Saved in:
Bibliographic Details
Main Authors: Lyu, Linye, Zhou, Jiawei, He, Daojing, Li, Yu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.17963
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913520168206336
author Lyu, Linye
Zhou, Jiawei
He, Daojing
Li, Yu
author_facet Lyu, Linye
Zhou, Jiawei
He, Daojing
Li, Yu
contents Prior works on physical adversarial camouflage against vehicle detectors mainly focus on the effectiveness and robustness of the attack. The current most successful methods optimize 3D vehicle texture at a pixel level. However, this results in conspicuous and attention-grabbing patterns in the generated camouflage, which humans can easily identify. To address this issue, we propose a Customizable and Natural Camouflage Attack (CNCA) method by leveraging an off-the-shelf pre-trained diffusion model. By sampling the optimal texture image from the diffusion model with a user-specific text prompt, our method can generate natural and customizable adversarial camouflage while maintaining high attack performance. With extensive experiments on the digital and physical worlds and user studies, the results demonstrate that our proposed method can generate significantly more natural-looking camouflage than the state-of-the-art baselines while achieving competitive attack performance. Our code is available at \href{https://anonymous.4open.science/r/CNCA-1D54}{https://anonymous.4open.science/r/CNCA-1D54}
format Preprint
id arxiv_https___arxiv_org_abs_2409_17963
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
Lyu, Linye
Zhou, Jiawei
He, Daojing
Li, Yu
Computer Vision and Pattern Recognition
Prior works on physical adversarial camouflage against vehicle detectors mainly focus on the effectiveness and robustness of the attack. The current most successful methods optimize 3D vehicle texture at a pixel level. However, this results in conspicuous and attention-grabbing patterns in the generated camouflage, which humans can easily identify. To address this issue, we propose a Customizable and Natural Camouflage Attack (CNCA) method by leveraging an off-the-shelf pre-trained diffusion model. By sampling the optimal texture image from the diffusion model with a user-specific text prompt, our method can generate natural and customizable adversarial camouflage while maintaining high attack performance. With extensive experiments on the digital and physical worlds and user studies, the results demonstrate that our proposed method can generate significantly more natural-looking camouflage than the state-of-the-art baselines while achieving competitive attack performance. Our code is available at \href{https://anonymous.4open.science/r/CNCA-1D54}{https://anonymous.4open.science/r/CNCA-1D54}
title CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.17963