A hybrid network intrusion detection using darwinian particle swarm optimization and stacked autoencoder hoeffding tree

<abstract> <p>Cybersecurity experts estimate that cyber-attack damage cost will rise tremendously. The massive utilization of the web raises stress over how to pass on electronic information safely. Usually, intruders try different attacks for getting sensitive information. An Intrusion Detection System (IDS) plays a crucial role in identifying the data and user deviations in an organization. In this paper, stream data mining is incorporated with an IDS to do a specific task. The task is to distinguish the important, covered up information successfully in less amount of time. The experiment focuses on improving the effectiveness of an IDS using the proposed Stacked Autoencoder Hoeffding Tree approach (SAE-HT) using Darwinian Particle Swarm Optimization (DPSO) for feature selection. The experiment is performed in NSL_KDD dataset the important features are obtained using DPSO and the classification is performed using proposed SAE-HT technique. The proposed technique achieves a higher accuracy of 97.7% when compared with all the other state-of-art techniques. It is observed that the proposed technique increases the accuracy and detection rate thus reducing the false alarm rate.</p> </abstract>

Download Full-text

An Intelligent Network Intrusion Detection System Using Particle Swarm Optimization (PSO) and Deep Network Networks (DNN)

International Journal of Swarm Intelligence Research ◽

10.4018/ijsir.2021040104 ◽

2021 ◽

Vol 12 (2) ◽

pp. 57-73

Author(s):

Preethi D. ◽

Neelu Khare

Keyword(s):

Feature Selection ◽

Particle Swarm Optimization ◽

Intrusion Detection ◽

Intrusion Detection System ◽

Detection System ◽

Particle Swarm ◽

Network Intrusion Detection ◽

Swarm Optimization ◽

Network Intrusion ◽

Proposed Model

Network intrusion detection system (NIDS) plays a major role in ensuring network security. In this paper, the authors propose a PSO-DNN-based intrusion detection system. The correlation-based feature selection (CFS) applied for feature selection with particle swarm optimization (PSO) as search method and deep neural networks (DNN) for classification of network intrusions. The Adam optimizer is applied for optimizing the learning rate, and softmax classifier is used for classification. The experimentations were duly conducted on the standard benchmark NSL-KDD dataset. The proposed model is validated using 10-fold cross-validation and evaluated using the performance metrics such as accuracy, precision, recall, and F1-score. Also, the results are also compared with DNN and CFS+DNN. The experimental results show that the proposed model performs better compared with other methods considered for comparison.

Download Full-text

SOM and PSO Based Alerts Clustering in Intrusion Detection System

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.401-403.1453 ◽

2013 ◽

Vol 401-403 ◽

pp. 1453-1457 ◽

Cited By ~ 1

Author(s):

Yong Wen Jing ◽

Li Fen Li

Keyword(s):

Particle Swarm Optimization ◽

Intrusion Detection ◽

Learning Algorithm ◽

Detection System ◽

Particle Swarm ◽

Binary Particle Swarm Optimization ◽

Self Organizing Maps ◽

Swarm Optimization ◽

Network Intrusion ◽

Comparative Results

With the growing deployment of host and network intrusion detection systems (IDSs), thousands of alerts are generally generated from them per day. Managing these alerts becomes critically important. In this paper, a hybrid alert clustering method based on self-Organizing maps (SOM) and particle swarm optimization (PSO) is presented. We firstly select the important features through binary particle swarm optimization (BPSO) and mutual information (MI) and get a dimension reduced dataset. SOM is used to cluster the dataset. PSO is used to evolve the weights for SOM to improve the clustering result. The algorithm is based on a type of unsupervised machine learning algorithm that infers relationships from data without the need to train the algorithm with expertly labelled data. The approach is validated using the 2000 DARPA intrusion detection datasets and comparative results between the canonical SOM and our scheme are presented.

Download Full-text