Abstract
Cyber attacks are increasing with the advent of advanced network technologies. With the rising security demands, the detection of cyber-attacks has emerged as a promising field that offers big prospect for the researcher in the field of cyber security. In the similar scenario, authors have proposed an improved multi-malware detection system that could effectively detect attacks as DDoS, malware, spoofing. Firstly Genetic Algorithm used to select potential feature from dataset, followed by Artificial Bee Colony with Discrete Wavelet Transform to further filters out the irrelevant features. A Hybrid classifier ANN-SVM used to enhance the classification efficiency of our proposed system in identifying the cyber-attacks. The novelty of the work lies in the precise detection of the malicious behaviour of the nodes. The simulation study over 100 rounds reflects the performance of the proposed system in terms of higher precision, recall and f-measure. The proposed IDS outperformed existing work with improved precision of 0.112, 0.062 and 0.224 and recall of 0.049, 0.159 and 0.022 in comparison to the three existing works dedicated to DDoS, Malware and Spoofing attacks. Also, the performance of the proposed work in terms of True Positive rate (TPR), False Positive rate (FPR), and accuracy shows better performance compared to existing works.

Key words: Cyber Attacks, Intrusion Detection System (IDS), Artificial Neural Network (ANN), Artificial Bee colony (ABC), Support Vector Machine (SVM).