A ddos ​​detection method based on deep learning

A DDOS and detection method technology, applied in the field of network communication, can solve the problems of ferocious attacks and difficult prevention

Active Publication Date: 2020-04-28
ZHEJIANG GONGSHANG UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since DDoS is different from a DoS attack that only needs a computer terminal and a modem, a DDoS attack uses a group of controlled machines to launch an attack on a fixed site at the same time. Such attacks are fierce and difficult to guard against. more destructive

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
  • A ddos ​​detection method based on deep learning
  • A ddos ​​detection method based on deep learning
  • A ddos ​​detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] The present invention will be further described below in conjunction with embodiment.

[0041] The specific process of DDOS detection involved in the present invention can be described as follows:

[0042] The open source network data set ISCX2012 (Information Security Center of Excellence 2012) is used as a sample of the deep learning network model in the DDoS attack detection scheme based on deep learning. ISCX2012 records 7 days of traffic information in the real network environment, including legitimate network traffic and various types of malicious DDoS attack traffic.

[0043] (1) The specific embodiment of the feature processing stage

[0044] (1.1) Extract 20 data message fields from the ISCX2012 dataset as feature values, and define the corresponding data types of the fields. The specific content is shown in Table 1, and a set of specific examples about these 20 fields are given.

[0045] Table 1 Data characteristic field type

[0046]

[0047]

[0048...

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 present invention discloses a DDOS detection method based on deep learning. The method comprises a feature processing stage and a model detection stage. In the feature processing stage, feature extraction, format conversion and dimension reconstruction are performed on an input data packet. In the model detection stage, a processed feature is input into a deep learning network model to detect whether the input data packet is a DDOS attack packet. The DDOS detection method based on deep learning of the present invention utilizes the features such as high-level data abstracted through deep learning, automatic learning, and easy model updating, and is superior to the traditional DDOS detection method in detection accuracy and independency of software and hardware equipment.

Description

technical field [0001] The invention relates to the technical field of network communication, in particular to a DDOS detection method based on deep learning. Background technique [0002] With the rapid development of the global informatization process, attackers in the network take advantage of the security loopholes in the system architecture of the network and the server system in the network, or steal personal information of network users, or destroy the normal network environment, or prevent the target host from Normal interactive communication, the network environment is facing increasingly serious security challenges. With the explosive growth of the number of Internet users in recent years, new network applications, such as social networking, high-definition online video, and innovative service models, such as cloud computing and big data, have brought new challenges to traditional networks. The development of the traditional network architecture in terms of networ...

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 Patents(China)
IPC IPC(8): H04L29/06
CPCH04L63/1458
Inventor 李传煌孙正君龚梁金蓉王伟明
Owner ZHEJIANG GONGSHANG UNIVERSITY
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