用视觉语言模型零样本验证签名真伪，效果取决于伪造类型。
Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study
- 将笔迹时序数据转为图像，用模型生成生物特征评分。
- 随机伪造下错误率低至0.32%，超越有监督方法。
- 熟练伪造时模型易产生误导性解释，需警惕推理幻觉。
视觉语言模型在通用视觉推理中表现强劲，但在严格生物特征任务中的应用仍未知。本研究探索了先进VLM（GPT-5.2和Gemini 2.5 Pro）在Signature Verification Challenge（SVC）基准上的零样本性能。原始动态笔迹数据转化为静态图像，压力信息以笔画透明度编码。引入新评分协议，通过提取隐含标记概率计算稳健的生物特征分数。实验显示，信号质量与伪造类型显著影响结果：随机伪造下，GPT-5.2在移动端等误差率降至0.32%，优于现有有监督模型；而熟练伪造场景中，因两签名几乎相同，性能大幅下降，并出现“合理化陷阱”——链式思考（CoT）推理导致模型产生笔迹幻觉，将伪造痕迹误判为自然变异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。