SECURE LINKER: ENSEMBLE-DRIVEN MALICIOUS URL DETECTION FOR SAFER WEB NAVIGATION

Abstract: The rapid expansion of internet usage has led to an increase in cyber threats, especially through malicious URLs that host phishing pages, malware, or exploit kits. Traditional blacklisting methods are often inadequate due to the dynamic nature of these threats. This paper proposes Secure Linker, a system that utilizes ensemble learning techniques to detect malicious URLs with higher accuracy and resilience. The system combines multiple Machine Learning classifiers, leveraging their individual strengths to make more reliable predictions. Experimental results show that ensemble methods outperform individual models in terms of accuracy, precision, recall, and overall robustness.

Keywords: Malicious URL, Machine learning, Phishing, Spamming, Malware, Spoofing.