Adversarial sample generation method and device based on text extension, medium and equipment

A technology of confronting samples and generating devices, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as the inability to reveal model robustness, small vocabulary changes, etc., to enrich the expression form of sentences and ensure the syntactic structure correctness effect

Pending Publication Date: 2021-01-15
TSINGHUA UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, the resistant samples thus generated are close to the original text with only small lexical changes, which may not reveal all the robustness issues of the model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Adversarial sample generation method and device based on text extension, medium and equipment
  • Adversarial sample generation method and device based on text extension, medium and equipment
  • Adversarial sample generation method and device based on text extension, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The principle and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present invention, rather than to limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0033] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, device, method or computer program product. Therefore, the present disclosure may be embodied in the form of complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0034] According to the embodiments of the present invention, a method, device, medium and...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention provides an adversarial sample generation method and device based on text extension, a medium and equipment. The method comprises the steps of analyzing a syntactic structure of an original text to obtain a target component which can be modified in the syntactic structure; determining a modification language type for modifying the target component according to the syntactic structure of the original text; taking the target component and the revision language type as input, and generating a revision language through a text generation model; and inserting the revision after the position of the target component to generate the adversarial sample. The original text is expanded to generate the adversarial sample by inserting the revision language, so that the statement expression form of the adversarial sample is greatly enriched, and the syntactic structure correctness of the text and the readability of the text are ensured.

Description

technical field [0001] Embodiments of the present invention relate to the field of natural language processing, and more specifically, embodiments of the present invention relate to a method, device, medium, and device for generating an adversarial example based on text expansion. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] In an adversarial environment, the deep neural network model will be input with some maliciously constructed adversarial samples (for example, pictures or voice information) based on normal samples. Under the attack of adversarial samples, the deep neural network model will make wrong predictions. Therefore, the use of adversarial examples to attack deep neural networks can detect potential vulnerabilities in deep neural network models, and then b...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/211G06F40/268G06N3/04G06N3/08
CPCG06F40/211G06F40/268G06N3/08G06N3/045
Inventor 黄民烈邵智宏
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap