US 12,111,925 B1
Methods and apparatus for detecting and preventing obfuscated cyberattacks using machine learning techniques
Vikram Hegde, Milpitas, CA (US); and Chunsheng Victor Fang, Mountain View, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Mar. 2, 2023, as Appl. No. 18/177,524.
Application 18/177,524 is a continuation of application No. 16/582,265, filed on Sep. 25, 2019, granted, now 11,620,379.
Claims priority of provisional application 62/739,283, filed on Sep. 30, 2018.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/55 (2013.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06N 3/04 (2023.01); G06N 3/088 (2023.01); G06N 20/00 (2019.01)
CPC G06F 21/554 (2013.01) [G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06N 3/04 (2013.01); G06N 3/088 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium comprising code which, when executed by a processor, cause the processor to:
monitor, via the processor, a set of command lines received via a command line interface, each command line from the set of command lines associated with an executable script configured to be executed by an operating system;
convert a command line from the set of command lines into a numerical form in a vector data structure;
classify, after converting the command line and via a machine learning model, the command line into an obfuscation category; and
prevent the operating system from executing the command line when the obfuscation category indicates that the command line is part of a cybersecurity attack.