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.

Date of Patent:
Jun. 27, 2023

Filed:

Aug. 27, 2020
Applicants:

International Business Machines Corporation, Armonk, NY (US);

Rensselaer Polytechnic Institute, Troy, NY (US);

Inventors:

Ao Liu, Troy, NY (US);

Sijia Liu, Somerville, MA (US);

Bo Wu, Cambridge, MA (US);

Lirong Xia, Troy, NY (US);

Qi Cheng Li, Beijing, CN;

Chuang Gan, Cambridge, MA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2023.01); G06F 16/56 (2019.01); G06T 3/40 (2006.01); G06T 5/00 (2006.01); G06F 18/21 (2023.01);
U.S. Cl.
CPC ...
G06N 3/08 (2013.01); G06F 16/56 (2019.01); G06F 18/21 (2023.01); G06T 3/4046 (2013.01); G06T 5/002 (2013.01); G06T 2207/20084 (2013.01);
Abstract

Interpretation maps of convolutional neural networks having certifiable robustness using Rényi differential privacy are provided. In one aspect, a method for generating an interpretation map includes: adding generalized Gaussian noise to an image x to obtain T noisy images, wherein the generalized Gaussian noise constitutes perturbations to the image x; providing the T noisy images as input to a convolutional neural network; calculating T noisy interpretations of output from the convolutional neural network corresponding to the T noisy images; re-scaling the T noisy interpretations using a scoring vector υ to obtain T re-scaled noisy interpretations; and generating the interpretation map using the T re-scaled noisy interpretations, wherein the interpretation map is robust against the perturbations.


Find Patent Forward Citations

Loading…