Overview / Usage

In this project, my group in the University of Hawaii at Manoa is collaborating with a group at the University of Maryland to instantiate a proactive approach to cyber security. Specifically, we are analyzing through social network and topic modeling the cybersecurity discourse on the web to identify the formation of emerging concepts in vulnerabilities, attacks, and weakness in software.

Existing approaches to providing awareness and maintaining knowledge of attacks are starting and predicted to fall behind (e.g. see http://www.csoonline.com/article/3204568/application-security/closing-the-cve-gap-is-mitre-up-to-it.html). Moreover, current automated approaches focus mostly on entity recognition or a set of specific terms to bootstrap context. One major limitation of this approach is in identifying emerging vulnerabilities at a conceptual level, which our group seeks to address.

My role in the group consists of overseeing master students work, and investigate text mining algorithms that realize the project vision. More details will be provided on later stages of the project.

Please see more about my lab work at https://sailuh.github.io/perceive/