Pentagon sets cybersecurity sights on social media

The Defense Department is looking for new tools that will better track postings and interactions within social media for a “broad range of tactical as well as strategic military operations,” according to a DOD solicitation.

A notice from the Defense Advanced Research Projects Agency indicates the Pentagon is seeking new software that will automatically sift through social media sites and track how groups interact and evolve, according to a Nextgov report.

According to DARPA, previous efforts to track online activities and related data haven’t been very fruitful, and now the agency wants new, automated tools that use algorithms to help track and distinguish how criminal groups recruit, collaborate, compete and interact through social media.

"Social media have evolved from a platform that provides infrastructure that supports maintaining connections between friends to a platform that supports recruiting, collaborating, organizing and competing for resources… Among these communities and teams are terrorist and other criminal organizations,” the DARPA solicitation noted. “The impact of these teams on the social landscape, their interactions with other teams, the evolution of network state over time, and competition with other teams and communities has not been adequately researched. Due to the overwhelming deluge of data generated by users across social media platforms, this analysis cannot be done manually.”

The hope is that the new tools will better analyze the dynamics of these online communities and predict trends and activities. Ideally, the systems would examine aspects such as the reasons people join a given group; the knowledge, skills and opinions they bring to the community and what effect that has; how knowledge is shared and what impacts that and other factors may have on behavior; and how the dynamics evolve over time.

“While collaborations in social media have been researched extensively, little attention has been paid to how the groups compete with each other for members and influence on opinions of other teams and communities,” DARPA noted. “Understanding what affects such online behavior is needed for trend forecasting.”

One of the biggest challenges will be working through the mass quantities of data; the notice specifies “algorithms must be able to operate on large datasets of millions of nodes, generate robust and reliable group behavior and interaction models, and provide the users with factors and their relative contribution to changes in online behaviors. This technology will be used by analysts in forecasting online behaviors and identifying competition and possible cyber terrorism events.”