Hacker Intrusion Detection System Based on Artificial Neural Network

2012 ◽  
Vol 263-266 ◽  
pp. 2924-2928
Author(s):  
Jing Huang ◽  
Hai Bin Chen ◽  
Jiang Zhang ◽  
Han Bo Zhang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
System Model ◽  
Data Set ◽  
Advantages And Disadvantages ◽  
Network Intrusion ◽  
Artificial Neural

In this paper, some scholars’ idea of applying neural network technology in the design of hacker intrusion detection system model and making a hacker intrusion detection system model based on artificial neural network is adopted. This study selects KDDCup’99 for network intrusion detection data set to learn the characteristics of the intrusion accurately; completes the normalization of all characteristics to achieve rapid convergence of the artificial neural network; analyses the advantages and disadvantages of different neural network training functions; achieves a high accuracy rate for intrusion detection successfully.

scholarly journals Classification of Intrusion using Artificial Neural Network with GWO

2020 ◽  
Vol 9 (4) ◽  
pp. 599-606
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Intrusion Detection ◽  
Detection System ◽  
Denial Of Service ◽  
Data Set ◽  
Detection Systems ◽  
Network Intrusion ◽  
Network Intrusion Detection Systems ◽  
Artificial Neural

In the present milieu of connected world, where security is the major concern, Intrusion Detection System is the prominent area of research to deal with various types of attacks in network. Intrusion detection systems (IDS) finds the dynamic and malicious traffic of network, in accordance to the aspect of network. Various form of IDS has been developed working on distinctive approaches. One popular approach is machine learning in which various algorithms like ANN, SVM etc. have been used. But the most prominent method used is ANN. The performance of the ANN can significantly be improved by combining it with different metaheuristic algorithms. In present work, GWO is used to optimize ANN. For this KDD-99 data-set is used to classify various types of attacks i.e. denial of service (DOS), normal and other form of attack. The present paper provides detailed analysis of the performance of Artificial Neural Network and optimized Artificial Neural Network with GA, PSO and GWO. The research shows that ANN with GWO outperform as compared to others (ANN, ANN with PSO and ANN with GA).

Development of Intrusion Detection System for Security Threats in Internet of Things Using Artificial Neural Network

2019 ◽  
Vol 16 (8) ◽  
pp. 3242-3245
Author(s):  
R. Ramadevi ◽  
N. R. Krishnamoorthy ◽  
D. Marshiana ◽  
Sujatha Kumaran ◽  
N. Aarthi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Internet Of Things ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Denial Of Service ◽  
Security Threats ◽  
Data Set ◽  
Artificial Neural

Internet of things (IoT) is a revolutionary technology which changes our life and work. Many industry sectors such as manufacturing, transportation, utilities, health care, consumer electronics and automobiles are invested and adopted towards IoT technology. The major inconvenience with IoT is its safety, as it is prone to attack by hackers. Detection Systems are used to detect these intrusions to protect the information and communication systems. Hence it is essential to design an intrusion detection system for security threats of IoT networks. This paper focuses, on the development of Artificial Neural Network (ANN) based Intrusion Detection System for threat analysis in IoT network. KDD-99 data set with Denial of Service (DoS) type attack is used to train and test three different ANN models. In this research, a Feed Forward Back Propagation (FFBP) network is used to detect the DoS attack. The process of optimization of a FFBP network involves comparison of classification accuracy during both training and testing in terms of true positive and false positive rates. For the data set considered the optimised network has achieved 100% efficiency during both training and testing.

Sign in / Sign up

Export Citation Format

Share Document