DEVELOPMENT OF A MACHINE LEARNING MODEL FOR EARLY DETECTION OF MALICIOUS WEB ATTACKS IN INFORMATION SYSTEMS

Abstract

The rapid growth of web-based information systems has significantly increased cybersecurity risks and the number of malicious web attacks targeting digital infrastructures. Traditional security systems based on static rules and signature analysis are often unable to detect sophisticated and previously unknown cyber threats. This study focuses on the development of a machine learning model for the early detection of malicious web attacks in information systems. The proposed framework applies intelligent data analysis and pattern recognition methods to identify suspicious activities within web traffic and user behavior. Machine learning algorithms such as Decision Trees, Random Forest, and Support Vector Machines are used to classify web activities as normal or malicious. Feature extraction and anomaly detection techniques are integrated into the system to improve detection accuracy and reduce false-positive rates. Experimental analysis demonstrates that machine learning technologies can effectively detect cyber threats at early stages before significant damage occurs. The proposed model provides scalable and adaptive protection mechanisms for modern web environments and contributes to the development of intelligent cybersecurity systems.