Automated Phishing Detection Through URL Analysis and Machine Learning

Abstract

Phishing attacks are categorized as one of the greatest threats to cybersecurity. Threat, which is misinformation to make the user provide important and personal information via fake websites or emails. This paper also realizes the notion of a machine phishing detection-based learning tool aimed at classifying URLs they designated as ”phishing”, ”suspicious,” or ”safe.” Utilizing a Random Forest classifier, the system examines URL-based characteristics inclusive of URL. length, special symbols, and the usage of HTTPs to distinguish between real URLs and fake ones (or phishing URLs) with high accuracy. The model was trained and validated on a given dataset of labeled URLs, achieving 95.2% accuracy of classification higher compared to other results. For the sake of usability, the detection tool is implemented as a web application for real-time classification and the results of the classification. user-friendly interface. This is because the performance and metrics such as accuracy and speed depend on them. accuracy by using measures such as precision, recall, and F1-score. effectiveness. This paper will help to improve the level of online security. in an endeavor to provide an automated approach that deprecates dependence on minimizing human judgment and can efficiently detect cases of phishing threats.