Saved in:
Bibliographic Details
Main Authors: Li, Yue, Yi, Xin, Shi, Dongsheng, Cui, Yongyi, de Melo, Gerard, Wang, Linlin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.03122
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914270211473408
author Li, Yue
Yi, Xin
Shi, Dongsheng
Cui, Yongyi
de Melo, Gerard
Wang, Linlin
author_facet Li, Yue
Yi, Xin
Shi, Dongsheng
Cui, Yongyi
de Melo, Gerard
Wang, Linlin
contents Establishing reliable and verifiable fingerprinting mechanisms is fundamental to controlling the unauthorized redistribution of large language models (LLMs). However, existing approaches face two major challenges: (a) ensuring imperceptibility, including resistance to statistical identification and avoidance of accidental activation during fingerprint construction, and (b) preserving both model utility and fingerprint detectability under subsequent model modifications. To address these challenges, we propose an end-to-end fingerprinting framework with two components. First, we design a rule-based code-mixing fingerprint (CF) that maps natural-query-like prompts to multi-candidate targets, reducing accidental triggering via high-complexity code-mixing formulations. Second, we introduce Multi-Candidate Editing (MCEdit), which jointly optimizes multi-candidate targets and enforces margins between target and non-target outputs to improve post-modification detectability. Extensive experiments demonstrate that our framework provides a robust and practical solution for fingerprinting LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Construction to Injection: Edit-Based Fingerprints for Large Language Models
Li, Yue
Yi, Xin
Shi, Dongsheng
Cui, Yongyi
de Melo, Gerard
Wang, Linlin
Computation and Language
Artificial Intelligence
Machine Learning
Establishing reliable and verifiable fingerprinting mechanisms is fundamental to controlling the unauthorized redistribution of large language models (LLMs). However, existing approaches face two major challenges: (a) ensuring imperceptibility, including resistance to statistical identification and avoidance of accidental activation during fingerprint construction, and (b) preserving both model utility and fingerprint detectability under subsequent model modifications. To address these challenges, we propose an end-to-end fingerprinting framework with two components. First, we design a rule-based code-mixing fingerprint (CF) that maps natural-query-like prompts to multi-candidate targets, reducing accidental triggering via high-complexity code-mixing formulations. Second, we introduce Multi-Candidate Editing (MCEdit), which jointly optimizes multi-candidate targets and enforces margins between target and non-target outputs to improve post-modification detectability. Extensive experiments demonstrate that our framework provides a robust and practical solution for fingerprinting LLMs.
title From Construction to Injection: Edit-Based Fingerprints for Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.03122