Leveraging Artificial Intelligence for Enhancing Real-Time Honeypot Security

This study investigates the integration of machine learning methods to enhance the effectiveness of honeypot systems in detecting cyber threats in real time. Honeypots are security mechanisms designed to lure and monitor unauthorized access attempts, functioning as decoys to understand malicious behavior better. The study applies artificial intelligence to refine these systems by employing five classification algorithms: Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), Naive Bayes (NB), and Support Vector Machine (SVM). Each algorithm was evaluated based on its ability to classify network traffic directed at honeypots. Among them, the Random Forest classifier achieved the most accurate results with a 98% success rate, highlighting the significant promise of AI -driven methods in strengthening honeypot defenses.