Malweb: An Efficient Malicious Websites Detection System using Machine Learning Algorithms

These days, malware is one of the supreme acknowledged cyber threats. As data volumes increase rapidly, the number of malware threats increases. Malware not only increases in quantities but also becomes smarter and more difficult to detect. Detect malware threats on websites caused by high data traffic, becomes a challenging problem, which must be solved. Moreover, billions of dollars are lost annually due to malicious website scams. Applying analytics to discover new information, predict future malware insights, and make control decisions is a critical process that makes online websites secure. In this research, we propose and analyze a machine learning-based system to detect the behavior of malicious websites based on specific features. With these features, we classify websites as either malicious versus non-malicious. This paper employs a variety of machine learning techniques, including Logistic Regression, Decision Tree, and Naïve Bayes to detect malicious and non-malicious websites, based on various feature selection circumstances to improve results. Applying feature selection with a new way depends on the threshold of categories so Reasonable results are reached with 100% accuracy, recall, and precision when applying Logistic Regression and Decision Tree algorithms while 95% when applying a Naïve Bayes algorithm with an acceptable timing slot.