Cybersecurity analytics was the theme of the Fifth Annual Business Analytics Workshop, held in College Park, Md., on Monday, May 18, 2015. Co-sponsored by the University of Maryland’s Robert H. Smith School of Business and IBM, the day-long workshop consisted of topics ranging from calculating cybersecurity investments to applying machine learning to cyber defense. The workshop provided ample time for questions from the audience and speakers delivered real-time solutions to some of the attendees.
This workshop brings together thought leaders from the University of Maryland, IBM and the federal government to provide perspectives and share ideas on how to utilize business analytics techniques to improve cybersecurity. The presentations focused on how analytics methodologies can be employed to that end.
Conference organizer Frank Stein, director of the IBM Analytics Solution Center, welcomed attendees saying,” Cybersecurity is a huge problem to our customers and one of the key solutions approaches is to use Data Analytics. Today you will see a wide variety of analytical approaches -- we hope they will be of value to you.” Stein organizes the conference with Mike Ball, senior associate dean and Dean’s Chair in Management Science.
The morning keynote speaker was Brian Barrios, portfolio director for National Cybersecurity Federally Funded Research and Development Center (FFRDC). The National Cybersecurity FFRDC is operated by MITRE in partnership with the University of Maryland and with support of the National Cybersecurity Center of Excellence (NCCoE), within the National Institute of Standards and Technology (NIST). As part of NIST, an agency within the Department of Commerce, the center is dedicated to increasing the rate of adoption of practical cybersecurity solutions.
Barrios described five consumer-facing challenges: point of sale, data integrity, automated info sharing, external entity access and developer tools. He said that we need to move fast to keep up with the threat and bring together the problem-owners and solution-owners into the same room.
The afternoon keynote speaker was Joseph Kielman, a science adviser in the Science and Technology Directorate (S&T) at the Department of Homeland Security (DHS). Kielman is assigned to the Homeland Security Advanced Research Projects Agency, where he manages research programs in cybersecurity as well as visualization and data analytics.
Kielman discussed how DHS approaches the cybersecurity threat and the resulting challenges, offering these important statistics to kick-off his presentation (available in PDF):
- Annual global IP traffic will surpass the zettabyte threshold (1.3 zettabytes) by the end of 2016. In 2016, global IP traffic will reach 1.3 zettabytes per year or 110.3 exabytes per month.
- Global IP traffic has increased eightfold over the past five years, and will increase threefold over the next five years. Overall, IP traffic will grow at a compound annual growth rate (CAGR) of 29 percent from 2011 to 2016.
- In 2016, the gigabyte equivalent of all movies ever made will cross global IP networks every three minutes. Global IP networks will deliver 12.5 petabytes every five minutes in 2016.
- The number of devices connected to IP networks will be nearly three times as high as the global population in 2016.
Currently DHS has a Homeland Security Data Analysis Network for cybersecurity threat analysis and information sharing in development. He invited attendees to contact him for additional information.
Other speakers include Michel Cukier, director for Advanced Cybersecurity Experience for Students (ACES) and associate director for education for the Maryland Cybersecurity Center (MC2); Lawrence A. Gordon, EY Alumni Professor of Managerial Accounting and Information Assurance at the Smith School and affiliate professor in the University of Maryland Institute for Advanced Computer Studies (UMIACS); and Greg Porpora, chief engineer across IBM Federal Big Data and Analytics.
The workshop ended with a panel discussion on cybersecurity analytics that was moderated by Lawrence Gordon. Panelists included Donna Dodson, NIST; David Maimon, University of Maryland; Anand Ranganathan, IBM.
Maimon, assistant professor in the department of Criminology and Criminal Justice, gave an interesting crime comparison saying that typically for cybersecurity crimes, we look at the gun and try to figure out why it was shot. Instead, we should look at the person and the behavioral motivations in a more holistic approach.
Registration was complimentary through the generous support of IBM. Special thanks to the Maryland Cybersecurity Center for partnering with us on this event.
Please visit the UMD-IBM Business Analytics Workshop website to download presentations.
About Cybersecurity Analytics
Since the early beginnings of the Internet, compromised data security and breaches have been important concerns. In the last decade, these concerns have escalated to unprecedented heights with increased globalization of finance and commerce, heightened competition in intellectual property, and the emergence of the threat of cyber-terrorism and cyber-warfare. In such an environment, a very important skill for government entities and corporations alike is using and processing data intelligently to rapidly identify and thwart attacks and potential breaches, and to fix vulnerabilities in systems and defenses to prevent future threats. Business analytics techniques such as data mining, statistical pattern recognition, network optimization, and big data analysis are becoming vital tools on this front. Related applications span a wide range, including defense, intelligence, homeland security, financial data and intellectual property, security, secure commerce, and infrastructure protection.
- Alissa Arford, Office of Marketing Communications