Revealing Cyber Risks: Malicious URL Detection with Diverse Machine Learning Strategies
P. Naresh, Parasagani Srinath, Koduru Akshit, Gubbala Chanakya, Manubothula Samba Shiva Raju, Pachava Venkata Teja · 2024
The increasing prevalence of cyber threats, particularly those propagated through malicious URLs, underscores the need for robust security measures. This research proposes a machine learning-based approach to effectively identify and neutralize malicious URLs. The proposed system integrates Random Forest and XGBoost algorithms to analyze URL features such as length, special characters, and domain information. These powerful algorithms are capable of handling large datasets and complex feature interactions, enabling accurate classification of URLs as benign or malicious. The system’s performance is evaluated using various metrics, including accuracy, precision, recall, and F1-score. The results demonstrate the effectiveness of the proposed approach in detecting malicious URLs with high accuracy and precision. By integrating this system into cybersecurity infrastructure, organizations can significantly enhance their security posture, protect sensitive data, and mitigate the risks associated with malicious URLs.