US 12,278,833 B2
Method and apparatus for testing a malware detection machine learning model
Justas Rafanavičius, Vilnius (LT); Aleksandr Ševčenko, Vilnius (LT); and Mantas Briliauskas, Vilnius (LT)
Assigned to UAB 360 IT, Vilnius (LT)
Filed by UAB 360 IT, Vilnius (LT)
Filed on Oct. 18, 2022, as Appl. No. 17/968,637.
Prior Publication US 2024/0129329 A1, Apr. 18, 2024
Int. Cl. G06F 21/00 (2013.01); G06N 20/00 (2019.01); H04L 9/40 (2022.01)
CPC H04L 63/1433 (2013.01) [G06N 20/00 (2019.01); H04L 63/1416 (2013.01)] 15 Claims
OG exemplary drawing
 
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.