Backdoor Attacks and Defenses Targeting Multi-Domain AI Models: A Comprehensive Review
ACM Computing Surveys · 30.04.2025 · 57 (4) · 1-35
DOI: 10.1145/3704725 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.12.2024. Verfasst von Shaobo Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 195 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Cloud Technology Endowed Professorship.
Abstract (Originalsprache)
Since the emergence of security concerns in artificial intelligence (AI), there has been significant attention devoted to the examination of backdoor attacks. Attackers can utilize backdoor attacks to manipulate model predictions, leading to significant potential harm. However, current research on backdoor attacks and defenses in both theoretical and practical fields still has many shortcomings. To systematically analyze these shortcomings and address the lack of comprehensive reviews, this article presents a comprehensive and systematic summary of both backdoor attacks and defenses targeting multi-domain AI models. Simultaneously, based on the design principles and shared characteristics of triggers in different domains and the implementation stages of backdoor defense, this article proposes a new classification method for backdoor attacks and defenses. We use this method to extensively review backdoor attacks in the fields of computer vision and natural language processing, and we also examine the current applications of backdoor attacks in audio recognition, video action recognition, multimodal tasks, time series tasks, generative learning, and reinforcement learning, while critically analyzing the open problems of various backdoor attack techniques and defense strategies. Finally, this article builds upon the analysis of the current state of AI security to further explore potential future research directions for backdoor attacks and defenses.
Förderung
- National Natural Science Foundation of China
- Cloud Technology Endowed Professorship
Zitieren
APA
Zhang, S., Pan, Y., Liu, Q., Yan, Z., Choo, K. R., & Wang, G. (2025). Backdoor Attacks and Defenses Targeting Multi-Domain AI Models: A Comprehensive Review. ACM Computing Surveys, 57(4), 1-35. https://doi.org/10.1145/3704725
Vancouver
Zhang S, Pan Y, Liu Q, Yan Z, Choo KR, Wang G. Backdoor Attacks and Defenses Targeting Multi-Domain AI Models: A Comprehensive Review. ACM Computing Surveys. 2025;57(4):1-35. doi:10.1145/3704725
BibTeX
@article{Zhang2025,
author = {Zhang, Shaobo and Pan, Yimeng and Liu, Qin and Yan, Zheng and Choo, Kim-Kwang Raymond and Wang, Guojun},
title = {Backdoor Attacks and Defenses Targeting Multi-Domain AI Models: A Comprehensive Review},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {4},
pages = {1--35},
doi = {10.1145/3704725}
}
EUVIMED