Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
Sixu Chen, Xiang Chen, Hongyao Yu, Jiaxin Hong, Hao Fang, Shuoyang Sun, Bin Chen, Shu-Tao Xia

TL;DR
Prompt2Fingerprint introduces a novel, plug-and-play framework that efficiently generates model fingerprints from text descriptions, eliminating the need for resource-intensive retraining and enabling scalable LLM ownership verification.
Contribution
It reformulates LLM fingerprinting as a conditional parameter generation task, allowing instant, reusable fingerprint injection without additional training.
Findings
Maintains high fingerprint accuracy and robustness
Reduces computational overhead significantly
Enables scalable, instant fingerprinting for LLMs
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
