Optimal Interdiction of Illegal Network Flow
Date of Issue2016
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16)
School of Computer Science and Engineering
Large scale smuggling of illegal goods is a longstanding problem, with $1.4b and thousands of agents assigned to protect the borders from such activity in the US-Mexico border alone. Illegal smuggling activities are usually blocked via inspection stations or ad-hoc checkpoints/roadblocks. Security resources are insufficient to man all stations at all times; furthermore, smugglers regularly conduct surveillance activities. This paper makes several contributions toward the challenging task of optimally interdicting an illegal network flow: i) A new Stackelberg game model for network flow interdiction; ii) A novel Column and Constraint Generation approach for computing the optimal defender strategy; iii) Complexity analysis of the column generation subproblem; iv) Compact convex nonlinear programs for solving the subproblems; v) Novel greedy and heuristic approaches for subproblems with good approximation guarantee. Experimental evaluation shows that our approach can obtain a robust enough solution outperforming the existing methods and heuristic baselines significantly and scale up to realistic-sized problems.
© 2016 International Joint Conferences on Artificial Intelligence. This paper was published in Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16) and is made available as an electronic reprint (preprint) with permission of IJCAI. The published version is available at: [http://www.ijcai.org/Abstract/16/357]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.