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:
Nov. 28, 2023

Filed:

Jul. 21, 2023
Applicant:

Jiangnan University, Wuxi, CN;

Inventors:

Hengyang Lu, Wuxi, CN;

Chenyou Fan, Wuxi, CN;

Wei Fang, Wuxi, CN;

Jun Sun, Wuxi, CN;

Xiaojun Wu, Wuxi, CN;

Assignee:

JIANGNAN UNIVERSITY, Jiangsu, CN;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 21/56 (2013.01); G06F 18/2415 (2023.01);
U.S. Cl.
CPC ...
G06F 21/566 (2013.01); G06F 18/2415 (2023.01); G06F 2221/034 (2013.01);
Abstract

The present invention provides a text classification backdoor attack method, system, device and a computer storage medium. The method includes: training a pretraining model by using a clean training set to obtain a clean model; generating a pseudo label data set by using a positioning label generator; performing multi-task training on a Sequence-to-Sequence model by using the pseudo label data set to obtain a locator model; generating a backdoor data set by using the locator model; and training the clean model by using the backdoor data set to obtain a dirty model. A pseudo label data set is generated by using a pretrained clean model without manual annotation. A backdoor attack location in a text sequence may be dynamically predicted by using a locator model based on a Sequence-to-Sequence and multi-task learning architecture without manual intervention, and a performance indicator obtained by dynamically selecting an attack location is better.


Find Patent Forward Citations

Loading…