Collaborative Research: Data Science for Cybersecurity

There is a growing shortage of cybersecurity professionals today, with the shortage estimated at 5.5 million in 2023. Cybersecurity professionals require education in data science to be able to properly collect, clean, correlate, store and analyze real system and network data, and make informed cybersecurity decisions. This project develops a large set of hands-on, virtual materials for teaching data science for cybersecurity. These materials will be hosted on the NSF-funded SPHERE research infrastructure and will be publicly and freely available to interested teachers and students. These materials will prepare new generations of cybersecurity professionals to tackle real-world problems collaboratively and at a large scale. This project builds learning materials that will enrich cybersecurity curricula at many schools and colleges, with practical, hands-on exercises that teach data science for cybersecurity. The materials will be useful as either homework assignments or class projects. The materials will include individual and group assignments. Individual materials will provide three difficulty levels - beginner, intermediate and advanced -- and they will support self-learning and self-assessment. Group assignments will engage groups of students on realistic, large scale cybersecurity tasks to promote teamwork, collaboration and communication. The materials will be publicly and freely available to all interested teachers and students, on the NSF-funded SPHERE research infrastructure. Teachers and students will also leverage SPHERE to collect, clean, store, manage and analyze cybersecurity data to gain practical data-science skills. This project is supported by the Data Science Corps program, which supports data science education and training to build a strong national data science infrastructure and workforce. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.