@inproceedings{xu-etal-2025-unlocking,
    title = "Unlocking the Effectiveness of {L}o{RA}-{FP} for Seamless Transfer Implantation of Fingerprints in Downstream Models",
    author = "Xu, Zhenhua  and
      Yan, Zhaokun  and
      Xu, Binhan  and
      Tong, Xin  and
      Xu, Haitao  and
      Chen, Yourong  and
      Han, Meng",
    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.230/",
    doi = "10.18653/v1/2025.findings-emnlp.230",
    pages = "4302--4312",
    ISBN = "979-8-89176-335-7",
    abstract = "With the rapid development of large language models (LLMs), protecting intellectual property (IP) has become increasingly crucial. To tackle high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight plug-and-play framework that encodes backdoor fingerprints into LoRA adapters via constrained fine-tuning. This enables seamless fingerprint transplantation through parameter fusion, eliminating full-parameter updates while maintaining integrity. Experiments demonstrate that LoRA-FP achieves superior robustness against various scenarios like incremental training and model fusion, while significantly reducing computational overhead compared to traditional approaches."
}