A new patent application for an invention to WIPO (World Intellectual Property Organization)

A study on the application of machine learning methods to detect suspicious activities of IT system users by analyzing a multifactor environment has been completed. The study resulted in a new invention filed with the World Intellectual Property Organization (WIPO). Patent title “SYSTEM AND METHOD FOR DETECTING ATYPICAL BEHAVIOR OF USERS IN AN INFORMATION SYSTEM BY ANALYZING THEIR ACTIONS USING A MARKOV CHAIN AND AN ARTIFICIAL NEURAL NETWORK”.

The invention will allow to extend the functionality of the product e-StepControl anomaly detection algorithm. Multifactor analysis against IT system users will be used to detect anomalies. The new atypical activity detection algorithm takes into account at least the following factors:

• the sequence of user activities,
• time intervals between activities,
• web browser version,
• IP address,
• activity ON or OFF hours,
• other events.

It is planned to include multifactor analysis algorithm for anomaly detection in e-StepControl version 3.0. The release of the new version of the product is planned for the 3th quarter of 2021.