@inproceedings{yang-etal-2025-forget,
    title = "Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning",
    author = "Yang, Shiji  and
      Zhao, Shu  and
      Mei, Congyao  and
      Yang, Zhen  and
      Chen, Jie  and
      Qian, Fulan  and
      Duan, Zhen  and
      Zhang, Yanping",
    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.1338/",
    doi = "10.18653/v1/2025.findings-emnlp.1338",
    pages = "24597--24607",
    ISBN = "979-8-89176-335-7",
    abstract = "Prompt tuning for Large Language Models (LLMs) is vulnerable to backdoor attacks. Existing methods find backdoor attacks to be a significant threat in data-rich scenarios. However, in data-limited scenarios, these methods have difficulty capturing precise backdoor patterns, leading to weakened backdoor attack capabilities and significant side effects for the LLMs, which limits their practical relevance. To explore this problem, we propose a backdoor attacks through contrastive-enhanced machine unlearning in data-limited scenarios, called BCU. Specifically, BCU introduces a multi-objective machine unlearning method to capture precise backdoor patterns by forgetting the association between non-trigger data and the backdoor patterns, reducing side effects. Moreover, we design a contrastive learning strategy to enhance the association between triggers and backdoor patterns, improving the capability of backdoor attacks. Experimental results on 6 NLP datasets and 4 LLMs show that BCU exhibits strong backdoor attack capabilities and slight side effects, whether the training data is rich or limited. Our findings highlight practical security risks of backdoor attacks against LLMs, necessitating further research for security purposes. Our code is available at https://github.com/AHU-YangSJ/BCU."
}