@inproceedings{huang-etal-2025-intrinsic,
    title = "Intrinsic Model Weaknesses: How Priming Attacks Unveil Vulnerabilities in Large Language Models",
    author = "Huang, Yuyi  and
      Zhan, Runzhe  and
      Wong, Derek F.  and
      Chao, Lidia S.  and
      Tao, Ailin",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.findings-naacl.77/",
    pages = "1405--1425",
    ISBN = "979-8-89176-195-7",
    abstract = "Large language models (LLMs) have significantly influenced various industries but suffer from a critical flaw, the potential sensitivity of generating harmful content, which poses severe societal risks. We developed and tested novel attack strategies on popular LLMs to expose their vulnerabilities in generating inappropriate content. These strategies, inspired by psychological phenomena such as the {\textquotedblleft}Priming Effect{\textquotedblright}, {\textquotedblleft}Safe Attention Shift{\textquotedblright}, and {\textquotedblleft}Cognitive Dissonance{\textquotedblright}, effectively attack the models' guarding mechanisms. Our experiments achieved an attack success rate (ASR) of 100{\%} on various open-source models, including Meta`s Llama-3.2, Google`s Gemma-2, Mistral`s Mistral-NeMo, Falcon`s Falcon-mamba, Apple`s DCLM, Microsoft`s Phi3, and Qwen`s Qwen2.5, among others. Similarly, for closed-source models such as OpenAI`s GPT-4o, Google`s Gemini-1.5, and Claude-3.5, we observed an ASR of at least 95{\%} on the AdvBench dataset, which represents the current state-of-the-art. This study underscores the urgent need to reassess the use of generative models in critical applications to mitigate potential adverse societal impacts."
}