Unlock instant, AI-driven research and patent intelligence for your innovation.

Backdoor sample detection method, system and device

A sample detection and sample technology, applied in the field of data security, can solve problems such as vulnerability to attack, decline in model recognition accuracy, and model contamination by backdoor samples

Active Publication Date: 2020-06-02
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This will cause the model to be polluted by backdoor samples and be vulnerable to attack
Model recognition accuracy drops

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
  • Backdoor sample detection method, system and device
  • Backdoor sample detection method, system and device
  • Backdoor sample detection method, system and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the following briefly introduces the drawings that need to be used in the description of the embodiments. Apparently, the accompanying drawings in the following description are only some examples or embodiments of this specification, and those skilled in the art can also apply this specification to other similar scenarios. Unless otherwise apparent from context or otherwise indicated, like reference numerals in the figures represent like structures or operations.

[0017] It should be understood that "system", "device", "unit" and / or "module" as used herein is a method for distinguishing different components, elements, components, parts or assemblies of different levels. However, the words may be replaced by other expressions if other words can achieve the same purpose.

[0018] As indicated in the specification and claims, the terms "a", "an", "an" and / or "the...

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 discloses a backdoor sample detection method, system and device. The method comprises the following steps: acquiring a plurality of training samples and a target modeldetermined based on the plurality of training samples, wherein the plurality of training samples belong to at least two sample categories; for any sample category, inputting each training sample in the sample category into the target model to obtain response data of the target model to each training sample; based on the response data corresponding to the training samples, determining feature datareflecting overall distribution of the response data; respectively comparing the response data corresponding to each training sample with the feature data to obtain a plurality of comparison results;and analyzing the plurality of comparison results, and determining whether the training samples in the sample category include backdoor samples or not. Therefore, whether the samples contain the backdoor sample or not can be detected on the premise of not marking data, the model is prevented from being polluted by the backdoor sample, and the accuracy of the model is improved.

Description

technical field [0001] This specification relates to the technical field of data security, in particular to a backdoor sample detection method, system and device. Background technique [0002] Due to its excellent performance, machine learning has been widely used in various scenarios, such as computer vision (CV), natural language processing (NLP), etc., and plays a vital role in various industries. Because of this, the security issues of machine learning are very worthy of attention. For example, adding backdoor samples to the training data of the model for backdoor attack will cause the trained model to misclassify the samples containing the backdoor. This will cause the model to be polluted by backdoor samples and vulnerable to attacks. The accuracy of model recognition drops. Therefore, it is necessary to provide a data processing method to improve the safety and reliability of machine learning models. Contents of the invention [0003] One of the embodiments of t...

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
IPC IPC(8): G06K9/62
CPCG06F18/232G06F18/241
Inventor 任彦昆
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD