Speaker: Smitha Sundareswaran 

Title: Detecting Malicious co-resident VMs indulging in cache-channel based covert attacks

Abstract:

Cloud computing services extend the usability of physical computing
infrastructure by multiplexing the infrastructure for different
customers on a single physical machine. This multiplexing is achieved
through the use of Virtual Machines (VMs) that users can instantiate
on demand, thus utilizing the precise amount of computing power needed
by them at that moment. While virtualization provides many benefits,
it introduces new vulnerabilities to the Cloud such as making it
possible to map the internal Cloud infrastructure, and to identify
where a particular target VM is likely to reside. Further, it allows
malicious VMs to mount cross-VM attacks through cache based side
channels.

In this project, we investigate covert side-channel attacks born
specifically as a result of the virtualization in Cloud systems. We
develop a framework to identify these attacks based on the observation
that the events taking place during the attacks lead to an
identifiable sequence of exceptions. We test the accuracy of our
framework on a simulated Cloud on a local machine, and on a real world
Cloud using the Amazon's EC2 infrastructure.