METHOD FOR ADJUSTING THE PARAMETERS OF A MACHINE LEARNING MODEL IN ORDER TO IDENTIFY FALSE TRIGGERING AND INFORMATION SECURITY INCIDENTS Russian patent published in 2021 - IPC G06F21/55 G06N20/00 

FIELD: computing technology.

SUBSTANCE: server-implemented method for adjusting the parameters of a machine learning model in order to identify false triggering and information security incidents (hereinafter incidents), wherein verdicts are changed for a certain part of information security events (hereinafter the first set of events) with a "false triggering" verdict to "incident" verdicts, wherein verdicts for events are determined using a machine learning model for determining false triggering and/or incidents, wherein the first set of events is selected, in particular, randomly among events with a "false triggering" verdict, wherein such an amount of events of the first set is selected that does not exceed the second threshold, which is a parameter of the machine learning model; at least part of the events of the first set of events are sent for analysis to the analytical center; using the analysis results containing the verdicts issued to the events sent for analysis, the parameters of the machine learning model are adjusted to determine false triggering and/or incidents.

EFFECT: reduction in the amount of false triggering.

19 cl, 7 dwg