@inproceedings{zhang-etal-2025-beyond-text,
    title = "Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation",
    author = "Zhang, Jiankun  and
      Zeng, Shenglai  and
      Ren, Jie  and
      Zheng, Tianqi  and
      Liu, Hui  and
      Tang, Xianfeng  and
      Liu, Hui  and
      Chang, Yi",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1259/",
    pages = "24800--24821",
    ISBN = "979-8-89176-332-6",
    abstract = "Multimodal Retrieval-Augmented Generation (MRAG) systems enhance LMMs by integrating external multimodal databases, but introduce unexplored privacy vulnerabilities. While text-based RAG privacy risks have been studied, multimodal data presents unique challenges. We provide the first systematic analysis of MRAG privacy vulnerabilities across vision-language and speech-language modalities. Using a novel compositional structured prompt attack in a black-box setting, we demonstrate how attackers can extract private information by manipulating queries. Our experiments reveal that LMMs can both directly generate outputs resembling retrieved content and produce descriptions that indirectly expose sensitive information, highlighting the urgent need for robust privacy-preserving MRAG techniques."
}