Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
Zhenhua Xu, Zhaokun Yan, Binhan Xu, Xin Tong, Haitao Xu, Yourong Chen, Meng Han
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.
BibTeX
@inproceedings{emnlp2025_unlockingtheeffe,
title = {Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models},
author = {Zhenhua Xu and Zhaokun Yan and Binhan Xu and Xin Tong and Haitao Xu and Yourong Chen and Meng Han},
booktitle = {EMNLP 2025},
year = {2025}
}