Patent · US Active

Resiliency of machine learning models

US10733287B2 · kind B2 · utility

3Cited by

0References

20Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Manish Kesarwani · Bengaluru, IN
Suranjana Samanta · Bengaluru, IN
Deepak Vijaykeerthy · Chennai, IN
Sameep Mehta · Bengaluru, IN
Karthik Sankaranarayanan · Kanchinakote, IN

Key dates

Filing date	May 14, 2018
Grant date	Aug 4, 2020
Priority date	—
Expiry date	Feb 1, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06N20/00
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

One embodiment provides a method, including: deploying a machine learning model, wherein the deployed machine learning model is used in responding to queries from users; receiving, at the deployed machine learning model, input from a user; identifying a type of machine learning model attack corresponding to the received input; computing, responsive to receiving the input, a resiliency score of the machine learning model, wherein the resiliency score indicates resistance of the machine learning model against the identified type of attack; and performing an action responsive to the computed resiliency score.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.