Directorate for Computer and Information Science and Engineering (CISE)
The lack of real-world data has hampered many cybersecurity researchers, making it difficult to tune algorithms and validate results. This letter is to let you know that new data resources are becoming available and to encourage you to take advantage of them in your research.
NSF's Trustworthy Computing program recently convened an invitational workshop on Cyber Security Data for Experimentation with the collaboration of the Department of Homeland Security (DHS), the Office of Naval Research, the Treasury Department, as well as other agencies. The workshop goal was to find new ways for industrial partners to exchange data with academic researchers. Access to data in DHS's PREDICT repository was also discussed. Academic, industry, and government participants engaged in spirited discussion and developed a deeper understanding of the issues involved in gaining access to industrial data sources and sharing research results based on those data.
Slides, videos of talks, and notes from the workshop can be found at the workshop website http://www.gtisc.gatech.edu/nsf_workshop10. One positive outcome of the workshop was the offer from some companies to work with researchers to provide access to their data. The workshop website has links to brief descriptions of what each company is willing to consider and how to contact someone for details.
I invite you to make use of these resources. If you could make use of such data for a currently-funded NSF grant, then I encourage you to apply for a supplement under normal NSF procedures to support your use of these resources.
Many thanks to Professor Nick Feamster of Georgia Tech for his role in organizing the workshop and the website.
Keith A. Marzullo
Division Director, CISE/CNS
PROGRAM OFFICER CONTACT INFORMATION
Trustworthy Computing Contact: Carl Landwehr (firstname.lastname@example.org)