Int J Performability Eng ›› 2022, Vol. 18 ›› Issue (10): 741-750.

### Parametric and Non-parametric Analysis on MAOA-based Intelligent IoT-BOTNET Attack Detection Model

Balaganesh Bojarajulua, Sarvesh Tanwara,*, and Thipendra Pal Singhb

1. aAmity Institute of Information Technology, Amity University, Noida, 201313, India;
bSchool of Computer Science, University of Petroleum & Energy Studies, Dehradun, Uttarakhand, 248007, India;
• Submitted on  ;  Revised on  ; Accepted on
• Contact: *E-mail address: s.tanwar1521@gmail.com

Abstract: Recently, an IoT device has taken over as the primary platform for botnet operations. Further research is required to build the proper detection techniques based on the new aspects of botnet assaults since they are not entirely safe. This study aims to develop a parametric analysis of the suggested MAOA hybrid optimization model for intelligent botnet attack detection. The model consists of the extraction of particular features, Improved Information Gain based feature selection, and a hybrid classification-based attack detection model "(Bi-directional Gated Recurrent Unit (BI-GRU)) and Recurrent Neural Network (RNN)," where the training weights of BI-GRU are tuned optimally by MAOA algorithm. Finally, parametric and non-parametric analysis is done to evaluate the performance of the proposed work.

Key words: IoT, RNN, BOTNET, MAOA algorithm, Bi-GRU