ACL 2025finding0 citations

The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective

Zixuan Xia, Haifeng Sun, Jingyu Wang, Qi Qi, Huazheng Wang, Xiaoyuan Fu, Jianxin Liao

Abstract

Prompts, especially high-quality ones, play an invaluable role in assisting large language models (LLMs) to accomplish various natural language processing tasks. However, carefully crafted prompts can also manipulate model behavior. Therefore, the security risks that “prompts themselves face” and those “arising from harmful prompts” cannot be overlooked and we define the Prompt Threat (PT) issues. In this paper, we review the latest attack methods related to prompt threats, focusing on prompt leakage attacks and prompt jailbreak attacks. Additionally, we summarize the experimental setups of these methods and explore the relationship between prompt threats and prompt injection attacks.

BibTeX
@inproceedings{xia-etal-2025-threat,
    title = "The Threat of {PROMPTS} in Large Language Models: A System and User Prompt Perspective",
    author = "Xia, Zixuan  and
      Sun, Haifeng  and
      Wang, Jingyu  and
      Qi, Qi  and
      Wang, Huazheng  and
      Fu, Xiaoyuan  and
      Liao, Jianxin",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.675/",
    doi = "10.18653/v1/2025.findings-acl.675",
    pages = "12994--13035",
    ISBN = "979-8-89176-256-5"
}
The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective · ACL 2025