A Survey of Defenses Against AI-Generated Visual Media: Detection, Disruption, and Authentication
ACM Computing Surveys · 30.04.2026 · 58 (5) · 1-35
DOI: 10.1145/3770916 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 20.11.2025. Verfasst von Jingyi Deng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 285 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Shaanxi Province Key Industry Innovation Program.
Abstract (Originalsprache)
Deep generative models have demonstrated impressive performance in various computer vision applications, including image synthesis, video generation, and medical analysis. Despite their significant advancements, these models may be used for malicious purposes, such as misinformation, deception, and copyright violation. In this article, we provide a systematic and timely review of research efforts on defenses against AI-generated visual media, covering detection, disruption, and authentication. We review existing methods and summarize the mainstream defense-related tasks within a unified passive and proactive framework. Moreover, we survey the derivative tasks concerning the trustworthiness of defenses, such as their robustness and fairness. For each defense strategy, we formulate its general pipeline and propose a multidimensional taxonomy applicable across defense tasks, based on methodological strategies. Additionally, we summarize the commonly used evaluation datasets, criteria, and metrics. Finally, by analyzing the reviewed studies, we provide insights into current research challenges and suggest possible directions for future research.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Shaanxi Province Key Industry Innovation Program
Zitieren
APA
Deng, J., Lin, C., Zhao, Z., Liu, S., Peng, Z., Wang, Q., & Shen, C. (2026). A Survey of Defenses Against AI-Generated Visual Media: Detection, Disruption, and Authentication. ACM Computing Surveys, 58(5), 1-35. https://doi.org/10.1145/3770916
Vancouver
Deng J, Lin C, Zhao Z, Liu S, Peng Z, Wang Q, et al. A Survey of Defenses Against AI-Generated Visual Media: Detection, Disruption, and Authentication. ACM Computing Surveys. 2026;58(5):1-35. doi:10.1145/3770916
BibTeX
@article{Deng2026,
author = {Deng, Jingyi and Lin, Chenhao and Zhao, Zhengyu and Liu, Shuai and Peng, Zhe and Wang, Qian and Shen, Chao},
title = {A Survey of Defenses Against AI-Generated Visual Media: Detection, Disruption, and Authentication},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {5},
pages = {1--35},
doi = {10.1145/3770916}
}
EUVIMED