SapiAgent: A Bot Based on Deep Learning to Generate Human-Like Mouse Trajectories

Margit Antal, Krisztián Búza, Norbert Fejér

Abstract: The growing interest in bot detection can be attributed to the fact that fraudulent actions performed by bots cause surprisingly high economical damage. State-of-the-art bots aim at mimicking as many as possible aspects of human behavior, ranging from response times and typing dynamics to human-like phrasing and mouse trajectories. In order to support research on bot detection, in this paper, we propose an approach to generate human-like mouse trajectories, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SapiAgent</i> . To implement SapiAgent, we employ deep autoencoders and a novel training algorithm. We performed experiments on our publicly available <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SapiMouse</i> dataset which contains human mouse trajectories collected from 120 subjects. The results show that SapiAgent is able to generate more realistic mouse trajectories compared with Bézier curves and conventional autoencoders.