作者: Frank Doelitzscher , Martin Knahl , Christoph Reich , Nathan Clarke
关键词:
摘要: Security is still a major concern in Cloud computing, especially the detection of nefarious use or abuse cloud instances. One reason for this, ever-growing complexity and dynamic underlying system design architecture. To be able to detect misuse instances, this work presents an anomaly Infrastructure as Service Clouds. It based on customers' usage behaviour analysis. Neural networks are used analyse learn normal customers, then anomalies which could originate from security incident caused by overtaken virtual machine. increases transparency customers about their instances supports provider infrastructure. A simulation environment prototype get presented. Experiments validate effectiveness proposed system.