US 11,810,339 B2
Neural network host platform for detecting anomalies in cybersecurity modules
Adam Jason, Zelienople, PA (US)
Assigned to Proofpoint, Inc., Sunnyvale, CA (US)
Filed by Proofpoint, Inc., Sunnyvale, CA (US)
Filed on May 10, 2022, as Appl. No. 17/740,740.
Application 17/740,740 is a continuation of application No. 17/038,727, filed on Sep. 30, 2020, granted, now 11,361,198.
Claims priority of provisional application 63/040,770, filed on Jun. 18, 2020.
Prior Publication US 2022/0269911 A1, Aug. 25, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/62 (2022.01); G06N 3/02 (2006.01); G06V 10/778 (2022.01); G06F 18/2433 (2023.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01); G06V 10/94 (2022.01); H04L 9/40 (2022.01)
CPC G06V 10/7784 (2022.01) [G06F 18/2148 (2023.01); G06F 18/2185 (2023.01); G06F 18/2433 (2023.01); G06N 3/02 (2013.01); G06V 10/95 (2022.01); H04L 63/14 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing platform, comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive information defining a training module;
capture a plurality of screenshots corresponding to different permutations of the training module;
pre-process each screenshot of the plurality of screenshots corresponding to different permutations of the training module;
input, into an auto-encoder, the pre-processed screenshots corresponding to the different permutations of the training module, wherein inputting the pre-processed screenshots corresponding to the different permutations of the training module causes the auto-encoder to compare the pre-processed screenshots to anticipated screenshots for the training module to output a reconstruction error value;
identify, based on the reconstruction error value, an outlier permutation of the training module;
generate a user interface comprising information identifying the outlier permutation of the training module; and
send the user interface to at least one user device.