Weblog anomaly detection method in combination with GRU and SVDD

An anomaly detection and logging technology, applied in data exchange networks, digital transmission systems, electrical components, etc., can solve the problems of large manpower and material resources, low detection accuracy, weak detection ability of unknown abnormal types, etc., to achieve good detection and positioning. , the effect of reducing false positives

Active Publication Date: 2019-10-25
FUJIAN NORMAL UNIV
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Problem 1: The traditional anomaly detection algorithm does not reduce the dimensionality of these high-dimensional feature attribute data well. A better method is to randomly extract some features for detection. The detection efficiency of the algorithm is low, and it requires a lot of manpower an

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
  • Weblog anomaly detection method in combination with GRU and SVDD
  • Weblog anomaly detection method in combination with GRU and SVDD
  • Weblog anomaly detection method in combination with GRU and SVDD

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Such as Figure 1-3 As shown in one of them, the present invention discloses a network log anomaly detection method combined with GRU and SVDD, which performs data dimensionality reduction processing on the original network log data set with high correlation between high latitude and characteristic attributes, and converts the attribute features of the network log data set into It is converted into a new principal component that is irrelevant among attributes; then GRU is used to extract the data attribute features after dimensionality reduction preprocessing, and finally the high-efficiency single classification method is used to replace the output layer of GRU to obtain abnormal users.

[0030] Furthermore, the principal component analysis method is used to reduce the dimensionality of the original network log data set with high correlation between high latitude and characteristic attributes.

[0031] Further, the method includes a model training phase and an anomaly ...

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 discloses a weblog anomaly detection method in combination with GRU and SVDD, and the method comprises the steps: carrying out the dimension reduction of a large-scale weblog data set through principal component analysis, and extracting effective attributes; then, using the processed training data set for training a GRU-SVDD classifier model; and finally, inputting an actual log to be detected into the GRU-SVDD comparator, and detecting an exception in the log. The method is superior to classical GRU-MLP, LSTM and other algorithms. According to the method, the abnormal conditionin the test data set can be well detected and positioned.

Description

technical field [0001] The invention relates to the field of network anomaly detection, in particular to a network log anomaly detection method combined with GRU and SVDD. Background technique [0002] With the rapid development of technologies such as big data and the Internet of Things, enterprises put various application services on remote server platforms, which bring a lot of convenience to the people and at the same time, network attacks against big data platform servers have become more common. It is estimated that by 2019, due to the frequent occurrence of global cybercrime, it will bring economic losses of up to 2 trillion US dollars to global enterprises and people. The log data in these servers, that is, the big data platform collects a large amount of high-dimensional normal user access log data. According to the previous literature, effectively ensuring the reliability and security of the system has shown great potential for analyzing and utilizing large-scale ...

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): H04L29/06H04L12/24
CPCH04L41/142H04L63/1425
Inventor 肖如良邹利琼蔡声镇陈雄倪友聪
Owner FUJIAN NORMAL 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