Journal article · 2026 · Open access
Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models
ACM Computing Surveys, 59(1), 1–34 · Published 5 October 2026 · DOI 10.1145/3857219
In brief
“Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models” is a 2026 journal article by Jinming Wen and 4 co-authors, published in ACM Computing Surveys. OpenAlex counts 3 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at ACM Computing Surveys.
- Citations
- 3
- Most cited in
- 2025 (2)
- References
- 134
- Authors
- 5
Abstract
With the rapid development of multimodal large language models (MLLMs) and the cost of large amounts of data and resources, researchers are more inclined to use public datasets and fine-tune open-source MLLMs to achieve excellent performance in audiovisual related tasks 1 . While this trend accelerates progress, it also introduces security risks. Empirical studies demonstrate that the latest MLLMs can be manipulated to generate harmful content through crafted inputs, including adversarial perturbations and malicious queries, bypassing internal safeguards. To gain a deeper comprehension of the inherent security vulnerabilities associated with audio-visual-based multimodal models, a series of surveys investigates various types of attacks, including adversarial and backdoor attacks. While existing surveys on audio-visual attacks provide a comprehensive overview, they are limited to specific types of attacks, which lack a unified review of various types of attacks. To bridge this gap, this article presents a comprehensive and systematic review of audio-visual attacks, which include adversarial, backdoor, and jailbreak attacks. Furthermore, we also review various types of attacks in the latest audio-visual-based MLLMs, a dimension notably absent in existing surveys. Drawing from extensive literature, this article delineates both challenges and emergent trends for future research on audio-visual attacks and defenses.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wen, J., Wu, X., Li, Y., Jia, Y., & Zhao, S. (2026). Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models. ACM Computing Surveys, 59(1), 1–34. https://doi.org/10.1145/3857219
MLA 9
Wen, Jinming, et al. “Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models.” ACM Computing Surveys, vol. 59, no. 1, 2026, pp. 1–34. https://doi.org/10.1145/3857219.
Chicago
Wen, Jinming, XC Wu, Yuwen Li, Yanhao Jia, and Shuai Zhao. 2026. “Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models.” ACM Computing Surveys 59 (1): 1–34. https://doi.org/10.1145/3857219.
Harvard
Wen, J. et al. (2026) ‘Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models’, ACM Computing Surveys, 59(1), pp. 1–34. doi:10.1145/3857219.
IEEE
J. Wen, X. Wu, Y. Li, Y. Jia, and S. Zhao, “Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models,” ACM Computing Surveys, vol. 59, no. 1, pp. 1–34, 2026, doi: 10.1145/3857219.
BibTeX
@article{wen2026vulnerabilities,
title = {{Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models}},
author = {Wen, Jinming and Wu, XC and Li, Yuwen and Jia, Yanhao and Zhao, Shuai},
journal = {ACM Computing Surveys},
year = {2026},
volume = {59},
number = {1},
pages = {1--34},
doi = {10.1145/3857219},
url = {https://doi.org/10.1145/3857219}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- multimodal large language models
- adversarial attacks
- backdoor attacks
- jailbreak attacks
- security vulnerabilities
- attack defense
- harmful content generation
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Wen, J., Wu, X., Li, Y., Jia, Y., & Zhao, S. (2026). Vulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal Models. ACM Computing Surveys, 59(1), 1–34. https://doi.org/10.1145/3857219
How many times has this paper been cited?
3 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at ACM Computing Surveys: sign in and open the full text from this page.
Who wrote this paper?
Jinming Wen, XC Wu, Yuwen Li, Yanhao Jia, Shuai Zhao.
What is the DOI of this paper?
10.1145/3857219, permanently at https://doi.org/10.1145/3857219. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.