Physical Adversarial Attack Meets Computer Vision: A Decade Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9797-9817
DOI: 10.1109/tpami.2024.3430860 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Hui Wei und 8 weiteren Autor:innen. Die Arbeit wurde bisher 110-mal zitiert (Crossref) und nennt 181 Literaturangaben. Gefördert von: Hubei Key R&D, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision, their vulnerability to adversarial attacks remains a critical concern. Extensive research has demonstrated that incorporating sophisticated perturbations into input images can lead to a catastrophic degradation in DNNs' performance. This perplexing phenomenon not only exists in the digital space but also in the physical world. Consequently, it becomes imperative to evaluate the security of DNNs-based systems to ensure their safe deployment in real-world scenarios, particularly in security-sensitive applications. To facilitate a profound understanding of this topic, this paper presents a comprehensive overview of physical adversarial attacks. First, we distill four general steps for launching physical adversarial attacks. Building upon this foundation, we uncover the pervasive role of artifacts carrying adversarial perturbations in the physical world. These artifacts influence each step. To denote them, we introduce a new term: adversarial medium. Then, we take the first step to systematically evaluate the performance of physical adversarial attacks, taking the adversarial medium as a first attempt. Our proposed evaluation metric, hiPAA, comprises six perspectives: Effectiveness, Stealthiness, Robustness, Practicability, Aesthetics, and Economics. We also provide comparative results across task categories, together with insightful observations and suggestions for future research directions.
Förderung
- Hubei Key R&D
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Peking University
- JSPS KAKENHI
- JST ASPIRE
Zitieren
APA
Wei, H., Tang, H., Jia, X., Wang, Z., Yu, H., Li, Z., Satoh, S., Van Gool, L., & Wang, Z. (2024). Physical Adversarial Attack Meets Computer Vision: A Decade Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9797-9817. https://doi.org/10.1109/tpami.2024.3430860
Vancouver
Wei H, Tang H, Jia X, Wang Z, Yu H, Li Z, et al. Physical Adversarial Attack Meets Computer Vision: A Decade Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9797-9817. doi:10.1109/tpami.2024.3430860
BibTeX
@article{Wei2024,
author = {Wei, Hui and Tang, Hao and Jia, Xuemei and Wang, Zhixiang and Yu, Hanxun and Li, Zhubo and Satoh, Shin'ichi and Van Gool, Luc and Wang, Zheng},
title = {Physical Adversarial Attack Meets Computer Vision: A Decade Survey},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {9797--9817},
doi = {10.1109/tpami.2024.3430860}
}
EUVIMED