Malicious Web Links Detection - A Comparative Analysis of Machine Learning Algorithms

"One of the most challenging categories threats circulating into online world is social engineering, with malicious web links, fake news, clickbait, and other tactics. Malware URLs are extremely dangerous because they represent main propagating vector for malware. Malicious links detection a task mechanism should not influence consumers’ experience. The proposed solutions must be sensitive enough, fast enough to perform before user accesses link downloads its content. Our paper proposes three goals. purpose this refine methodology that may used experiment machine learning algorithms. Moreover, we propose use training comparing several algorithms such as Random Forest, Decision Tree, K-Nearest Neighbor. results compared, justified, placed in literature. In addition, identify relevant features draw some observations about them. 2010 Mathematics Subject Classification. 68T99, 68U99. 1998 CR Categories Descriptors. 68T99 [Artificial Intelligence]: Applications Expert Systems – Experiments Web Links Detection; 68U99 [Management Computing Information Systems]: Security Protection Links. Key words phrases. detection, web-malware, artificial intelligence."