US 12,353,543 B1
Systems and methods for utilizing multiple analysis techniques to distinguish stalkerware from privacy-invasive application types
Kevin Alejandro Roundy, Culver City, CA (US); and Acar Tamersoy, Culver City, CA (US)
Assigned to Gen Digital Inc., Tempe, AZ (US)
Filed by GEN DIGITAL INC., Tempe, AZ (US)
Filed on Jun. 28, 2022, as Appl. No. 17/809,375.
Int. Cl. G06F 21/55 (2013.01)
CPC G06F 21/554 (2013.01) [G06F 2221/033 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for utilizing multiple analysis techniques to distinguish stalkerware from privacy-invasive application types, at least a portion of the method being performed by one or more computing devices comprising at least one processor, the method comprising:
inspecting, by the one or more computing devices, application package data associated with a target application;
analyzing, by the one or more computing devices, application marketplace data comprising text and image data for the target application to determine one or more descriptions of potential privacy-invasive actions;
predicting, by the one or more computing devices and utilizing a program machine learning classifier, one or more sensitive data leaks associated with the target application based on the application package data;
predicting, by the one or more computing devices and utilizing a marketplace data machine learning classifier, surveillance activities associated with the target application based on the one or more descriptions of the potential privacy-invasive actions; and
performing, by the one or more computing devices, a security action that assigns a privacy invasion category to the target application based on the predicted one or more sensitive data leaks and the predicted surveillance activities to distinguish the target application from among a plurality of invasive application types comprising stalkerware and other privacy invasion application types.