Research and Implementation of Intrusion Detection System Based on Artificial Neural Network

2010 ◽  
Vol 129-131 ◽  
pp. 1421-1425
Author(s):  
Xiao Cui Han

Through the research on intrusion detection and artificial neural network, this paper designs an intrusion detection system based on artificial neural network, in detail describes the theory and implementation of all modules, and then carries out test and analysis for it, the results show that it has great advantages in web-based intrusion detection.

Internet of Things (IoT) makes everything in the real world to get connected. The resource constrained characteristics and the different types of technology and protocols tend to the IoT be more vulnerable than the conventional networks. Intrusion Detection System (IDS) is a tool which monitors analyzes and detects the abnormalities in the network activities. Machine Learning techniques are implemented with the Intrusion detection systems to enhance the performance of IDS. Various studies on IoT reveals that Artificial Neural Network (ANN) provides better accuracy and detection rate than other approaches. In this paper, an Artificial Neural Network based IDS (ANNIDS) technique based on Multilayer Perceptron (MLP) is proposed to detect the attacks initiated by the Destination Oriented Direct Acyclic Graph Information Solicitation (DIS) attack and Version attack in IoT environment. Contiki O.S/Cooja Simulator 3.0 is used for the IoT simulation.


Sign in / Sign up

Export Citation Format

Share Document