Hybrid Approach for Network Intrusion Detection System Using Random Forest Classifier and Rough Set Theory for Rules Generation

2019 ◽  
pp. 274-287
Author(s):  
Nilesh B. Nanda ◽  
Ajay Parikh
Keyword(s):  
Random Forest ◽  
Intrusion Detection ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Detection System ◽  
Hybrid Approach ◽  
Random Forest Classifier ◽  
Network Intrusion Detection ◽  
Network Intrusion

Rough Set Theory Based Hybrid Method for Network Intrusion Detection

2013 ◽  
Vol 373-375 ◽  
pp. 815-818
Author(s):  
Na Jiao
Keyword(s):  
Intrusion Detection ◽  
Set Theory ◽  
Rough Set ◽  
Hybrid Method ◽  
Rough Set Theory ◽  
Network Intrusion Detection ◽  
Large Network ◽  
Fuzzy C Means ◽  
Network Intrusion ◽  
International Knowledge

In this paper, we propose an intrusion detection method that combines rough set theory and Fuzzy C-Means for network intrusion detection. The first step consists of feature selection which is based on rough set theory. The next phase is clustering by using Fuzzy C-Means. Rough set theory is an efficient tool for further reducing redundancy. Fuzzy C-Means allows objects which are belong to several clusters simultaneously, with different degrees of membership. To evaluate the performance of the introduced approach, we applied them to the international Knowledge Discovery and Data mining intrusion detection dataset. In the experimentations, we compare the performance of the rough set theory based hybrid method for network intrusion detection. Experimental results illustrate that our algorithm is accurate model for handling complex attack patterns in large network. And the method can increase the efficiency and reduce the dataset by looking for overlapping categories.

scholarly journals Random Forest Classifier Based Network Intrusion Detection System

2021 ◽  
Vol 9 (VI) ◽  
pp. 4603-4608
Author(s):  
Aadhar Dutta
Keyword(s):  
Random Forest ◽  
Intrusion Detection ◽  
Private Information ◽  
Intrusion Detection System ◽  
Detection System ◽  
Random Forest Classifier ◽  
Network Intrusion Detection ◽  
Detection Model ◽  
Digital World ◽  
Network Intrusion

In today's digital world, we all use the Internet and connect to a network, but all the data we send or receive, is safe? Some kind of attack is present in network packets that might access the computer's private information to the hacker. We cannot see and tell whether a network is safe to connect with or not, so we made a Network Intrusion Detection Model predict whether these network packets are secure or some attack is there on the package. We use Random Forest Classifier to obtain the maximum accuracy. To test our model in real-time, we have created a packet sniffer that would sniff out network packets, convert them into required features, and then try it in our model to predict the legitimacy of the network packet.

Intrusion Detection Using Modern Techniques

2011 ◽  
pp. 259-273
Author(s):  
Tarum Bhaskar ◽  
Narasimha Kamath B.
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Artificial Neural Network ◽  
Intrusion Detection ◽  
Set Theory ◽  
Rough Set ◽  
Intrusion Detection System ◽  
Rough Set Theory ◽  
Detection System ◽  
Mining Tools

Intrusion detection system (IDS) is now becoming an integral part of the network security infrastructure. Data mining tools are widely used for developing an IDS. However, this requires an ability to find the mapping from the input space to the output space with the help of available data. Rough sets and neural networks are the best known data mining tools to analyze data and help solve this problem. This chapter proposes a novel hybrid method to integrate rough set theory, genetic algorithm (GA), and artificial neural network. Our method consists of two stages: First, rough set theory is applied to find the reduced dataset. Second, the results are used as inputs for the neural network, where a GA-based learning approach is used to train the intrusion detection system. The method is characterized not only by using attribute reduction as a pre-processing technique of an artificial neural network but also by an improved learning algorithm. The effectiveness of the proposed method is demonstrated on the KDD cup data.

Sign in / Sign up

Export Citation Format

Share Document