An Efficient Anomaly Intrusion Detection Method With Feature Selection and Evolutionary Neural Network

Samira Sarvari,Nor Fazlida Mohd Sani,Mohd Taufik Abdullah,Zurina Mohd Hanapi

doi:10.1109/access.2020.2986217

Samira Sarvari, Nor Fazlida Mohd Sani + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.2986217

Copy DOI

Abstract

Recently, with the technological and digital revolution, the security of data is very crucial as a massive amount of data is generated from various networks. Intrusion Detection System (IDS) has been observed to be perhaps the best solution because of its capability to distinguish between attacks that originate within or outside a corporate network. In this study, the most significant features for enhancing the IDS efficiency and creating a smaller dataset in order to reduce the execution time for detecting attacks are selected from the sizeable network dataset. This research designed an anomaly-based detection, by adopting the modified Cuckoo Search Algorithm (CSA), called Mutation Cuckoo Fuzzy (MCF) for feature selection and Evolutionary Neural Network (ENN) for classification. The proposed search algorithm uses mutation to more accurately examine the search space, to allow candidates to escape local minima. Moreover, the value of the solution is evaluated based on the objective function and the Fuzzy C Means (FCM) clustering method used to provide the best results for the overlapping dataset and create the fuzzy membership search domain which includes all possible compromise solutions. A proposed model has been practically used to the problem of intrusion detection as well as been validated using the NSL-KDD dataset. The experimental results reveal that reducing features by selecting and utilizing the most relevant features can improve execution time and at the same time enhance the efficiency and performance of IDS.

Highlights

In recent years, the number of smart device users is rapidly increasing
The training method considered the capabilities of the Multiverse Optimizer (MVO) with respect to high exploration and exploitation to determine the optimal values of weights and biases of ARTIFICIAL NEURAL NETWORK (ANN)-Multilayer Perceptron (MLP)
This model applied to the problem of intrusion detection and is validated using the well-known dataset, NSL-KDD

Summary

INTRODUCTION

The number of smart device users is rapidly increasing This steered to a substantial rise in network traffic. Several methods were proposed to highlight an issue associated with the IDS, amongst them are the Feature Selection (FS) methods and optimization techniques. The optimization algorithms have been designed based on ideas inspired by nature involving a selection of the best option for certain given objectives. These kinds of algorithms can be grouped into three classes: SwarmBased Algorithms (SBAs), Evolutionary Algorithms (EAs), and Trajectory-Based Algorithms (TBAs). The CSA has gotten a lot of researchers’ attention compared with other techniques This is because it is related to a small number of components required within the initial search.

RELATED WORK

CUCKOO SEARCH WITH FUZZY C MEANS

EXPERIMENTAL SETUP AND RESULTS

RESULTS AND DISCUSSION

Findings

CONCLUSION AND SUMMARY