PROJECT TITLE :

Big Data Based Security Analytics for Protecting Virtualized Infrastructures in Cloud Computing - 2017

ABSTRACT:

Virtualized infrastructure in cloud computing has become an enticing target for cyberattackers to launch advanced attacks. This paper proposes a unique massive information based mostly security analytics approach to detecting advanced attacks in virtualized infrastructures. Network logs plus user application logs collected periodically from the guest virtual machines (VMs) are stored within the Hadoop Distributed File System (HDFS). Then, extraction of attack options is performed through graph-based event correlation and MapReduce parser primarily based identification of potential attack ways. Next, determination of attack presence is performed through 2-step machine learning, namley logistic regression is applied to calculate attack's conditional probabilities with respect to the attributes, and belief propagation is applied to calculate the assumption alive of an attack based mostly on them. Experiments are conducted to evaluate the proposed approach using well-known malware along with in comparison with existing security techniques for virtualized infrastructure. The results show that our proposed approach is effective in detecting attacks with minimal performance overhead.