Papers
arxiv:2602.09434

A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors

Published on Feb 10
Authors:
,

Abstract

A fingerprinting framework uses refusal vectors from safety-aligned large language models to track provenance and identify base model families robustly against modifications, with privacy-preserving verification extensions.

Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel fingerprinting framework that leverages the behavioral patterns induced by safety alignment, applying the concept of refusal vectors for LLM provenance tracking. These vectors, extracted from directional patterns in a model's internal representations when processing harmful versus harmless prompts, serve as robust behavioral fingerprints. Our contribution lies in developing a fingerprinting system around this concept and conducting extensive validation of its effectiveness for IP protection. We demonstrate that these behavioral fingerprints are highly robust against common modifications, including finetunes, merges, and quantization. Our experiments show that the fingerprint is unique to each model family, with low cosine similarity between independently trained models. In a large-scale identification task across 76 offspring models, our method achieves 100\% accuracy in identifying the correct base model family. Furthermore, we analyze the fingerprint's behavior under alignment-breaking attacks, finding that while performance degrades significantly, detectable traces remain. Finally, we propose a theoretical framework to transform this private fingerprint into a publicly verifiable, privacy-preserving artifact using locality-sensitive hashing and zero-knowledge proofs.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2602.09434
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2602.09434 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2602.09434 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2602.09434 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.