EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stealthy Vehicle Adversarial Camouflage Texture Generation Based on Neural Style Transfer

Wei Cai iD, Xingyu Di iD, Xin Wang, Weijie Gao iD, Haoran Jia

Entropy · 24.10.2024 · 26 (11) · 903

DOI: 10.3390/e26110903 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 24.10.2024. Verfasst von Wei Cai und 4 weiteren Autor:innen. Beteiligte Einrichtung: The Third Faculty of Xi'an Research Institute of High Technology, Xi'an 710064, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Defense Science and Technology 173.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adversarial attacks that mislead deep neural networks (DNNs) into making incorrect predictions can also be implemented in the physical world. However, most of the existing adversarial camouflage textures that attack object detection models only consider the effectiveness of the attack, ignoring the stealthiness of adversarial attacks, resulting in the generated adversarial camouflage textures appearing abrupt to human observers. To address this issue, we propose a style transfer module added to an adversarial texture generation framework. By calculating the style loss between the texture and the specified style image, the adversarial texture generated by the model is guided to have good stealthiness and is not easily detected by DNNs and human observers in specific scenes. Experiments have shown that in both the digital and physical worlds, the vehicle full coverage adversarial camouflage texture we create has good stealthiness and can effectively fool advanced DNN object detectors while evading human observers in specific scenes.

Schlagwörter

Stichwörter der Autor:innen

neural style transferobject detectionphysical attackstealthy adversarial attackwhite-box attack

Autor:innen und Institutionen

  • The Third Faculty of Xi'an Research Institute of High Technology, Xi'an 710064, China.

ORCID-Profile: Wei Cai, Xingyu Di, Weijie Gao

Förderung

  • National Defense Science and Technology 173

Zitieren

APA

Cai, W., Di, X., Wang, X., Gao, W., & Jia, H. (2024). Stealthy Vehicle Adversarial Camouflage Texture Generation Based on Neural Style Transfer. Entropy, 26(11), 903. https://doi.org/10.3390/e26110903

Vancouver

Cai W, Di X, Wang X, Gao W, Jia H. Stealthy Vehicle Adversarial Camouflage Texture Generation Based on Neural Style Transfer. Entropy. 2024;26(11):903. doi:10.3390/e26110903

BibTeX
@article{Cai2024,
  author = {Cai, Wei and Di, Xingyu and Wang, Xin and Gao, Weijie and Jia, Haoran},
  title = {Stealthy Vehicle Adversarial Camouflage Texture Generation Based on Neural Style Transfer},
  journal = {Entropy},
  year = {2024},
  volume = {26},
  number = {11},
  pages = {903},
  doi = {10.3390/e26110903}
}
Kostenlos starten →