IoT-Enhanced Malicious URL Detection Using Machine Learning

The exponential growth of the internet has led to a surge in malicious URLs, posing a significant threat to online security. Traditional methods, like signature-based detection, are increasingly inadequate in identifying these threats. This research introduces an innovative approach using machine learning (ML) algorithms-Random Forest, Light-GBM, and XGBoost-to detect malicious URLs. By training a classifier with a detailed dataset, including attributes such as domain and path length, our method achieves high accuracy, outperforming conventional techniques. We propose integrating IoT technology for real-time data collection and automated response mechanisms. IoT devices can monitor network traffic and URL access patterns, providing a dynamic dataset for the ML model. Upon detecting a malicious URL, these devices can immediately block access or alert users, offering proactive and efficient online protection. We compare our results with VirusTotal to demonstrate the superiority of ML over signature-based methods, highlighting our approach’s effectiveness and adaptability in improving online security.