Adaptive Toolkit for the Discovery of Threats (ATDT)

We propose to design, develop, and deploy an adaptive toolkit for automated threat discovery. The toolkit will provide innovative mechanisms to rapidly discover emerging threat situations. The proposed approach integrates intelligent knowledge discovery techniques with knowledge-based methods to facilitate robust and cost-effective threat detection. The main product of this project will be the Adaptive Toolkit for the Discovery of Threats (ATDT), an agent-based decision support system that facilitates the automated generation of information from distributed, multi-source, multi-discipline data to support early detection of emerging threats. ATDT's intelligent mechanisms include intelligent information retrieval, text and data mining, Bayesian threat modeling, and adaptive learning. Building off the threat assessment capabilities developed in the successful Phase I project, the proposed Phase II effort will (i) refine and enhance the ATDT architecture and tools, (ii) test and validate the ATDT methods and tools on real world Navy threat assessment application scenarios, (iii) demonstrate the ATDT threat assessment capabilities in the Phase II Navy advanced technology demonstration, (iv) transition ATDT to focused Navy applications, and (v) generalize ATDT for large scale commercial use.