Automatically generating security rules for a networked environment based on anomaly detection

Abstract

A computer implemented method of automatically generating security rules for a networked environment based on anomalies identified using Machine Learning (ML), comprising receiving one or more feature vectors each comprising a plurality of operational parameters of a plurality of objects of a networked environment, identifying one or more anomaly patterns in the networked environment by applying one or more trained ML models to the one or more feature vectors trained to identify patterns deviating from normal behavior of the plurality of objects, parsing each anomaly patterns to a set of behavioral rules by traversing the anomaly pattern through a tree-like decision model, and generating one or more security rules for the networked environment according to the set(s) of behavior rules. Wherein the one or more security rules are applied to increase security of the networked environment.