AN ARTIFICIAL INTELLIGENCE–BASED FRAMEWORK FOR IDENTIFYING CYBER THREATS IN WEB APPLICATIONS

Abstract

The development of web technologies and online communication platforms has created new cybersecurity challenges related to the increasing number of cyber threats targeting web applications. Traditional intrusion detection systems often fail to identify advanced attacks because they rely on static rules and predefined signatures. This study presents an artificial intelligence–based framework for identifying cyber threats in web applications using machine learning and pattern recognition technologies. The proposed system analyzes network traffic behavior, user activities, and web request anomalies to detect malicious actions in real time. Artificial intelligence algorithms such as Neural Networks, Random Forest, and Support Vector Machines are integrated into the framework to improve threat classification performance. Experimental results demonstrate that AI-driven security systems achieve higher detection accuracy and better adaptability compared to conventional cybersecurity methods. The study confirms the effectiveness of artificial intelligence technologies for strengthening web application security and preventing modern cyberattacks