Abstract:

With the exponential growth of online services, phishing attacks have become a major threat to cybersecurity, causing financial losses and compromising user privacy. Traditional detection methods, such as blacklists and heuristic rules, often fail to identify new and sophisticated phishing URLs. This paper proposes PhishGuard, a robust malicious URL detection framework using the Random Forest algorithm. By extracting URL-based features such as domain length, presence of special characters, and top-level domain information, the model classifies URLs as legitimate or phishing. Experimental results demonstrate that PhishGuard achieves high accuracy, precision, and recall, outperforming conventional machine learning approaches. The system provides an efficient, scalable solution for proactive phishing detection.

Description:

.