Human or Machine? It Is Not What You Write, But How You Write It

TL;DR

This paper demonstrates that analyzing the temporal dynamics of handwriting movements significantly improves the accuracy of distinguishing between human and machine-generated symbols, enhancing security measures.

Contribution

The study shows that temporal sequence analysis outperforms static image analysis in detecting machine-generated handwriting, offering a new approach for behavioral biometric security.

Findings

Static images yield ~75% classification accuracy.

Temporal sequences achieve ~95% accuracy.

Writing dynamics are more indicative of authenticity than the written content.

Abstract

Online fraud often involves identity theft. Since most security measures are weak or can be spoofed, we investigate a more nuanced and less explored avenue: behavioral biometrics via handwriting movements. This kind of data can be used to verify whether a user is operating a device or a computer application, so it is important to distinguish between human and machine-generated movements reliably. For this purpose, we study handwritten symbols (isolated characters, digits, gestures, and signatures) produced by humans and machines, and compare and contrast several deep learning models. We find that if symbols are presented as static images, they can fool state-of-the-art classifiers (near 75% accuracy in the best case) but can be distinguished with remarkable accuracy if they are presented as temporal sequences (95% accuracy in the average case). We conclude that an accurate detection of fake movements has more to do with how users write, rather than what they write. Our work has implications for computerized systems that need to authenticate or verify legitimate human users, and provides an additional layer of security to keep attackers at bay.