Developing and Evaluating an Artificial Intelligence Model for Malicious URL Detection

Today, the increased use of internet has become important in our lives and new communication technologies, social networks, e-commerce, online banking, among other applications have a significant impact on promotion growth business. In study, we aimed to work with large dataset achieve best results detecting malicious URL addresses using an artificial intelligence model. A 7-layer RNN model was used two similar national international datasets were combined merged create big consisting 579,112 addresses. Then, this data set is divided into training test sets. first trained at then second processed test. When model, achieved success rate over 91%. This very good result url Your contribution developing more effective methods for harmful sites as usage increases, parallel models makes detection such potentially assist users protecting from various types cyber-attacks targeted.