Papers
arxiv:2604.17041

SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models

Published on Apr 18
Authors:
,
,

Abstract

Large vision-language models face challenges with unauthorized reuse and intellectual property infringement, prompting the development of a non-intrusive ownership verification framework that uses semantically aligned fingerprint distillation and robust optimization techniques to create stealthy and resilient copyright protection mechanisms.

AI-generated summary

The public accessibility of large vision-language models (LVLMs) raises serious concerns about unauthorized model reuse and intellectual property infringement. Existing ownership verification methods often rely on semantically abnormal queries or out-of-distribution responses as fingerprints, which can be easily detected and removed by adversaries. We expose this vulnerability through a Semantic Divergence Attack (SDA), which identifies and filters fingerprint queries by measuring semantic divergence between a suspect model and a reference model, showing that existing fingerprints are not semantic-preserving and are therefore easy to detect and bypass. To address these limitations, we propose SIF (Semantically In-Distribution Fingerprints), a non-intrusive ownership verification framework that requires no parameter modification. SIF introduces Semantic-Aligned Fingerprint Distillation (SAFD), which transfers text watermarking signals into the visual modality to produce semantically coherent yet fingerprinted responses. In addition, Robust-Fingerprint Optimization (RFO) enhances robustness by simulating worst-case representation perturbations, making the fingerprints resilient to model modifications such as fine-tuning and quantization. Extensive experiments on LLaVA-1.5 and Qwen2.5-VL demonstrate that SIF achieves strong stealthiness and robustness, providing a practical solution for LVLM copyright protection. Code is available at https://github.com/UCF-ML-Research/SIF-VLM-Fingerprint

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2604.17041
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/2604.17041 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2604.17041 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.