Abstract
We describe an innovative application of a novel game-theoretic approach for a national scale secu-rity deployment. Working with the United States Transportation Security Administration (TSA), we have developed a new application called GUARDS to allocate the TSA’s limited resources across hun-dreds of security activities to provide protection at over 400 United States airports. Similar secu-rity applications (e.g., ARMOR and IRIS) have fo-cused on one-off tailored applications and one se-curity activity (e.g. checkpoints) per application,GUARDS on the other hand faces three new key issues: (i) reasoning about hundreds of heteroge-neous security activities; (ii) reasoning over diverse potential threats; (iii) developing a system designed for hundreds of end-users. Since a national deploy-ment precludes tailoring to specific airports, our key ideas are: (i) creating a new game-theoretic framework that allows for heterogeneous defender activities and compact modeling of a large number of threats; (ii) developing an efficient solution tech-nique based on general purpose Stackelberg game solvers; (iii) taking a partially centralized approach for knowledge acquisition. The scheduling assis-tant has been delivered to the TSA and is currently undergoing evaluation for scheduling practices at an undisclosed airport. If successful, the TSA in-tends to incorporate the system into their unpre-dictable scheduling practices nationwide.