Lune

EMNLP Findings2025

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 advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight, plug-andplay framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning. This design enables seamless fingerprint transplantation via parameter fusion, eliminating the need for full-parameter updates while preserving model integrity. Experimental results demonstrate that LoRA-FP not only significantly reduces computational overhead compared to conventional approaches but also achieves superior robustness across diverse scenarios, including incremental training and model fusion. Our code and datasets are publicly available at https://github.com/ Xuzhenhua55/LoRA-FP.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Composing Parameter-Efficient Modules with Arithmetic Operation cites LoRA: Low-Rank Adaptation of Large Language Models
  • CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor cites LoRA: Low-Rank Adaptation of Large Language Models
  • CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor cites Adversarial NLI: A New Benchmark for Natural Language Understanding
  • CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor cites Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
  • EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint cites LoRA: Low-Rank Adaptation of Large Language Models
  • EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint cites Adversarial NLI: A New Benchmark for Natural Language Understanding
  • EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint cites Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
  • LLM-Pruner: On the Structural Pruning of Large Language Models cites LoRA: Low-Rank Adaptation of Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic FingerprintZhenhua Xu, Meng Han, Wenpeng XingEMNLP 2025 · 2 citations
  2. CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation BackdoorZhenhua Xu, Xixiang Zhao, Xubin Yue, Shengwei Tian et al.EMNLP 2025

Builds on21

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. LLM-Pruner: On the Structural Pruning of Large Language ModelsXinyin Ma, Gongfan Fang, Xinchao WangNeurIPS 2023 · 994 citations
  3. Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free LunchLe Yu, Bowen Yu, Haiyang Yu, Fei Huang et al.ICML 2024 · 605 citations
  4. Adversarial NLI: A New Benchmark for Natural Language UnderstandingYixin Nie, Adina Williams, Emily Dinan, Mohit Bansal et al.ACL 2020 · 602 citations
  5. Composing Parameter-Efficient Modules with Arithmetic OperationJinghan Zhang, Shiqi Chen, Junteng Liu, Junxian HeNeurIPS 2023 · 164 citations

Related papers

  1. Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting TechniqueMark Russinovich, Yanan Cai, Ahmed SalemICLR 2026 · 51 citations
  2. VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge ProofsGuofu Liao, Taotao Wang, Shengli Zhang, Jiqun Zhang et al.NDSS 2026
  3. MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language ModelsShojiro Yamabe, Futa Kai Waseda, Tsubasa Takahashi, Koki WataokaACL 2025 · 4 citations
  4. Ghost in the Shell: Synonym-Aware Logit Shaping Fingerprint for Copyright Protection of Large Vision-Language ModelsXiaofan Zheng, Xinghao Wang, Xiaojun WanACL Findings 2026
  5. Merging-Resistant Watermarking for LoRA ModulesNa Zhao, Kejiang Chen, Yuang Qi, Kai Zeng et al.ACM MM 2025
Dusk over the sea between two cliffs drawn in fine vertical lines