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

arXiv: https://arxiv.org/abs/2010.13231 · HTML: https://mlsanity.com/paper/2010.13231/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

## Built on by (most cited first, 2 of 2)

- [Synthesis of 3D on-air signatures with the Sigma-Lognormal model](https://mlsanity.com/paper/2401.16329/) (2024)
- [Telling Human and Machine Handwriting Apart](https://mlsanity.com/paper/2601.11700/) (2026)

## Abstract (arXiv)

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.