# Telling Human and Machine Handwriting Apart

arXiv: https://arxiv.org/abs/2601.11700 · HTML: https://mlsanity.com/paper/2601.11700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 64 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [DeepWriting: Making Digital Ink Editable via Deep Generative Modeling](https://mlsanity.com/paper/1801.08379/) (2018)
- [Handwriting Transformers](https://mlsanity.com/paper/2104.03964/) (2021)
- [Out-of-Domain Detection for Low-Resource Text Classification Tasks](https://mlsanity.com/paper/1909.05357/) (2019)
- [Disentangling Writer and Character Styles for Handwriting Generation](https://mlsanity.com/paper/2303.14736/) (2023)
- [DeepWriteSYN: On-Line Handwriting Synthesis via Deep Short-Term Representations](https://mlsanity.com/paper/2009.06308/) (2020)
- [Diffusion models for Handwriting Generation](https://mlsanity.com/paper/2011.06704/) (2020)
- [Generating Handwriting via Decoupled Style Descriptors](https://mlsanity.com/paper/2008.11354/) (2020)
- [BeCAPTCHA-Mouse: Synthetic Mouse Trajectories and Improved Bot Detection](https://mlsanity.com/paper/2005.00890/) (2020)
- [BehavePassDB: Public Database for Mobile Behavioral Biometrics and Benchmark Evaluation](https://mlsanity.com/paper/2206.02502/) (2022)
- [MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification](https://mlsanity.com/paper/2210.08836/) (2022)
- [iDeLog: Iterative Dual Spatial and Kinematic Extraction of Sigma-Lognormal Parameters](https://mlsanity.com/paper/2401.15473/) (2024)
- [Static and Dynamic Synthesis of Bengali and Devanagari Signatures](https://mlsanity.com/paper/2401.17026/) (2024)
- [Ubicomp Digital 2020 -- Handwriting classification using a convolutional recurrent network](https://mlsanity.com/paper/2008.01078/) (2020)
- [Human or Machine? It Is Not What You Write, But How You Write It](https://mlsanity.com/paper/2010.13231/) (2020)

## Abstract (arXiv)

Handwriting movements can be leveraged as a unique form of behavioral biometrics, to verify whether a real user is operating a device or application. This task can be framed as a reverse Turing test in which a computer has to detect if an input instance has been generated by a human or artificially. To tackle this task, we study ten public datasets of handwritten symbols (isolated characters, digits, gestures, pointing traces, and signatures) that are artificially reproduced using seven different synthesizers, including, among others, the Kinematic Theory (Sigma h model), generative adversarial networks, Transformers, and Diffusion models. We train a shallow recurrent neural network that achieves excellent performance (98.3 percent Area Under the ROC Curve (AUC) score and 1.4 percent equal error rate on average across all synthesizers and datasets) using nonfeaturized trajectory data as input. In few-shot settings, we show that our classifier achieves such an excellent performance when trained on just 10 percent of the data, as evaluated on the remaining 90% of the data as a test set. We further challenge our classifier in out-of-domain settings, and observe very competitive results as well. Our work has implications for computerized systems that need to verify human presence, and adds an additional layer of security to keep attackers at bay.