.jpg)
METHOD TO GENERATE TRAINING DATA FOR A BOT DETECTOR MODULE, BOT DETECTOR MODULE TRAINED FROM TRAINING DATA GENERATED BY THE METHOD AND BOT DETECTION SYSTEM
EP21702262; PCT/EP2021/051864; 202030066
A method is presented for generating training data for a bot detector module through human interaction with a mobile device. The method comprises receiving at least one signal generated by at least one sensor integrated into the mobile device, with the signal being at least one signal generated during the interaction of a human with the mobile device. The method further comprises calculating scalar and/or time variables of at least one sensor-generated signal that characterize human behavior, thus providing real training data and generating training data comprising at least the real training data. A bots detector module and a bots detection system are also presented.
A new bot detection technology has been developed for digital platforms and services. In recent years the use of mobile devices, smartphones or tablets as well as internet access through these devices has increased, and with it insecurity due to different dangers. Through this detection method based on human interaction with devices and training with models based on real and synthetic data, it is possible to discriminate between normal users and malicious programs. The method allows to generate synthetic swipe gestures using Generative Adversarial Networks and samples acquired during real human-device interaction. This method allows to generate synthetic samples that mimic the human behaviour. The built CAPTCHA system (BeCAPTCHA) models the user behaviour in smartphone interaction using multiple inbuilt sensors The main application lies in the platform and services of the web world, mainly detecting digital fraud. This can be applied both in networks (fake news), in video games, in the banking sector, and others.