Innovative Approaches to Behavioral Modeling, Threat Modeling and Threat Prediction

While great progress has been made in the lowest levels of data fusion, practical advances in behavior modeling and prediction remain elusive. While certainly there remains much room to improve data fusion algorithms, the most critical failing of existing approaches is their inability to support the required knowledge modeling and continuing refinement under realistic constraints (e.g., few historic exemplars, lack of knowledge engineering support, and the need for rapid system deployment). The proposed Propheteer systems will directly address this issue through a self-facilitating knowledge modeling approach that can flexibly exploit a range of knowledge contributions made by individual SME's including historic exemplars, hypothetical scenarios, existing probabilistic models and model fragments, key constraints, etc. Propheteer will support the integration of these different perspectives into a uniform model that will be employed to intelligently appraise and fuse available evidence and reason about multiple situation interpretations. Finally, Propheteer will provide analysts with the insight required to recognize model shortcomings, and will exploit its ability to compose models from fragmentary knowledge to streamline ongoing model refinement. Our prior experience and existing software components will allow for rapid progress in Phase I prototyping and provide a solid foundation for a complete implementation in Phase II.