The Intelligence Advanced Research Projects Activity (IARPA) will host a Proposers’ Day conference for the Scientific advances to Continuous Insider Threat Evaluation (SCITE) program on 16 April, 2015 in Washington D.C.
The event is in anticipation of the release of a new solicitation in support of the program. IARPA will be to provide introductory information on SCITE and the research problems that the program aims to address, to respond to questions from potential proposers, and to provide a forum for potential proposers to present their capabilities and identify potential team partners.
Insider threats are individuals with privileged access within an organization who are, or intend to be, engaged in malicious behaviors such as espionage, sabotage or violence. The SCITE program seeks to develop and test methods to detect insider threats, through two separate research tracks.
The first track of research will develop a new class of indicators, called active indicators, and associated automated detection tools. The SCITE program will develop and rigorously test a diverse array of potential active indicators.
The second track of research will develop Inference Enterprise Models (IEM) – models of enterprises organized around detecting insider threats. An IEM forecasts the accuracy of an enterprise in detecting potential threats. SCITE research will develop flexible IEM approaches that can be used to forecast performance of specified subsets of an enterprise (e.g., forecast the impact of adding a new tool to find instances of a specific behavior) or complete enterprise models (e.g., forecast performance of enterprises that employ diverse tools).
The SCITE program expects to draw upon the strengths of academia and industry through collaborative teaming. It is anticipated that teams will be multidisciplinary and might include computer scientists, data scientists, social and behavioral scientists, mathematicians, statisticians, and subject matter experts having applied experience with personnel security and insider threat detection.