The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Mar. 03, 2026
Filed:
Sep. 19, 2022
International Business Machines Corporation, Armonk, NY (US);
Massachusetts Institute of Technology, Cambridge, MA (US);
Lam Minh Nguyen, Ossining, NY (US);
Wang Zhang, Cambridge, MA (US);
Subhro Das, Cambridge, MA (US);
Pin-Yu Chen, White Plains, NY (US);
Alexandre Megretski, Acton, MA (US);
Luca Daniel, Cambridge, MA (US);
INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US);
MASSACHUSETTS INSTITUTE OF TECHNOLOGY, Cambridge, MA (US);
Abstract
A computer implemented method for certifying robustness of image classification in a neural network is provided. The method includes initializing a neural network model. The neural network model includes a problem space and a decision boundary. A processor receives a data set of images, image labels, and a perturbation schedule. Images are drawn from the data set in the problem space. A distance from the decision boundary is determined for the images in the problem space. A re-weighting value is applied to the images. A modified perturbation magnitude is applied to the images. A total loss function for the images in the problem space is determined using the re-weighting value. A confidence level of the classification of the images in the data set is evaluated for certifiable robustness.