@inproceedings{zhang-etal-2025-security,
    title = "The Security Threat of Compressed Projectors in Large Vision-Language Models",
    author = "Zhang, Yudong  and
      Xie, Ruobing  and
      Sun, Xingwu  and
      Chen, Jiansheng  and
      Kang, Zhanhui  and
      Wang, Di  and
      Wang, Yu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1111/",
    doi = "10.18653/v1/2025.findings-emnlp.1111",
    pages = "20397--20407",
    ISBN = "979-8-89176-335-7",
    abstract = "The choice of a suitable visual language projector (VLP) is critical to the successful training of large visual language models (LVLMs). Mainstream VLPs can be broadly categorized into compressed and uncompressed projectors, and each offers distinct advantages in performance and computational efficiency. However, their security implications have not been thoroughly examined. Our comprehensive evaluation reveals significant differences in their security profiles: compressed projectors exhibit substantial vulnerabilities, allowing adversaries to successfully compromise LVLMs even with minimal knowledge of structure information. In stark contrast, uncompressed projectors demonstrate robust security properties and do not introduce additional vulnerabilities. These findings provide critical guidance for researchers in selecting optimal VLPs that enhance the security and reliability of visual language models. The code is available at \url{https://github.com/btzyd/TCP}."
}