@inproceedings{zhuang-etal-2025-exploring,
    title = "Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation",
    author = "Zhuang, Jun  and
      Jin, Haibo  and
      Zhang, Ye  and
      Kang, Zhengjian  and
      Zhang, Wenbin  and
      Dagher, Gaby G.  and
      Wang, Haohan",
    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.114/",
    doi = "10.18653/v1/2025.findings-emnlp.114",
    pages = "2147--2160",
    ISBN = "979-8-89176-335-7"
}