Classification of ransomwaresusing Artificial Neural Networks and Bayesian Networks

Nowadays, ransomware has become the most widespread malware targeting businesses and individuals. It's one of the computer viruses that infiltrate servers, computers, smartphones etc... In this paper and based on the previous work, we will modify and re-classify the ransomware in 9 classes labeled; to make this classification we used artificial neural networks and Bayesian networks. To do this task, we had to rebuild a new learning base that relies on the new files. We used Java programs previously implemented to make a new extraction of strings, which allows us to identify common strings in the system calls of each ransomware file in order to create a learning database and another to do the test. Once these databases are ready, we will start the classification with the Wekatool. The aim of this work is to compare the old classification with the new one using the artificial neural networks and Bayesian networks.