"CyberGraph: Mapping Cyber Threats to Prevent the Next Attack"

As cyber intrusions grow more frequent and sophisticated, it is essential to continue the development of tools to help cybersecurity analysts identify and eliminate security threats. Howie Huang, a professor of electrical and computer engineering in the George Washington University School of Engineering and Applied Science, and a team of computer engineering students in his Graph Computer Lab, are developing a novel tool that uses Artificial Intelligence (AI) to assist cybersecurity analysts in strengthening the security of enterprise networks. The AI system is being developed under their startup, called "CyberGraph." The Defense Advanced Research Projects Agency (DARPA) and the National Science Foundation (NSF) awarded the team with grants totaling $2.5 million in support of their CyberGraph research. The lack of cybersecurity professionals, as well as the generation of high volume, low accuracy alerts by current tools, contribute to the ease at which cybersecurity analysts miss critical alerts. CyberGraph's proprietary patent-pending graph technology captures network user behavior, generates high fidelity alerts, and provides contextualized incident stories for cybersecurity analysts through the application of machine learning and graph theory. This article continues to discuss the goals, techniques, and capabilities of CyberGraph's AI tool, along with the support and research behind it.

GW Today reports "CyberGraph: Mapping Cyber Threats to Prevent the Next Attack"