US 11,930,030 B1
Detecting and responding to malicious acts directed towards machine learning models
Tanner Burns, Austin, TX (US); Chris Sestito, Austin, TX (US); and James Ballard, Fredericksburg, VA (US)
Assigned to HiddenLayer Inc., Austin, TX (US)
Filed by HiddenLayer Inc., Leander, TX (US)
Filed on Nov. 8, 2023, as Appl. No. 18/504,995.
Application 18/504,995 is a continuation of application No. 17/866,051, filed on Jul. 15, 2022.
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01); H04L 41/16 (2022.01); H04L 41/22 (2022.01)
CPC H04L 63/1425 (2013.01) [H04L 41/16 (2013.01); H04L 41/22 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for monitoring a machine learning-based system for malicious acts comprising:
receiving vectorization data by a sensor being executed on a server, the vectorization data derived from input data intended for a first machine learning model and provided by a requestor;
receiving, by the sensor, an output generated by the machine learning model, the machine learning model generating the output in response to receiving the vectorization data;
transmitting vectorization data and the output to a processing engine by the sensor;
processing the vectorization data and the output by the processing engine to generate an attack score, the attack score indicating a likelihood of a malicious action towards the machine learning model via the vectorization data; and
applying a response to a request associated with the requestor, the response based at least in part on the attack score, the response applied in place of the output of the first machine learning model, the applying of the response including:
selecting, by a response engine, a response based on an output by a second machine learning model within the processing engine, the output of the second machine learning model including a prediction of an attack on the first machine learning model; and
causing the output of the first machine learning model to be modified or causing the requestor to be disconnected.