Abstract :

The Project Seeks To Create A System For Identifying Distributed Denial Of Service (DDOS) The Usage Of Sophisticated Techniques, Specifically Machine Learning Algorithms Including Logistics Regression, K-Nearest Neighbor And Random Forest. The Proposed Technique Aims To Benefit A High Degree Of Accuracy In Figuring Out DDOS Attacks. Precise Detection Is Essential For Proper Alleviation Of Such Threats. The Aim Of The Research Is To Overcome Current Methodologies And Significantly Improve DDOS Attacks. This Means Emphasis On Innovations And Improved Solutions. The Project Selects The NSL KDD Data File To Evaluate The Proposed Models. This Data File Is Selected Because To Reduce Redundancy With Respect To Others, Which Brings Better And More Accurate Results During Testing And Evaluation. The Project Performs A Comparative Analysis Of Many Machine Learning Classifiers, Including LR, RF, DT And KNN. This Comparison Emphasizes The Advantages And Disadvantages Of Several DDOS Attack Detection. The Project Approach Includes A Systematic Procedure, Including Data Collection, Function Extraction And Classification. It Uses The Characteristics And Network Behavior As The Basic Elements For Detection Procedure. This Shows The Methodological Approach For The Improvement Of The DDOS Detection System. The DDOS Detection Undertaking Includes A Comprehensive Record Method With A Voting Classifier That Integrates RF And Adaboost, In Addition To A Stacking Classifier That Combines RF, MLP And LightGBM. This Goal Is To Increase The Overall Performance Of The Gadget The Usage Of The Additional Properties Of Several Device Getting To Know Techniques. “Index Terms - DDoS; Deep Learning; Random Forest; Logistic Regression; KNN; NSL KDD Dataset”.

Published:

30-7-2025

Issue:

Vol. 25 No. 7 (2025)

Page Nos:

897-907

Section:

Articles

License:

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

How to Cite