Researchers at IBM Thomas J. Watson Research Center and IBM Research-Zurich have developed a cloud computing security system that makes elements of the cloud act as a kind of virtual bouncer. The new system is based on the theory that as long as the cloud can see a customer's data and leased computational devices, it should check those elements for malicious code. The system enables the cloud to search virtual machines to see what operating systems they are using, whether they are running correctly, and whether they contain malicious code.
The IBM research was one of several papers presented at the recent ACM Cloud Computing Security Workshop, the first event to focus on cloud computing security. "In clouds, the barrier to entry is lower, and the thing customers are most concerned about is their information," says IBM's J.R. Rao. "We want to make sure their information is handled in a manner consistent with their expectation of security and privacy."
Cloud computing could become particularly dangerous if hackers learn how to place malicious virtual machines on the same physical servers as legitimate users. Hackers could theoretically steal data from cache memory on multicore systems within the server. Microsoft has proposed a system that would assign hierarchies within cache memory, which would serve as a partition to protect against this kind of attack.
From Technology Review
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA