Recent Advances in Vision Transformer Robustness Against Adversarial Attacks in Traffic Sign Detection and Recognition: A Survey
ACM Computing Surveys · 31.10.2025 · 57 (10) · 1-33
DOI: 10.1145/3729167 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 07.05.2025. Verfasst von Oluwajuwon Fawole und 1 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 121 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DoD/U.S. Army Research Laboratory at Howard University.
Abstract (Originalsprache)
The emergence of Vision Transformers (ViTs) has marked a significant advancement in machine learning, particularly in applications requiring robust visual recognition capabilities, such as traffic sign detection for autonomous driving systems. But, deploying these models in adversarial environments where robustness is critical remains a challenge. This survey provides a comprehensive review of the integration of ViTs in traffic sign detection and recognition, emphasizing their vulnerability to adversarial attacks and the methods developed to enhance their robustness. This article also presents a compressive comparison of ViTs in a tabular form for side-by-side comparison.
Förderung
- DoD/U.S. Army Research Laboratory at Howard University
Zitieren
APA
Fawole, O., & Rawat, D. (2025). Recent Advances in Vision Transformer Robustness Against Adversarial Attacks in Traffic Sign Detection and Recognition: A Survey. ACM Computing Surveys, 57(10), 1-33. https://doi.org/10.1145/3729167
Vancouver
Fawole O, Rawat D. Recent Advances in Vision Transformer Robustness Against Adversarial Attacks in Traffic Sign Detection and Recognition: A Survey. ACM Computing Surveys. 2025;57(10):1-33. doi:10.1145/3729167
BibTeX
@article{Fawole2025,
author = {Fawole, Oluwajuwon and Rawat, Danda},
title = {Recent Advances in Vision Transformer Robustness Against Adversarial Attacks in Traffic Sign Detection and Recognition: A Survey},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {10},
pages = {1--33},
doi = {10.1145/3729167}
}
EUVIMED