Graph Analysis for Predicting and Preventing Logistics Exposure (GRAPPLE)

Physical Sciences Inc (PSI) proposes to develop a data analytics and visualization platform to enable DOD logistics officers to improve Operations Security (OPSEC) by understanding their operational exposure in publically available information (PAI). The proposed Graph Analysis for Predicting and Preventing Logistics Exposure (GRAPPLE) system will ingest, align and analyze multiple diverse streams of PAI to automatically detect anomalies and patterns that are most indicative of military logistics operations.  Graph analytics techniques will enable efficient discovery of relevant patterns from individually benign data sources by building connectivity between related entities and events in different data channels. Further, GRAPPLE will guide logistics officers in applying countermeasures to optimally disguise operations within benign streams of commerce. GRAPPLE will leverage transitioned, operational graph capabilities for entity alignment, anomaly detection, and graph pattern search, developed by PSI under the DARPA SIGMA+ program.  The proposed development will improve OPSEC by providing comprehensive tools to visualize and mitigate the unintentional exposure of DOD operations against intelligent adversaries, proposing countermeasure that will reduce the probability of exposure by at least 30%.