view counter

CybersecurityCloud security reaches silicon

By Larry Hardesty

Published 19 January 2016

In the last ten years, computer security researchers have shown that malicious hackers don’t need to see your data in order to steal your data. From the pattern in which your computer accesses its memory banks, adversaries can infer a shocking amount about what’s stored there. The risk of such attacks is particularly acute in the cloud, where you have no control over whose applications are sharing server space with yours. An antagonist could load up multiple cloud servers with small programs that do nothing but spy on other people’s data. System for defending against memory-access attacks is being implemented in chips.

In the last ten years, computer security researchers have shown that malicious hackers don’t need to see your data in order to steal your data. From the pattern in which your computer accesses its memory banks, adversaries can infer a shocking amount about what’s stored there.

The risk of such attacks is particularly acute in the cloud, where you have no control over whose applications are sharing server space with yours. An antagonist could load up multiple cloud servers with small programs that do nothing but spy on other people’s data.

Two years ago, researchers in the group of MIT’s Srini Devadas, the Edwin Sibley Webster Professor in MIT’s Department of Electrical Engineering and Computer Science, proposed a method for thwarting these types of attacks by disguising memory-access patterns. Now, they’ve begun to implement it in hardware.

In March, at the Architectural Support for Programming Languages and Operating Systems conference, they presented the layout of a custom-built chip that would use their scheme, which is now moving into fabrication. And at the IEEE International Symposium on Field-Programmable Custom Computing Machines in May, they will describe some additional improvements to the scheme, which they’ve tested on reconfigurable chips.

The principle behind the scheme is that, whenever a chip needs to fetch data from a particular memory address, it should query a bunch of other addresses, too, so that an adversary can’t determine which one it’s really interested in. Naturally, this requires shipping much more data between the chip and memory than would otherwise be necessary.

To minimize the amount of extra data needed, the researchers store memory addresses in a data structure known as a “tree.” A family tree is a familiar example of a tree, in which each “node” (a person’s name) is attached to only one node above it (the node representing the person’s parents) but may connect to several nodes below it (the person’s children).

Every address is randomly assigned to a path through the tree — a sequence of nodes stretching from the top of the tree to the bottom, with no backtracking. When the chip requires the data stored at a particular address, it also requests data from all the other nodes on the same path.