Charles River Analytics has won a follow-on U.S. Air Force contract to identify malware.
The program, known as Semi-Supervised Algorithms against Malware Evolution (SESAME), is a learning-based system that evolves in response to changing threats.
SESAME blends “a rich understanding of malware set” with machine-learning algorithms to learn the essential characteristics of malware, according to a Charles River news release. It will use cloud-based learning technologies for scale.
Charles River is partnering with Arun Lakhotia, a professor at the Center for Advanced Computer Studies at the University of Louisiana at Lafayette, to develop SESAME.
“Human analysts cannot cope with the large volume of malware, and automated methods have difficulty recognizing evolving malware," said Avi Pfeffer, principal scientist at Charles River. "Our goal under the SESAME effort is to develop a robust, scalable system that improves malware detection while countering attempts by attackers to subvert our defenses.”