A led by a team with principal investigators from Penn State, George Mason University, Dartmouth College and the University of Michigan, has received a $500,000 grant extension from the Army Research Office to advance the researchers’ work to build solutions that combat cyberattacks.
“The project has generated significant and broad impacts on several fronts, and this add-on grant indicates that the project’s scientific breakthroughs are highly regarded by the Army Research Office and Department of Defense,” said , Raymond G. Tronzo, MD Professor of Cybersecurity in the College of Information Sciences and Technology, who serves as the Penn State principal investigator.
So far in their work, the researchers have developed a new class of technologies called Adaptive Cyber Defense (ACD), which force hackers to continually re-assess, re-engineer and re-launch their attacks through dynamically-changing attack surfaces – which are unprotected hardware and software vulnerabilities – and system configurations.
The team has built on two previously separate research areas: Adaption Techniques (AT), which introduce diversity and uncertainty into networks, applications and hosts; and Adversarial Reasoning (AR), which combines machine learning, behavioral science, operations research, control theory and game theory to learn more about attackers through a methodological approach.
“By integrating game-theoretic and control-theoretic analyses for trade-off analysis, ACD presents adversaries with optimized and dynamically changing attack surfaces and system configurations, thereby significantly increasing the attacker’s workloads and decreasing their probabilities of success,” said Liu.
According to Liu, these results could give the U.S. Department of Defense a significant advantage not only in the growing area of autonomous, adaptive operations in cyberspace, but also in other warfighting domains of air, ground, space and sea. The additional funding will enable his team to immediately leverage past work and accelerate future basic science research relevant to warfighter capabilities.
“The two main goals of this additional effort are to investigate the scientific foundations of autonomous systems which can adapt while operating against adversaries that themselves are adaptive and autonomous; and, understand ways in which human operators can effectively monitor, understand and possibly steer such autonomous systems at high supervisory levels suitable for human-autonomous systems teaming,” said Liu.
The project was initially launched in 2013 with a $6.25 million grant from the Army Research Office.
The is a tri-service Department of Defense program that supports research teams whose research efforts intersect more than one traditional science and engineering discipline.
