US 10,891,374 B1
Systems and methods for improving performance of cascade classifiers for protecting against computer malware
Ryan Curtin, Atlanta, GA (US); and Keith Kenemer, Rosewell, GA (US)
Assigned to CA, INC., San Jose, CA (US)
Filed by CA, INC., San Jose, CA (US)
Filed on Mar. 28, 2018, as Appl. No. 15/938,377.
Int. Cl. G06F 21/56 (2013.01); G06N 20/00 (2019.01)
CPC G06F 21/56 (2013.01) [G06N 20/00 (2019.01); G06F 2221/034 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for improving performance of cascade classifiers for protecting against computer malware, the method being performed by one or more computing devices comprising at least one processor, the method comprising:
receiving a training dataset usable to train a cascade classifier of a machine-learning classification system;
receiving a sample to add to the training dataset;
calculating a weight for the sample using at least a target location for the cascade classifier;
modifying the training dataset using the sample and the weight;
performing a weighted training for the cascade classifier of the machine-learning classification system using the modified training dataset;
identifying computer malware using the cascade classifier; and
in response to identifying the computer malware, performing a security action to protect the one or more computing devices from the computer malware.