Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Sixu, Chen, Xiang, Yu, Hongyao, Hong, Jiaxin, Fang, Hao, Sun, Shuoyang, Chen, Bin, Xia, Shu-Tao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917510923681792
author Chen, Sixu
Chen, Xiang
Yu, Hongyao
Hong, Jiaxin
Fang, Hao
Sun, Shuoyang
Chen, Bin
Xia, Shu-Tao
author_facet Chen, Sixu
Chen, Xiang
Yu, Hongyao
Hong, Jiaxin
Fang, Hao
Sun, Shuoyang
Chen, Bin
Xia, Shu-Tao
contents The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing LLM fingerprinting methods, particularly active approaches that embed identity signals via fine-tuning, achieve high accuracy and robustness, they suffer from significant scalability bottlenecks. These methods typically treat fingerprint injection as an independent, one-off optimization task rather than a reusable capability, necessitating separate, resource-intensive training for every new identity. This incurs prohibitive computational costs and deployment delays. To address this, we propose Prompt2Fingerprint (P2F), the first framework that reformulates fingerprinting as a conditional parameter generation task. By leveraging a specialized generator, P2F maps textual descriptions directly to low-rank parameter increments in a single forward pass, enabling plug-and-play LLM fingerprint injection without further model retraining. Our experiments demonstrate that P2F maintains high fingerprint accuracy, harmlessness, and robustness while significantly reducing computational overhead, offering a scalable and instant solution for LLM ownership management.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18474
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
Chen, Sixu
Chen, Xiang
Yu, Hongyao
Hong, Jiaxin
Fang, Hao
Sun, Shuoyang
Chen, Bin
Xia, Shu-Tao
Cryptography and Security
Artificial Intelligence
Computation and Language
Machine Learning
The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing LLM fingerprinting methods, particularly active approaches that embed identity signals via fine-tuning, achieve high accuracy and robustness, they suffer from significant scalability bottlenecks. These methods typically treat fingerprint injection as an independent, one-off optimization task rather than a reusable capability, necessitating separate, resource-intensive training for every new identity. This incurs prohibitive computational costs and deployment delays. To address this, we propose Prompt2Fingerprint (P2F), the first framework that reformulates fingerprinting as a conditional parameter generation task. By leveraging a specialized generator, P2F maps textual descriptions directly to low-rank parameter increments in a single forward pass, enabling plug-and-play LLM fingerprint injection without further model retraining. Our experiments demonstrate that P2F maintains high fingerprint accuracy, harmlessness, and robustness while significantly reducing computational overhead, offering a scalable and instant solution for LLM ownership management.
title Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
topic Cryptography and Security
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2605.18474