RAUCA consistently outperforms existing methods in both simulation and real-world settings.} }
Endnote
%0 Conference Paper %T RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation %A Jiawei Zhou %A Linye Lyu %A Daojing He %A Yu Li %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-zhou24n %I PMLR %P 62076--62087 %U https://proceedings.mlr.press/v235/zhou24n.html %V 235 %X Adversarial camouflage is a widely used physical attack against vehicle detectors for its superiority in multi-view attack performance. One promising approach involves using differentiable neural renderers to facilitate adversarial camouflage optimization through gradient back-propagation. However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle, resulting in suboptimal attack performance. Moreover, these approaches neglect diverse weather conditions, reducing the efficacy of generated camouflage across varying weather scenarios. To tackle these challenges, we propose a robust and accurate camouflage generation method, namely RAUCA. The core of RAUCA is a novel neural rendering component, Neural Renderer Plus (NRP), which can accurately project vehicle textures and render images with environmental characteristics such as lighting and weather. In addition, we integrate a multi-weather dataset for camouflage generation, leveraging the NRP to enhance the attack robustness. Experimental results on six popular object detectors show that RAUCA consistently outperforms existing methods in both simulation and real-world settings.
APA
Zhou, J., Lyu, L., He, D. & Li, Y.. (2024). RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:62076-62087 Available from https://proceedings.mlr.press/v235/zhou24n.html.

Related Material