Multi-Tenant Cloud Security- Risk Prediction through Cyber-Value-at-Risk (CVaR)

Cloud computing is a rapidly growing field in information science that has the potential to revolutionize the way we use the Internet. Despite its many benefits, users are often hesitant to store their data in the cloud due to concerns about security, particularly in multi-tenant environments where multiple users share the same resources. To address this challenge, traditional access controls have been implemented in the cloud to ensure the security of the multi-tenant environment. However, these access controls alone are not sufficient to achieve the desired level of security due to the dynamic nature of the cloud environment. The paper discusses about how a weak Authentication, Authorization, and Accounting (AAA) can violate the confidentiality, integrity, and availability (CIA) in cybersecurity. Further, it proposes a risk bases authentication (RBA) approach using supervised learning and calculating risk probability using logistics regression to enable controlled authentication process to secure assets in the multi-tenant cloud environments. The paper explained a method to calculate cyber-value-at-risk (CVaR) using RBA method, access control cost, risk probability, and, asset value. It further utilized financial historic simulation method to elaborate the generation of aggregated CVaR for overall cloud assets in an organizational setting. In summary, cloud computing is a promising technology that can transform the way we use the Internet. However, security concerns remain a major obstacle to its widespread adoption. By integrating AI with RBA, we can enhance the security of multi-tenant cloud environments and protect user data from cyber threats. The proposed CVaR model provides a useful tool for calculating the risk associated with cloud computing and can be used to guide future research in this area.