# When Simple Statistical Algorithms Outperform Deep Learning: A Case of Keystroke Dynamics

### Ahmed Wahab, Daqing Hou

#### 2023

#### Abstract

Keystroke dynamics has gained relevance over the years for its potential in solving practical problems like online fraud and account takeovers. Statistical algorithms such as distance measures have long been a common choice for keystroke authentication due to their simplicity and ease of implementation. However, deep learning has recently started to gain popularity due to their ability to achieve better performance. When should statistical algorithms be preferred over deep learning and vice-versa? To answer this question, we set up experiments to evaluate two state-of-the-art statistical algorithms: Scaled Manhattan and the Instance-based Tail Area Density (ITAD) metric, with a state-of-the-art deep learning model called TypeNet, on three datasets (one small and two large). Our results show that on the small dataset, statistical algorithms significantly outperform the deep learning approach (Equal Error Rate (EER) of 4.3% for Scaled Manhattan / 1.3% for ITAD versus 19.18% for TypeNet). However, on the two large datasets, the deep learning approach performs better (22.9% & 28.07% for Scaled Manhattan / 12.25% & 20.74% for ITAD versus 0.93% & 6.77% for TypeNet).

Download#### Paper Citation

#### in Harvard Style

Wahab A. and Hou D. (2023). **When Simple Statistical Algorithms Outperform Deep Learning: A Case of Keystroke Dynamics**. In *Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,* ISBN 978-989-758-626-2, pages 363-370. DOI: 10.5220/0011684100003411

#### in Bibtex Style

@conference{icpram23,

author={Ahmed Wahab and Daqing Hou},

title={When Simple Statistical Algorithms Outperform Deep Learning: A Case of Keystroke Dynamics},

booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},

year={2023},

pages={363-370},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0011684100003411},

isbn={978-989-758-626-2},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,

TI - When Simple Statistical Algorithms Outperform Deep Learning: A Case of Keystroke Dynamics

SN - 978-989-758-626-2

AU - Wahab A.

AU - Hou D.

PY - 2023

SP - 363

EP - 370

DO - 10.5220/0011684100003411