Children's Hospital of Philadelphia and University of Pennsylvania received a five-year, $6 million grant to study artificial intelligence systems and how to better protect them from malicious disruptions, according to an Oct. 27 news release.
The researchers will focus on developing new tools and technologies that use insights from human cognitive development to make AI systems better at protecting themselves from threats.
"Robust, concept-learning techniques will assure that trained models operate effectively in the presence of malicious attacks, offering a substantial improvement over the vulnerability of today’s systems that can be easily compromised by even small anomalies," said Insup Lee, project leader and computer and information science professor at University of Pennsylvania.
The grant is part of the U.S. Department of Defense's Multidisciplinary University Research Initiative, which is the department's signature research funding mechanism.