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

A DDoS detection method for household IoT devices based on machine learning

A networked device and machine learning technology, applied in machine learning, instruments, computing, etc., can solve problems such as differences and achieve the effect of reducing losses

Active Publication Date: 2020-03-17
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the traffic of IoT devices differs greatly from that of other internet-connected devices such as laptops and smartphones

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 for household IoT devices based on machine learning
  • A DDoS detection method for household IoT devices based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] A machine learning-based DDoS detection method for home Internet of Things devices, which is used to realize high-precision DDoS detection of specific network behaviors of Internet of Things devices, specifically includes the following steps:

[0030] S101. A local network is established, such as figure 1 As shown, the local network established in this embodiment includes routers, multiple mainstream household IoT devices, attack devices and DoS targets.

[0031] Specifically, mainstream household IoT devices are mainly used to achieve normal traffic, while attacking equipment and DoS targets are mainly used for DoS attacks. Among them, the mainstream household IoT devices in this embodiment specifically include network cameras, smart speakers and Smart bracelet with bluetooth connection to android smartphone.

[0032] At the same time, in this embodiment, the Linux virtual machine on the server is used as the DoS source, that is, the attack device, and the Apache Web ...

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 DDoS detection method of household Internet of Things equipment based on machine learning, comprising the following steps: A. establishing a local network to simulate the network of household Internet-of-things equipment to generate normal data and DoS data; B, collecting normal data and DoS data generated in the step A, and carrying out feature analysis and feature extraction on the collected normal data and DoS data; C. deviding the feature data into a training set and a test set, wherein the train set is used for training a machine learning decision tree, a randomfor model and generating a binary classification model, and the test set is used for verifying the accuracy rate and the recall rate of the generated binary classification model to weigh the feasibility of the machine learning model in detecting DDoS traffic; D. running the generated binary classification model on the network middleware for data acquisition, feature extraction, packet classification and identification of normal traffic packets and DoS traffic packets. The method of the invention can realize high-precision DDoS detection for specific network behavior.

Description

technical field [0001] The invention relates to the technical field of Internet of Things security detection and machine learning, in particular to a machine learning-based DDoS detection method for household Internet of Things devices. Background technique [0002] Although more and more Internet of Things (IoT) devices are connected to the Internet, many of them are not secure, which further deteriorates the Internet environment. Insecure IoT devices allow botnets to attack them. Using unsecured home IoT devices, some botnets, such as Mirai, conduct distributed denial-of-service (DDoS) attacks on critical infrastructure. The growing threat has prompted the development of new techniques to identify and block attack traffic from IoT botnets. [0003] Recent anomaly detection research has shown that machine learning can be used to identify malicious web traffic. At the same time, the traffic of IoT devices differs greatly from that of other internet-connected devices such a...

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): H04L29/06G06N20/00H04L29/08
CPCH04L63/1416H04L63/1425H04L63/1458H04L67/12H04L2463/141H04L2463/142H04L2463/144
Inventor 江佳峻
Owner SICHUAN CHANGHONG ELECTRIC CO LTD