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:
May. 24, 2022

Filed:

Jun. 05, 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);

Abhishek Bhandwaldar, Somerville, MA (US);

Chuang Gan, Cambridge, MA (US);

Lirong Xia, Troy, NY (US);

Qi Cheng Li, Beijing, CN;

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06T 1/00 (2006.01); G06T 5/00 (2006.01); G06T 5/20 (2006.01); G06N 3/02 (2006.01); G06T 5/50 (2006.01);
U.S. Cl.
CPC ...
G06T 1/005 (2013.01); G06N 3/02 (2013.01); G06T 5/003 (2013.01); G06T 5/20 (2013.01); G06T 5/50 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20216 (2013.01);
Abstract

Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.


Find Patent Forward Citations

Loading…