Anomaly Detection based on NSL-KDD using XGBoost with Optuna Tuning

Keyphrases

• Anomaly Detection 100%
• Best Parameters 33%
• Classifier Model 33%
• Cyber-attacks 16%
• Detection Accuracy 16%
• Dynamic Pattern 16%
• Feature Selection 16%
• Financial Loss 16%
• Hidden Danger 16%
• Human Life 16%
• Hypertuning 33%
• Internet Development 16%
• Intrusion Behavior 16%
• Intrusion Detection System 16%
• Low Efficiency 16%
• Machine Learning Models 16%
• Malicious Attacks 33%
• Network Security 16%
• NSL-KDD 100%
• Optuna 100%
• Training Model 16%
• User Account 16%
• XGBoost 100%
• XGBoost Classifier 50%

INIS

• accuracy 33%
• cyber attacks 33%
• data 33%
• detection 100%
• dynamics 33%
• efficiency 33%
• humans 33%
• internet 33%
• intrusion 100%
• intrusion detection systems 33%
• learning 33%
• losses 66%
• machine learning 33%
• risks 33%
• security 33%
• tuning 100%

Computer Science

• Anomaly-Based Detection 100%
• Classifier Model 50%
• Cyber Attack 25%
• Extreme Gradient Boosting 100%
• Feature Extraction 25%
• Feature Selection 25%
• Intrusion Detection 25%
• Intrusion Detection System 25%
• Learning System 25%
• Machine Learning 25%
• Malicious Attack 50%
• Network Security 25%
• Training Model 25%