Rule-Based Intrusion Detection System Using Logical Analysis Of Data
Keywords:
Network Security, Machine Learning, Intrusion Detection System, Logical Analysis Of Data (LAD”)Abstract
The Increasing Prevalence And Complexity Of Cyber-Attacks Provide A Significant Danger To Organizational
Network Infrastructures. This Study Responds To The Crucial Necessity For Efficient Intrusion Detection Systems
(IDS) By Way Of Assessing Multiple Machine Learning Strategies Utilizing The NSL-KDD Dataset, A Well-
Established Benchmark In Network Security. Making Use Of Support Vector Machine (SVM), Naive Bayes,
Selection Tree, Random Forest, And Logical Analysis Of Data (LAD), Our Have A Look At Highlights LAD's
Effectiveness In Intrusion Detection, With An Accuracy Of 83%. Increasing In This Basis, We Check Out
Ensemble Tactics, Particularly The Voting Classifier That Integrates Random Forest And Adobos, Attaining An
Exceptional Accuracy Of 100%. This Research Affirms The Importance Of Intrusion Detection Structures In
Shielding Networks And Underscores The Potential Of Ensemble Techniques To Enhance Security Measures.
Our Findings Highlight The Essential Characteristic Of Machine Learning In Strengthening Community
Defenses, Imparting A Way For Stepped Forward Cyber Resilience And Proactive Threat Mitigation Techniques
Within Organizations
