| CPC H04L 63/1433 (2013.01) [G06N 20/00 (2019.01); H04L 63/1416 (2013.01)] | 15 Claims |

|
1. A method for testing a machine learning model comprising:
selecting a first dataset including malware samples collected over a first period;
training a machine learning model using the first dataset;
selecting a second dataset including malware samples collected over a second period having a beginning that is shifted in time by a predefined amount with respect to a beginning of the first period so that the second dataset contains malware samples to which the trained machine learning model has not been exposed and a time-shifted portion of the first dataset; and
testing the machine learning model using the second dataset.
|