Abstract :

Nowadays, The Problem Of Network Security Is More Important Than Ever In The Currently In- Terconnected World. Denial Of Service (DoS) And Distributed Denial Of Service (DDoS) Is Perhaps One Of The Most Exaggerated And Highly Prevalent Risks That Online Structures Face. Such Attacks Clog Networks With Bogus Traffic That Result In Disruptions And Access Of Services Is Unavailable To Authorized Users. Intrusion Detection Systems (IDS) Tend To Malfunction When They Are Used Against Novel Or Even Variant Kinds Of Such Attacks Because It Operates With A Set Of Baselines, Such As Signatures That Are Always Pre-determined. It Is A Suggestion Of An Intelligent Hybrid Intru- Sion Detection Approach With The Combined Forces Of The Convolutional Neural Networks (CNN) And Long-Short Term Memory (LSTM) Models. The CNN Component Identifies The Spatial Variations Of The Network Traffic. Where As LSTM Network Detects The Temporal Dynamics. Combined, They Create A Very Effective Model That Can Identify Sophisticated, Multi-faceted, Attack Vectors On The Fly. A Web-based Dashboard To Help Monitor The System And Interact With The User Is Developed By Means Of The Django And Bootstrap Tools. Traffic Visualizations And System Logs, Which An Administrator Can Act Promptly On. Furthermore, The System Is Designed To Have Adaptive Mechanism Of Learning That Will Enable It To Be Always Updated And Improved Basing On Latest Traffic Data. Model Training And Testing Apply CICIDS2017 Dataset, Thereby Creating A Strong And Viable Testing Plat- Form. In General, The Solution Proposed Could Be Used To Have An Accurate, Scalable And Adaptive Im- Plementation Of DoS, DDoS Attack Detection And Mitigation Ensuring A Basis Of Future Enhances To The Network Security Through AI Technology. Keywords: DoS/ DDoS Attacks, CNN, LSTM, Cybersecurity, Deep Learning, Machine Learn- Ing Decision Tree, Random Forest, XGBoost, Ad- ABoost, And Logistic Regression.

Published:

17-7-2025

Issue:

Vol. 25 No. 7 (2025)

Page Nos:

496 - 505

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite