Detecting Ransomware Automated Based on Network Behavior by Using Machine Learning

Ransomware has been a detrimental form of malware, in which many companies have become victims of these attacks and are required to release specific amounts of money to attackers without knowing if they will ever relieve their data. There has been a dramatic growth in ransomware attacks in recent years. This research will provide effective methods for preventing these attacks and limiting the effects of the attack if they ever occur. Our technique is based on using an ensemble machine learning classification algorithm in a random forest and boosting algorithm to evaluate network behavior. We used the Adaboost algorithm to create a sequence model to predict accurate results in an automated effective, and efficient method that detected ransomware.