A Machine Learning Framework for Intrusion Detection System in IoT Networks Using an Ensemble Feature Selection Method

2021 ◽  
Author(s):  
Ge Guo
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Feature Selection Method ◽  
Selection Method ◽  
Learning Framework

scholarly journals IDSFS: A Signature Based Intrusion Detection System with High Pertinent Feature Selection Method

2019 ◽  
Vol 8 (2) ◽  
pp. 25-31
Author(s):  
S. Latha ◽  
Sinthu Janita Prakash
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
False Positive Rate ◽  
Feature Selection Method ◽  
Selection Method ◽  
Positive Rate ◽  
Frame Work ◽  
Pertinent Feature

Securing a network from the attackers is a challenging task at present as many users involve in variety of computer networks. To protect any individual host in a network or the entire network, some security system must be implemented. In this case, the Intrusion Detection System (IDS) is essential to protect the network from the intruders. The IDS have to deal with a lot of network packets with different characteristics. A signature-based IDS is a potential tool to understand former attacks and to define suitable method to conquest it in variety of applications. This research article elucidates the objective of IDS with a mechanism which combines the network and host-based IDS. The benchmark dataset for DARPA is considered to generate the IDS mechanism. In this paper, a frame work IDSFS – a signature-based IDS with high pertinent feature selection method is framed. This frame work consists of earlier proposed Feature Selection method (HPFSM), Artificial Neural Network for classification of nodes or packets in the network, then the signatures or attack rules are configured by implementing Association Rule mining algorithm and finally the rules are restructured using a pattern matching algorithm-Aho-Corasick to ease the rule checking. The metrics like number of features, classification accuracy, False Positive Rate (FPR), Precision, Number of rules, Running Time and Memory consumption are checked and proved the proposed frame work’s efficiency.

scholarly journals Wrapper-Based Feature Selection Analysis For Semi-Supervised Anomaly Based Intrusion Detection System

2020 ◽  
Vol 5 (2) ◽  
pp. 32
Author(s):  
Andreas Jonathan Silaban ◽  
Satria Mandala ◽  
Erwid Jadied Mustofa
Keyword(s):  
Logistic Regression ◽  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Feature Selection Method ◽  
Past Research ◽  
Selection Method ◽  
Improve Accuracy ◽  
Wrapper Feature Selection

<p>Intrusion Detection System (IDS) plays as a role in detecting various types of attacks on computer networks. IDS identifies attacks based on a classification data network. The result of accuracy was weak in past research. To solve this problem, this research proposes using a wrapper feature selection method to improve accuracy detection. Wrapper-Feature selection works in the preprocessing stage to eliminate features. Then it will be clustering using a semi-supervised method. The semi-supervised method divided into two steps. There are supervised random forest and unsupervised using Kmeans. The results of each supervised and unsupervised will be ensembling using linear and logistic regression. The combination of wrapper and semi-supervised will get the maximum result.</p>

scholarly journals A Signature Based Intrusion Detection System with HPFSM and Fuzzy Based Classification Method (IDSFSC)

2019 ◽  
Vol 8 (2) ◽  
pp. 23-29
Author(s):  
S. Latha ◽  
Sinthu Janita Prakash
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
False Positive Rate ◽  
Feature Selection Method ◽  
Selection Method ◽  
Individual Host ◽  
Positive Rate ◽  
Frame Work

Securing a network from the attackers is a challenging task at present as many users involve in variety of computer networks. To protect any individual host in a network or the entire network, some security system must be implemented. In this case, the Intrusion Detection System (IDS) is essential to protect the network from the intruders. The IDS has to deal with a lot of network packets with different characteristics. A signature-based IDS is a potential tool to understand former attacks and to define suitable method to conquest it in variety of applications. This research article elucidates the objective of IDS with a mechanism which combines the network and host-based IDS. The benchmark dataset for DARPA is considered to generate the IDS mechanism. In this paper, a frame work IDSFSC – signature-based IDS with high pertinent feature selection method is framed. This frame work consists of earlier proposed Feature Selection Method (HPFSM with Enhanced Artificial Neural Network (EANN) for classification of nodes or packets in the network, then the signatures or attack rules are configured by implementing Association Rule mining algorithm and finally the rules are restructured using a pattern matching algorithm-Aho-Corasick to ease the rule checking. The metrics classification accuracy, False Positive Rate (FPR) and Precision are checked and proved the proposed frame work’s efficiency.

An intelligent flow-based and signature-based IDS for SDNs using ensemble feature selection and a multi-layer machine learning-based classifier

2020 ◽  
pp. 1-20
Author(s):  
K. Muthamil Sudar ◽  
P. Deepalakshmi
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Network Architecture ◽  
Detection System ◽  
Software Defined Networking ◽  
Control Plane ◽  
Control Logic ◽  
Data Plane

Software-defined networking is a new paradigm that overcomes problems associated with traditional network architecture by separating the control logic from data plane devices. It also enhances performance by providing a highly-programmable interface that adapts to dynamic changes in network policies. As software-defined networking controllers are prone to single-point failures, providing security is one of the biggest challenges in this framework. This paper intends to provide an intrusion detection mechanism in both the control plane and data plane to secure the controller and forwarding devices respectively. In the control plane, we imposed a flow-based intrusion detection system that inspects every new incoming flow towards the controller. In the data plane, we assigned a signature-based intrusion detection system to inspect traffic between Open Flow switches using port mirroring to analyse and detect malicious activity. Our flow-based system works with the help of trained, multi-layer machine learning-based classifier, while our signature-based system works with rule-based classifiers using the Snort intrusion detection system. The ensemble feature selection technique we adopted in the flow-based system helps to identify the prominent features and hasten the classification process. Our proposed work ensures a high level of security in the Software-defined networking environment by working simultaneously in both control plane and data plane.

Sign in / Sign up

Export Citation Format

Share Document