# BeCAPTCHA-Type: Biometric Keystroke Data Generation for Improved Bot Detection

arXiv: https://arxiv.org/abs/2207.13394 · HTML: https://mlsanity.com/paper/2207.13394/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 42 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 8 of 8)

- [Neural Autoregressive Distribution Estimation](https://mlsanity.com/paper/1605.02226/) (2016)
- [TypeNet: Deep Learning Keystroke Biometrics](https://mlsanity.com/paper/2101.05570/) (2021)
- [A Survey of Privacy Vulnerabilities of Mobile Device Sensors](https://mlsanity.com/paper/2106.10154/) (2021)
- [BeCAPTCHA-Mouse: Synthetic Mouse Trajectories and Improved Bot Detection](https://mlsanity.com/paper/2005.00890/) (2020)
- [SetMargin Loss applied to Deep Keystroke Biometrics with Circle Packing Interpretation](https://mlsanity.com/paper/2109.00938/) (2021)
- [Fast Free-text Authentication via Instance-based Keystroke Dynamics](https://mlsanity.com/paper/2006.09337/) (2020)
- [Mobile Keystroke Biometrics Using Transformers](https://mlsanity.com/paper/2207.07596/) (2022)
- [Robust Keystroke Biometric Anomaly Detection](https://mlsanity.com/paper/1606.09075/) (2016)

## Built on by (most cited first, 3 of 3)

- [Type2Branch: Keystroke Biometrics based on a Dual-branch Architecture with Attention Mechanisms and Set2set Loss](https://mlsanity.com/paper/2405.01088/) (2024)
- [Blockchain and Biometrics: Survey, GDPR Analysis, and Future Directions](https://mlsanity.com/paper/2302.10883/) (2023)
- [Rendering on Real Silicon: GPU Render-Timing as a Passive, AI-Resistant CAPTCHA Signal](https://mlsanity.com/paper/2607.23389/) (2026)

## Abstract (arXiv)

This work proposes a data driven learning model for the synthesis of keystroke biometric data. The proposed method is compared with two statistical approaches based on Universal and User-dependent models. These approaches are validated on the bot detection task, using the keystroke synthetic data to improve the training process of keystroke-based bot detection systems. Our experimental framework considers a dataset with 136 million keystroke events from 168 thousand subjects. We have analyzed the performance of the three synthesis approaches through qualitative and quantitative experiments. Different bot detectors are considered based on several supervised classifiers (Support Vector Machine, Random Forest, Gaussian Naive Bayes and a Long Short-Term Memory network) and a learning framework including human and synthetic samples. The experiments demonstrate the realism of the synthetic samples. The classification results suggest that in scenarios with large labeled data, these synthetic samples can be detected with high accuracy. However, in few-shot learning scenarios it represents an important challenge. Furthermore, these results show the great potential of the presented models.