Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study
摘要
Recent advancements in Vision-Language Models (VLMs) have demonstrated strong capabilities in general visual reasoning, yet their applicability to rigorous biometric tasks remains unexplored. This work presents an exploratory study evaluating the zero-shot performance of state-of-the-art VLMs (GPT-5.2 and Gemini 2.5 Pro) on the Signature Verification Challenge (SVC) benchmark. To enable visual processing, raw kinematic time-series are converted into static images, encoding pressure information into stroke opacity whenever available in the source data. Furthermore, we introduce a scoring protocol that extracts latent token probabilities to compute robust biometric scores. Experimental results reveal a significant performance dichotomy dependent on signal quality and forgery type. In random forgery scenarios, the zero-shot VLM achieves exceptional discrimination, with GPT-5.2 reaching an Equal Error Rate of 0.32% in mobile tasks, outperforming supervised state-of-the-art systems. Conversely, in skilled forgery scenarios, where the task is more challenging because both signatures are almost identical, the results are significantly worse, and a critical "Rationalization Trap" emerges: chain-of-thought (CoT) reasoning degrades performance as the model produces kinematic hallucinations to justify forgery artifacts as natural variability.
引用
@article{arxiv.2605.14845,
title = {Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study},
author = {Marta Robledo-Moreno and Ruben Vera-Rodriguez and Ruben Tolosana and Javier Ortega-Garcia},
journal= {arXiv preprint arXiv:2605.14845},
year = {2026}
}
备注
Accepted at the 14th International Workshop on Biometrics and Forensics