Designing an Intelligent Cybersecurity Intrusion Identify Framework Using Advanced Machine Learning Models in Cloud Computing

Mukund Sai Vikram Tyagadurgam, Venkataswamy Naidu Gangineni, Sriram Pabbineedi, Mitra Penmetsa, Jayakeshav Reddy Bhumireddy, Rajiv Chalasani

Citation: Mukund Sai Vikram Tyagadurgam, Venkataswamy Naidu Gangineni, Sriram Pabbineedi, Mitra Penmetsa, Jayakeshav Reddy Bhumireddy, Rajiv Chalasani, "Designing an Intelligent Cybersecurity Intrusion Identify Framework Using Advanced Machine Learning Models in Cloud Computing", Universal Library of Engineering Technology, Special Issue.

Copyright: This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

An effective method to attain improved security in identifying harmful activity in cloud computing during the past number of years has been A system for detecting intrusions (IDS). Efforts are being made on an intrusion detection system (IDS) to detect and classify network-level intrusions using machine learning (ML) techniques. Using a Bidirectional Long Short-Term Memory (Bi-LSTM) model, this paper proposes an intelligent cybersecurity intrusion detection system that can recognize complex attack patterns in network data. To apply a comprehensive data pre-processing pipeline over the CICIDS2017 dataset, it has performed numerical feature extraction, z-score normalization, and one-hot encoding for recognizing multi-class labels and SMOTE for the solution of class-imbalance problem. While its performance outpaced all others, the Bi-LSTM model improved at capturing both forward and backward time dependencies and obtained A 99% F1-score, a 98.51% accuracy rate, a 99% precision rate, and a 98% recall rate. Training and validation curves indicated strong generalization, and the normalized confusion matrix confirmed high classification accuracy across diverse intrusion types. A comparative analysis showed that the Bi-LSTM model outperformed traditional classifiers such as Naïve Bayes and Deep Multilayer Perceptron, establishing its effectiveness for advanced intrusion detection in intelligent cybersecurity systems. The study offers practical advice for choosing the best IDS models depending on certain network settings and security needs.


Keywords: Cyber-Attacks, Cybersecurity, Intrusion Detection System, Machine Learning, Deep Learning, Bi-LSTM.

Download doi https://doi.org/10.70315/uloap.ulete.2022.003