Enhancing Cybersecurity: A Comprehensive Analysis of Machine Learning Techniques in Detecting and Preventing Phishing Attacks with a Focus on Xgboost Algorithm

With the exponential rise in internet usage, individuals are progressively sharing their personal information online, resulting in a substantial volume of sensitive data and financial transactions susceptible to cyber threats. Techniques based on artificial intelligence, like machine learning, are powerful tools used to strive against phishing attacks. This research paper presents a comprehensive investigation employing support vector machines and XG-BOOST algorithms on various distinct datasets, such as Phishing Dataset for Machine Learning, Website Phishing Dataset 1, and Website Phishing Dataset 2. The study analyzes and reports the experimental outcomes, utilizing performance metrics such as accuracy, precision-recall, and confusion matrix. The support vector machine achieves accuracy, precision, and recall values of 85, 84, and 86%, respectively, while Xgboost demonstrates values of 90, 88, and 87, respectively. In general, the Xgboost
^a
lgorith
^m
consistently achieves more accuracy equal to 99.17 %, coupled with an impressive computation time of only 0.00894 seconds. Through rigorous experimental analysis, our findings show that Xgboost outperforms the support vector machines algorithm. Subsequently, we implement the xgboost algorithm on large dataset
^s
and introduce a novel concept in this research domain by incorporating an API extension feature in the webpage.