Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
ACM Computing Surveys · 31.01.2026 · 58 (2) · 1-42
DOI: 10.1145/3743126 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 09.09.2025. Verfasst von Chiyu Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 322 Literaturangaben.
Abstract (Originalsprache)
With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks demystification. However, existing surveys often target attack taxonomy and lack in-depth analysis like (1) unified insights into adversariality, transferability, and generalization; (2) detailed evaluations framework; (3) motivation-driven attack categorizations; and (4) an integrated perspective on both traditional and LVLM attacks. This article addresses these gaps by offering a thorough summary of traditional and LVLM adversarial attacks, emphasizing their connections and distinctions, and providing actionable insights for future research.
Zitieren
APA
Zhang, C., Zhou, L., Xu, X., Wu, J., & Liu, Z. (2026). Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey. ACM Computing Surveys, 58(2), 1-42. https://doi.org/10.1145/3743126
Vancouver
Zhang C, Zhou L, Xu X, Wu J, Liu Z. Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey. ACM Computing Surveys. 2026;58(2):1-42. doi:10.1145/3743126
BibTeX
@article{Zhang2026,
author = {Zhang, Chiyu and Zhou, Lu and Xu, Xiaogang and Wu, Jiafei and Liu, Zhe},
title = {Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {2},
pages = {1--42},
doi = {10.1145/3743126}
}
EUVIMED