Adversarial Attacks on Vision-Language Multimodal Systems: A Survey
With the boom of artificial intelligence, multimodal deep learning, especially large language models (LLMs), has advanced remarkably and found wide applications. However, adversarial security issues hamper further development on LLMs. This paper comprehensively reviews adversarial attacks on vision-language multimodal systems (VLMS), covering key aspects such as pretrained models, large language models, adversarial attack methodologies, defense strategies, benchmark datasets, downstream tasks, and evaluation metrics. It first details multimodal deep-learning key technologies and the features of relevant models. Then, it deeply analyzes the adversarial vulnerabilities of VLMS. Next, it systematically reviews various adversarial attack methods and defend strategies in multimodal systems, covering task-specific attacks and attacks on different models, with a detailed analysis of their principles, implementations, and effects. Finally, it looks ahead to the future of multimodal adversarial attacks, suggesting research directions like improving attack universality and compliance considerations. This review offers technical references, promotes research on multimodal adversarial attacks, and helps enhance VLMS security for reliable real-world applications. The latest papers on VLMS adversarial attacks are continuously collected in https://github.com/chilljudaoren/A-Survey-of-Adversarial-Attack.
Authors
- Qiqi Bao (ORCID: https://orcid.org/0009-0004-1703-6090)
- Hegui Zhu (ORCID: https://orcid.org/0000-0002-6501-4097)
- Chenhao Lin (ORCID: https://orcid.org/0000-0002-6265-7345)
- Yaguan Qian (ORCID: https://orcid.org/0000-0003-4056-9755)
- Shouling Ji (ORCID: https://orcid.org/0000-0003-4268-372X)
- Zhaoquan Gu (ORCID: https://orcid.org/0000-0001-7546-852X)
- Yan Gan (ORCID: https://orcid.org/0000-0002-6716-0039)
- Jia-Li Yin (ORCID: https://orcid.org/0000-0002-8087-9769)
- Zhihao Chen (ORCID: https://orcid.org/0009-0008-8797-1059)
- Shuo Wang (ORCID: https://orcid.org/0000-0001-8938-2364)
- Wei Wang (ORCID: https://orcid.org/0000-0002-5974-1589)
- Bin Wang (ORCID: https://orcid.org/0000-0002-3790-2708)
Institutions
- Georgia Institute of Technology (US)
- Chongqing University (CN)
- Zhejiang University of Science and Technology (CN)
- Shanghai Jiao Tong University (CN)
- Harbin Institute of Technology (CN)
- Zhejiang University (CN)
- Fuzhou University (CN)
- Xi'an Jiaotong University (CN)
- Northeastern University (CN)
Publication Details
- Journal
- ACM Transactions on Privacy and Security
- Published
- 2026-11-21
- DOI
- https://doi.org/10.1145/3871040
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00