Method and system for time series anomaly detection based on secure multi-party

A time series, anomaly detection technology, applied in the field of anomaly detection, can solve problems such as lack of research on cloud security, achieve great practical value, and solve the effect of privacy issues

Active Publication Date: 2017-11-14
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing time series research, the research on cloud security is still relatively scarce

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
  • Method and system for time series anomaly detection based on secure multi-party
  • Method and system for time series anomaly detection based on secure multi-party
  • Method and system for time series anomaly detection based on secure multi-party

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] specific implementation plan

[0017] The present invention will be described in further detail below through specific embodiments in conjunction with the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0018] In the prior art, the time series data is considered to be centralized, and the algorithms adopted also consider the current data set to be complete. In practical applications, the data distribution is often scattered. For example, the ECG data of a patient may be stored in three hospitals A, B, and C in a certain area. Therefore, when analyzing the patient's ECG data, it is necessary to integrate the data of A, B, and C to form a complete data set, and perform data mining on the complete data.

[0019] as attached figure 1 As shown, time series A and time series B are electrocardiogram (ECG) data of the same patient belonging to two hospitals, A and B, respectively. Hospital B now wants to find anomalies in time s...

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 invention provides a system and a method for time series anomaly detection based on secure multi-party. The system includes a server side and a user side. The server side includes at least two servers: a server C and a server S. Time series constituting a complete data set are stored in the server side in a distributed manner. The server C is a server providing service for the user side. Multi-party time series sharing is carried out between the server S and the server C based on a BCP encryption system. The server S is semi-honest, and has a master key mk for decryption. Disturbance is added to all operations in which S participates, in order to prevent S from getting relevant information about users. The server C and the server S initialize the BCP encryption system. The server C encrypts the time series stored therein, and then supplies the time series to the server S. The server S detects whether the time series are abnormal under a security protocol. The time series anomaly detection based on secure multi-party presented by the invention is of great practical value.

Description

technical field [0001] The invention relates to the technical field of anomaly detection, in particular to a time series anomaly detection method and system based on secure multi-party. Background technique [0002] In real life, various fields contain a large amount of time series data, such as patient's ECG data, EEG data, parameter data of a large number of sensors in power plants, network flow data, and so on. The abnormal subsequence (pattern) detection of time series is a very important field. Most of the time series data containing abnormal patterns are in normal form. The frequency of abnormal patterns is very small, but the rare abnormal patterns contain very important Information. Abnormal ECG data means that the patient may suffer from a certain type of heart disease. Abnormal EEG data may be caused by brain diseases such as epilepsy. Timely detection of abnormal ECG or EEG data can play a role in subsequent treatment. The abnormal sensor data of the factory may...

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): H04L29/06
Inventor 张春慨
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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