Nature Versus Hacker: Digital 'Ants' Swarm Malware In Research Project

Scientists have come up with a new way of defending networks from worms and other malware that applies a phenomenon from nature to cyber attacks: the defensive behavior of the tiny ant.

Thousands of different types of "digital" ants were created to move through a computer network and search for evidence of a malicious threat, and like real ants, leaving behind a "scent" or marker to attract other ants to follow it and swarm a potential infection. This so-called "swarm intelligence" approach to finding specific threats is geared at better and quicker detection of threats than current anti-malware software can perform. It's also better able to handle morphed versions of malware, according to the research.

"In nature, we know that ants defend against threats very successfully," says Errin Fulp, a Wake Forest University professor of computer science who specializes in security and networks. "They can ramp up their defense rapidly, and then resume routine behavior quickly after an intruder has been stopped. We were trying to achieve that same framework in a computer system."

Fulp's team at Wake Forest and the Department of Energy's Pacific Northwest National Laboratory in Washington state have worked together on the project. Fulp had previously developed faster malware scanning methods using parallel processing.

In a test of the technology this summer, the digital ants were able to discover a real computer worm planted by Wake Forest on a network of 64 computers in the lab

"Our idea is to deploy 3,000 different types of digital ants, each looking for evidence of a threat," Fulp says. "As they move about the network, they leave digital trails modeled after the scent trails ants in nature use to guide other ants. Each time a digital ant identifies some evidence, it is programmed to leave behind a stronger scent. Stronger scent trails attract more ants, producing the swarm that marks a potential computer infection."

The researchers say the digital ant method works best for big networks with a large number of identical machines. And digital ants can't take over your machine, either: they have to report back to the humans who control their "colony."

Have a comment on this story? Please click "Discuss" below. If you'd like to contact Dark Reading's editors directly, send us a message.