Visual Adversarial Attacks and Defenses in the Physical World: A Survey
ACM Computing Surveys · 31.07.2026 · 58 (10) · 1-36
DOI: 10.1145/3793659 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 01.04.2026. Verfasst von Xingxing Wei und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 216 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Although Deep Neural Networks (DNNs) have been widely applied in various real-world scenarios, they remain vulnerable to adversarial examples. Adversarial attacks in computer vision can be categorized into digital attacks and physical attacks based on their different forms. Compared to digital attacks, which generate perturbations in digital pixels, physical attacks are more practical in real-world settings. Due to the serious security risks posed by physically adversarial examples, many studies have been conducted to evaluate the physically adversarial robustness of DNNs in recent years. In this article, we provide a comprehensive survey of current physically adversarial attacks and defenses in computer vision. We establish a taxonomy by organizing physical attacks according to attack tasks, attack forms, and attack methods. This approach offers readers a systematic understanding of the topic from multiple perspectives. For physical defenses, we categorize them into pre-processing, in-processing, and post-processing for DNN models to ensure comprehensive coverage of adversarial defenses. Based on this survey, we discuss the challenges facing this research field and provide an outlook on future directions.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Wei, X., Pu, B., Zhao, S., Lu, J., & Wu, B. (2026). Visual Adversarial Attacks and Defenses in the Physical World: A Survey. ACM Computing Surveys, 58(10), 1-36. https://doi.org/10.1145/3793659
Vancouver
Wei X, Pu B, Zhao S, Lu J, Wu B. Visual Adversarial Attacks and Defenses in the Physical World: A Survey. ACM Computing Surveys. 2026;58(10):1-36. doi:10.1145/3793659
BibTeX
@article{Wei2026,
author = {Wei, Xingxing and Pu, Bangzheng and Zhao, Shiji and Lu, Jiefan and Wu, Baoyuan},
title = {Visual Adversarial Attacks and Defenses in the Physical World: A Survey},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {10},
pages = {1--36},
doi = {10.1145/3793659}
}
EUVIMED