Cyberattacks have moved beyond the simple virus; now they exploit holes in security systems in ways that are nearly impossible to detect with traditional methods.
But the U.S. Department of Defense just awarded the University of Washington $7.5 million to develop a system to spot and repel more advanced attacks.
“Unlike conventional viruses, these threats exploit vulnerabilities and persist over a very long time and they’re very difficult to detect,” said principal investigator Radha Poovendran, chair of the UW Department of Electrical Engineering and director of the Network Security Lab. “Right now, there is no good understanding of the interactions in these complex cyberattacks or how to mitigate them.”
The five year Multidisciplinary University Research Initiative grant, one of 23 such grants announced today, will enable the UW team to accelerate research by enabling interdisciplinary teams to work together on developing solutions.
Researchers are trying to find a scientific framework to understand “advanced persistent threats,” which can exploit vulnerabilities that only the attacker knows about.
By developing a system that uses statistical modeling, adaptive game theory, machine learning, and control and systems theory, the team hopes to detect the stealthy attacks and counteract them with various defense mechanisms.
An important component of the new system will revolve around adapting it as cyberattacks evolve.
“The adversary and the system are always trying to outsmart each other — in this way the interactions are essentially a game played between the system and adversary,” said Poovendran. “But the economic game theory that most modeling methods are grounded in doesn’t work well here. We are trying to develop a novel game theory framework that will significantly improve the results.”
The UW team is working on the project with other Multidisciplinary University Research Initiative grant recipients, including teams from the University of California, Georgia Tech and the University of Illinois.