Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Neural network backdoor attack detection method and device and electronic equipment

A technology of neural network and detection method, which is applied in the field of device and electronic equipment, detection method of neural network backdoor attack, can solve the problems of neural network model recognition accuracy reduction, poisoning, etc., to improve recognition accuracy and detection accuracy Effect

Inactive Publication Date: 2020-06-05
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] When training a neural network model, the training data may come from different devices and / or different data providers, so it is very easy to add a specific "back door" to the training data, resulting in a "back door" in the final generated model. The recognition accuracy of the network model is greatly reduced. This phenomenon is called "data poisoning" (data poison)

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
  • Neural network backdoor attack detection method and device and electronic equipment
  • Neural network backdoor attack detection method and device and electronic equipment
  • Neural network backdoor attack detection method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to better understand the technical solutions of this specification, the embodiments of this specification will be described in detail below in conjunction with the accompanying drawings.

[0054] It should be clear that the described embodiments are only some of the embodiments in this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this specification.

[0055] Terms used in the embodiments of the present specification are only for the purpose of describing specific embodiments, and are not intended to limit the present specification. As used in the embodiments of this specification and the appended claims, the singular forms "a", "said" and "the" are also intended to include the plural forms unless the context clearly dictates otherwise.

[0056] In the existing related technologies, when training ...

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 a neural network backdoor attack detection method and device and electronic equipment. In the method, training data is acquired and then used to train a neuralnetwork to obtain a trained neural network model, then training data corresponding to a first label category in the training data is obtained, and the training data corresponding to the first label category is input into the trained neural network model to obtain hidden layer data of the neural network model; and then, the hidden layer data is clustered, and the neural network backdoor attack isdetected according to a clustering result.

Description

technical field [0001] The embodiments of this specification relate to the technical field of artificial intelligence, and in particular to a detection method, device and electronic equipment for a neural network backdoor attack. Background technique [0002] With the development of artificial intelligence, neural network models have been widely used in various industries and play a very important role in various scenarios. [0003] When training a neural network model, the training data may come from different devices and / or different data providers, so it is very easy to add a specific "back door" to the training data, resulting in a "back door" in the final generated model. The recognition accuracy of the network model is greatly reduced. This phenomenon is called "data poisoning". Therefore, it is necessary to provide a method for detecting whether there is a backdoor in the training data and the neural network model. Contents of the invention [0004] The embodiment...

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): G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06N3/045G06F18/23213
Inventor 林建滨
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products