A System for Detecting Malicious Insider Data Theft in IaaS Cloud Environments

摘要

The Cloud Security Alliance lists data theft and insider attacks as critical threats to cloud security. Our work puts forth an approach using a train, monitor, detect pattern which leverages a stateful rule based k-nearest neighbors anomaly detection technique and system state data to detect inside attacker data theft on Infrastructure as a Service (IaaS) nodes. We posit, instantiate, and demonstrate our approach using the Eucalyptus cloud computing infrastructure where we observe a 100 percent detection rate for abnormal login events and data copies to outside systems.