AI-Enabled Threat Detection in Network Security
TL;DR
An AI-based threat detection framework that integrates network traffic analysis, preprocessing, feature engineering, threat classification, and automated response is proposed that outperforms conventional methods by providing higher detection accuracy, lower false alarms, and faster response.
Abstract
Modern networks face increasing cyber threats such as malware, ransomware, phishing, DDoS, insider attacks, and advanced persistent threats, making traditional signature-based security systems less effective. Artificial Intelligence (AI), through machine learning and deep learning, enables intelligent threat detection by identifying known and unknown attacks in real time. This study proposes an AI-based threat detection framework that integrates network traffic analysis, preprocessing, feature engineering, threat classification, and automated response. Experimental evaluation using metrics such as accuracy, precision, recall, F1-score, false positive rate, and detection latency demonstrates that the proposed framework outperforms conventional methods by providing higher detection accuracy, lower false alarms, and faster response. Despite challenges related to data quality, model interpretability, and computational cost, AI-driven cybersecurity offers a scalable and effective solution for modern network security.