US 11,698,967 B2
System for automated malicious software detection
Joshua Holden Jennings, South Royalton, VT (US); and Timothy Paul Kenney, Richmond, VT (US)
Assigned to SOOS LLC, Winooski, VT (US)
Filed by SOOS LLC, Winooski, VT (US)
Filed on Aug. 12, 2022, as Appl. No. 17/887,002.
Application 17/887,002 is a continuation of application No. 17/460,611, filed on Aug. 30, 2021, granted, now 11,436,330.
Claims priority of provisional application 63/203,255, filed on Jul. 14, 2021.
Prior Publication US 2023/0019837 A1, Jan. 19, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 7/04 (2006.01); G06F 21/56 (2013.01); G06F 40/20 (2020.01); G06N 20/00 (2019.01)
CPC G06F 21/566 (2013.01) [G06F 40/20 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for automated malicious software detection, the system comprising a computing device, the computing device comprising:
a processor; and
a memory communicatively connected to the processor, the memory containing instructions configuring the processor to:
receive a software component, wherein the software component comprises at least an element of software metadata, wherein the at least an element of software metadata comprises a component name;
obtain a source repository, wherein the source repository comprises at least an element of source metadata;
identify a string distance between the at least an element of software metadata and the at least an element of source metadata, wherein identifying the string distance further comprises:
determining a download count of the software component;
determining a download count of the at least an element of source metadata; and
determining the string distance as a function of a difference between the download count of the software component and the download count of the at least an element of source metadata;
generate a malicious machine-learning model as a function of a malicious training set, wherein the malicious training set correlates a metadata difference to a malicious identifier; and
determine a malicious quantifier as a function of the malicious machine-learning model and the string distance.