Holistic Cyber Threat Hunting Using Network Traffic Intrusion Detection Analysis for Ransomware Attacks

In recent times, cybercriminals have penetrated diverse areas or sectors of the human business enterprise to initiate ransomware attacks against information technology infrastructure. They demand for money called ransom from organizations and individuals to save valuable data. There are varieties of ransomware attacks floating worldwide using intelligent algorithms and with the usage of different setup vulnerabilities. In our research work, we are exploring the latest trends in terms of sector-wise infiltration, captured the most popular among available and also the distribution of the number of attacks using the location information available at the country level. To achieve the correlation between the sectors and locations along with the parametric analysis, we have utilized artificial intelligence techniques. Accuracy of the prediction of attack based on the sector level analysis we have implemented Random Forest and XGBoost algorithm. This research work focuses primarily on two aspects, first is to explore the different aspects of ransomware attacks using intelligent machine learning algorithms. The method used insights to severity of spread of ransomware attacks, second research outcome is to forensically evidence finding of the attack traces using traffic analysis. The challenge is to learn from the previous weaknesses available in the infrastructure and at the same time to prepare the organization and countries' own prevention methods based on the lessons learnt, our exploratory analysis using the latest set of data implementing with AI will give a positive dimension in this area. Also, the proactive approach for managing the data safely is based on the finding of digital forensic analysis of infected ransomware traffic.