Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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

Yifei Zhao, Qian Lou, Mengxin Zheng• 2026

Related benchmarks

TaskDatasetResultRank
Fingerprint MatchingQuantization Fingerprint Queries
Performance (4-bit)88
16
Fingerprint MatchingV7W
FMR0.52
16
Fingerprint MatchingPaintingForm
FMR47
16
Fingerprint MatchingMathV
FMR45
16
Fingerprint MatchingTextVQA
FMR43
16
Fingerprint MatchingLlavaMix
FMR31
7
Fingerprint MatchingTikZ
FMR37
7
Fingerprint MatchingGUI-Actor
FMR72
7
Fingerprint MatchingARC-AGI 1
FMR89
7
Showing 9 of 9 rows

Other info

Follow for update