TypeNet: Deep Learning Keystroke Biometrics

01/14/2021
by   Alejandro Acien, et al.
9

We study the performance of Long Short-Term Memory networks for keystroke biometric authentication at large scale in free-text scenarios. For this we introduce TypeNet, a Recurrent Neural Network (RNN) trained with a moderate number of keystrokes per identity. We evaluate different learning approaches depending on the loss function (softmax, contrastive, and triplet loss), number of gallery samples, length of the keystroke sequences, and device type (physical vs touchscreen keyboard). With 5 gallery sequences and test sequences of length 50, TypeNet achieves state-of-the-art keystroke biometric authentication performance with an Equal Error Rate of 2.2 physical and touchscreen keyboards, respectively, significantly outperforming previous approaches. Our experiments demonstrate a moderate increase in error with up to 100,000 subjects, demonstrating the potential of TypeNet to operate at an Internet scale. We utilize two Aalto University keystroke databases, one captured on physical keyboards and the second on mobile devices (touchscreen keyboards). To the best of our knowledge, both databases are the largest existing free-text keystroke databases available for research with more than 136 million keystrokes from 168,000 subjects in physical keyboards, and 60,000 subjects with more than 63 million keystrokes acquired on mobile touchscreens.

READ FULL TEXT

page 4

page 11

page 13

research
12/26/2022

TypeFormer: Transformers for Mobile Keystroke Biometrics

The broad usage of mobile devices nowadays, the sensitiveness of the inf...
research
07/15/2022

Mobile Keystroke Biometrics Using Transformers

Behavioural biometrics have proven to be effective against identity thef...
research
04/07/2020

TypeNet: Scaling up Keystroke Biometrics

We study the suitability of keystroke dynamics to authenticate 100K user...
research
06/14/2019

Relationship between Number of Subjects and Biometric Authentication Equal Error Rates

The relationship between the number of subjects included in a biometric ...
research
03/14/2022

Mobile Behavioral Biometrics for Passive Authentication

Current mobile user authentication systems based on PIN codes, fingerpri...
research
11/02/2018

Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition

Mobile biometric approaches provide the convenience of secure authentica...
research
06/16/2018

Recurrent neural network-based user authentication for freely typed keystroke data

Keystroke dynamics-based user authentication (KDA) based on long and fre...

Please sign up or login with your details

Forgot password? Click here to reset