Machine Learning Model Score Obfuscation Using Time-based Score Oscillations

Patent metadata

Field	Value
Publication number	US-2020349462-A1
Application number	US-201916399718-A
Country	US
Kind code	A1
Filing date	Apr 30, 2019
Priority date	Apr 30, 2019
Publication date	Nov 5, 2020
Grant date	—

Abstract

An artefact is received. Features are later extracted from the artefact and are used to populate a vector. The vector is input into a classification model to generate a score. This score is then modified using a time-based oscillation function and is provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
receiving an artefact; extracting features from the artefact and populating a vector; inputting the vector into a classification model to generate a score; modifying the score using a time-based oscillation function; and providing the modified score to a consuming application or process.

2 . The method of claim 1 further comprising reducing features in the vector prior to the inputting into the classification model.

3 . The method of claim 2 , wherein the features are reduced using random projection matrices.

4 . The method of claim 2 , wherein the features are reduced using principal component analysis.

5 . The method of claim 1 , wherein the classification model is a machine learning model trained using a training data set and providing a continuous scale output.

6 . The method of claim 1 , wherein the classification model characterizes the artefact as being malicious or benign to access, execute, or continue to execute.

7 . The method of claim 6 further comprising: preventing access or execution of the artefact when the classification model characterizes the artefact as being malicious.

8 . The method of claim 1 , wherein the time-based oscillation function is made of a combination of simpler periodic functions.

9 . The method of claim 1 , wherein the time-based oscillation function is bounded by maximum and minimum values.

10 . The method of claim 1 , wherein the time-based oscillation function includes attenuation to bound the magnitude of the generated noise.

11 . A system comprising:
at least one data processor; and memory storing instructions which, when executed by the at least one data processor, result in operations comprising:
receiving an artefact;
extracting features from the artefact and populating a vector;
inputting the vector into a classification model to generate a score;
modifying the score using a time-based oscillation function; and
providing the modified score to a consuming application or process.

12 . The system of claim 11 , wherein the operations further comprise: comprising reducing features in the vector prior to the inputting into the classification model.

13 . The system of claim 12 , wherein the features are reduced using random projection matrices.

14 . The system of claim 12 , wherein the features are reduced using principal component analysis.

15 . The system of claim 11 , wherein the classification model is a machine learning model trained using a training data set and providing a continuous scale output.

16 . The system of claim 11 , wherein the classification model characterizes the artefact as being malicious or benign to access, execute, or continue to execute.

17 . The system of claim 16 further comprising: preventing access or execution of the artefact when the classification model characterizes the artefact as being malicious.

18 . The system of claim 11 , wherein the time-based oscillation function is made of a combination of simpler periodic functions.

19 . The system of claim 11 , wherein the time-based oscillation function is bounded by maximum and minimum values.

20 . The system of claim 11 , wherein the time-based oscillation function includes attenuation to bound the magnitude of the generated noise.

Assignees

• Cylance Inc

Inventors

• Buckingham Hailey
• Beveridge David N

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• G06F21/629

  to features or functions of an application · CPC title

• G06F21/75 Primary

  by inhibiting the analysis of circuitry or operation · CPC title

• G06F21/554

  involving event detection and direct action · CPC title

• G06F2221/032

  Protect output to user by software means · CPC title