Journal article · 2026

Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models

Daizong Liu, Tianyao Luo, Junhao Dong, Xiaowen Cai, Hao He, Weidong Wang, Runwei Guan, Jianfeng Dong, Pan Zhou, Bo Du, Hui Xiong

IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18 · Published 2 October 2026 · DOI 10.1109/tpami.2026.3740091

View at the publisherCite this paper

In brief

“Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models” is a 2026 journal article by Daizong Liu and 10 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 0 citations as of 17 November 2026. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
0
Authors
11

Abstract

Although Large Vision-Language Models (LVLMs) have shown great capabilities across various downstream tasks, they are proven to be vulnerable to adversarial examples, thus resulting in critical safety issues. Existing adversarial attacks against LVLMs predominantly rely on uniform, image-wise perturbations, while largely overlooking how these models internally perceive and prioritize visual structures during multimodal alignment. Moreover… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Liu, D., Luo, T., Dong, J., Cai, X., He, H., Wang, W., Guan, R., Dong, J., Zhou, P., Du, B., & Xiong, H. (2026). Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3740091

MLA 9

Liu, Daizong, et al. “Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–18. https://doi.org/10.1109/tpami.2026.3740091.

Chicago

Liu, Daizong, Tianyao Luo, Junhao Dong, Xiaowen Cai, Hao He, Weidong Wang, Runwei Guan, et al. 2026. “Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–18. https://doi.org/10.1109/tpami.2026.3740091.

Harvard

Liu, D. et al. (2026) ‘Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–18. doi:10.1109/tpami.2026.3740091.

IEEE

D. Liu et al., “Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–18, 2026, doi: 10.1109/tpami.2026.3740091.

BibTeX

@article{liu2026flexible,
  title     = {{Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models}},
  author    = {Liu, Daizong and Luo, Tianyao and Dong, Junhao and Cai, Xiaowen and He, Hao and Wang, Weidong and Guan, Runwei and Dong, Jianfeng and Zhou, Pan and Du, Bo and Xiong, Hui},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2026},
  volume    = {PP},
  pages     = {1--18},
  doi       = {10.1109/tpami.2026.3740091},
  url       = {https://doi.org/10.1109/tpami.2026.3740091}
}

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

  • large vision-language models
  • adversarial attacks
  • gray-box attacks
  • vision encoder
  • multimodal alignment
  • adversarial vulnerability

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Liu, D., Luo, T., Dong, J., Cai, X., He, H., Wang, W., Guan, R., Dong, J., Zhou, P., Du, B., & Xiong, H. (2026). Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3740091

How many times has this paper been cited?

0 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Daizong Liu, Tianyao Luo, Junhao Dong, Xiaowen Cai, Hao He, Weidong Wang, Runwei Guan, Jianfeng Dong, Pan Zhou, Bo Du, Hui Xiong.

What is the DOI of this paper?

10.1109/tpami.2026.3740091, permanently at https://doi.org/10.1109/tpami.2026.3740091. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 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.