'Grand Challenge' seeks self-healing software

DARPA has revolutionized driverless cars. Can it do the same for cyber security?
Written by Tyler Falk, Contributor on

In 2005 the United States Department of Defense's research arm, DARPA, presented a $2 million "Grand Challenge" to encourage development of a driverless car that could complete a seven-plus mile course. The top-performing car came from a team from Stanford University whose leader is now head of Google's driverless car program. Now, less than a decade later, the biggest car companies in the world have plans to roll out driverless cars by 2020 and we're already seeing semi-autonomous features in cars.

DARPA is hoping its latest "Grand Challenge" can have a similar impact, this time in the cyber world.

The new $2 million challenge seeks to attract top computer security experts to create automated systems that can identify vulnerabilities, create patches and apply them to computers on a network. If successful, the unmanned, self-patching software could have impressive impacts on computer security.

"Today, our time to patch a newly discovered security flaw is measured in days," said Mike Walker, a DARPA program manager. "Through automatic recognition and remediation of software flaws, the term for a new cyber attack may change from zero-day to zero-second."

Teams with successful automated systems will be invited to participate in a tournament against other teams in 2016 to test how "capably their systems could protect hosts, scan the network for vulnerabilities and maintain the correct function of software."

More here.

Photo: Flickr/IntelFreePress

This post was originally published on Smartplanet.com

Editorial standards