Jason Matheny, director of the Intelligence Advanced Research Projects Activity, has said IARPA is exploring the potential use of machine learning tools and publicly available data to predict cyber attacks before they happen, Federal News Radio reported Tuesday.
Meredith Somers writes Matheny told Federal News Radio that IARPA is reviewing proposed forecasting methods under the agency’s Cyber-attack Automated Unconventional Sensor Environment project.
“CAUSE is another program in which we expect those kinds of breakthroughs to be possible now in a new domain within cyber defense, which… is an area where we need vast improvement,” he added, the station reports.
He believes that using information from social networks, news feeds, streaming videos and online search queries can help organizations prevent attacks on public and private infrastructure assets.
Matheny noted that IARPA will select research teams to receive CAUSE program funds and challenge them to demonstrate security event prediction models through a competition.