In an effort to protect the U.S. from the entry of terrorists and weapons of mass destruction, advanced technical capabilities are needed by the U.S. Customs Service to better target suspicious imports, by the Coast Guard to identify suspect vessels, and by the Immigration and Naturalization Service (INS) to identify potential terrorists. With respect to the entry of weapons of mass destruction into the US, concerns have perhaps been greatest over the 16 million shipping containers that enter every year because before September 11th it was estimated that only 2% of them were opened and physically inspected. In order to meet the new requirement and enhance the performance and reliability of the overall system, Customs has recently embarked on a major modernization initiative of its Information Technology systems. 

Drawing in data from Customs trade systems, targeting inspectors review manifest information as well as strategic and tactical intelligence to determine which shipments and containers may be "high-risk" and which ones are not. Policymakers are convinced that better information sharing and data mining could help prevent future attacks on the country. One of the challenges is to facilitate information sharing in a secure manner. Information sharing remains a major barrier due to the varying levels of data sensitivity, security clearances that carry different semantic meaning at different government agencies, and a wide variety of security policies adopted within these agencies.

The objective of the proposed work is to identify and address, through research and development, some of the challenges encountered in applying information technology to government information services. Specifically, the plan is to address research and development issues related to semantic interoperability, data mining and security and authorization. In addition to the research issues that will be addressed in this proposed work, the development of a proof of concept in the form of a prototype will be undertaken.

The research will focus on issues related to semantic interoperability, security, data mining, policy and political science. Specifically, in the area of semantic interoperability, the team focuses on providing expressive common language among information sources, automatic mapping, and the ability to dynamically adapt to changing environments. Furthermore, automatic text analysis and text mining techniques will be developed to automatically, rather than manually, build the knowledge base. The team addresses some of the challenges encountered when sharing information in a secure manner, including reconciling the heterogeneity among multiple security policies, resolving semantic heterogeneity among security policies, translation of coalition level policies to implementation level and vice versa, and support of delegation in coalition based systems. The research team also will address issues related to data mining to build an alert system. This includes developing classification/segmentation models and merging of different local models to a global model for outlier analysis, real time data mining, and providing iterative and interactive visualization. The multidisciplinary research team, which comes from multi-institutions is augmented by a set of domain experts in several related areas, including homeland security, border control, global logistics, transportation security, foreign terrorist tracking, as well as domestic and multinational investigations. These domain experts provide guidance on the functional requirements of the system and feedback on the prototype system as it progresses through its development.

Broader impact of the proposed project

The impact of this project is in many dimensions - (1) It advances the fundamental research in the areas of semantic interoperability, data mining and security enforcement (2) It devises solutions to accomplish secure interoperation among different government agencies. (3) As a result of the partnership of the research team with industry, SAP, which is the supplier of software to the

Customs Modernization Program and contractor to IBM, the prime contractor for eCustoms Partnership (eCP) that is implementing Customs Modernization, it provides the opportunity to directly influence the practical needs of US Customs. (4) The research and development work that will be undertaken in this project are generalizable and therefore can serve as a reference model to be adopted by related homeland security agencies.