Enhanced Artificial Intelligence-based Cybersecurity Intrusion Detection for Higher Education Institutions

Abstract

As higher education institutions (HEIs) go online, several benefits are attained, and also it is vulnerable to several kinds of attacks. To accomplish security, this paper presents artificial intelligence based cybersecurity intrusion detection models to accomplish security. The incorporation of the strategies into business is a tendency among several distinct industries, comprising education, have recognized as game changer. Consequently, the HEIs are highly related to the requirement and knowledge of the learner, making the education procedure highly effective. Thus, artificial intelligence (AI) and machine learning (ML) models have shown significant interest in HEIs. This study designs a novel Artificial Intelligence based Cybersecurity Intrusion Detection Model for Higher Education Institutions named AICID-HEI technique. The goal of the AICID-HEI technique is to determine the occurrence of distinct kinds of intrusions in higher education institutes. The AICID-HEI technique encompasses min-max normalization approach to pre-process the data. Besides, the AICID-HEI technique involves the design of improved differential evolution algorithm based feature selection (IDEA-FS) technique is applied to choose the feature subsets. Moreover, the bidirectional long short-term memory (BiLSTM) model is utilized for the detection and classification of intrusions in the network. Furthermore, the Adam optimizer is applied for hyperparameter tuning to properly adjust the hyperparameters in higher educational institutions. In order to validate the experimental results of the proposed AICID-HEI technique, the simulation results of the AICID-HEI technique take place by the use of benchmark dataset. The experimental results reported the betterment of the AICID-HEI technique over the other methods interms of different measures.