PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement

Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, Meng Han


Abstract
Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challenges from incremental fine-tuning erasure and feature-space defense due to their reliance on overfitting high-perplexity trigger patterns. We firstly reveal that, model editing in the fingerprint domain exhibits unique advantages including significantly lower false positive rates, enhanced harmlessness, and superior robustness. Building on this foundation, this paper innovatively proposes a Prefix-enhanced Fingerprint Editing Framework (PREE), which encodes copyright information into parameter offsets through dual-channel knowledge edit to achieve covert embedding of fingerprint features. Experimental results demonstrate that the proposed solution achieves the 90% trigger precision in mainstream architectures including LLaMA-3 and Qwen-2.5. The minimal parameter offset (change rate < 0.03) effectively preserves original knowledge representation while demonstrating strong robustness against incremental fine-tuning and multi-dimensional defense strategies, maintaining zero false positive rate throughout evaluations.
Anthology ID:
2025.findings-emnlp.204
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3794–3804
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.204/
DOI:
Bibkey:
Cite (ACL):
Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, and Meng Han. 2025. PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 3794–3804, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement (Yue et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.204.pdf
Checklist:
 2025.findings-emnlp.204.checklist.pdf