Port Resilience Operational / Tactical Enforcement to Combat Terrorism (PROTECT) Model for the United States Coast Guard
(In use by the US Coast Guard since 2011)

People

• Milind Tambe
• Bo An
• Albert Jiang
• Eric Shieh
• Rong Yang
• Andrew Deeds

Motivation

The Coast Guard Atlantic Area’s mission includes maritime security of our coasts, ports, and inland waterways, a mission that faces increased risks given threats such as terrorism and drug trafficking. Atlantic Area performs this mission at the Operational Level of the Coast Guard, looking at mission assessment across five districts encompassing the vast majority of economically significant ports in the United States.

Limited security resources prevent full security coverage at all times, which allows adversaries to observe and exploit patterns in selective patrolling or monitoring, e.g., they can plan actions avoiding existing patrols. Despite extensive outreach and coordination with other federal agencies, along with state, local authorities and industry there is simply not enough assets to maintain a 24/7 presence. This lack of assets extends to all 361 ports in the United States. Randomization of patrols and surveillance can be of help, but randomization must not mean haphazard operations. Randomization must still provide some quality-guaranteed security and very importantly, it must maximize deterrence.

Port Resilience Operational / Tactical Enforcement to Combat Terrorism (PROTECT) Model

The PROTECT model casts the patrolling problem as a Bayesian Stackelberg game. We take a game theoretic approach in evaluating the scenario of adversaries (i.e terrorists) versus the defenders (Coast Guard) to generate weighted randomized patrols for the Coast Guard.

We have successfully demonstrated PROTECT at the Port of Boston and next we plan to apply PROTECT in the
Port of New York.

Abstract from the "PROTECT: A Deployed Game Theoretic System to Protect the Ports of the United States" paper

While three deployed applications of game theory for security have recently been reported at AAMAS, we as a community remain in the early stages of these deployments; there is a continuing need to understand the core principles for innovative security applications of game theory. Towards that end, this paper presents PROTECT, a game-theoretic system deployed by the United States Coast Guard (USCG) in the port of Boston for scheduling their patrols. USCG has termed the deployment of PROTECT in Boston a success, and efforts are underway to test it in the port of New York, with the potential for nationwide deployment.

PROTECT is premised on an attacker-defender Stackelberg game model and offers five key innovations. First, this system is a departure from the assumption of perfect adversary rationality noted in previous work, relying instead on a quantal response (QR) model of the adversary's behavior --- to the best of our knowledge, this is the first real-world deployment of the QR model. Second, to improve PROTECT's efficiency, we generate a compact representation of the defender's strategy space, exploiting equivalence and dominance. Third, we show how to practically model a real maritime patrolling problem as a Stackelberg game. Fourth, our experimental results illustrate that PROTECT's QR model more robustly handles real-world uncertainties than a perfect rationality model. Finally, in evaluating PROTECT, this paper for the first time provides real-world data: (i) comparison of human-generated vs PROTECT security schedules, and (ii) results from an Adversarial Perspective Team's (human mock attackers) analysis.

Publications

Title	Author	Published At	Year	Download
PROTECT: A Deployed Game Theoretic System to Protect the Ports of the United States	Eric Shieh, Bo An, Rong Yang, Milind Tambe, Craig Baldwin, Joseph DiRenzo, Ben Maule, Garrett Meyer	International Conference on Autonomous Agents and Multiagent Systems (to appear)	2012
Computing Optimal Strategy against Quantal Response in Security Games	Rong Yang, Fernando Ordonez, Milind Tambe	International Conference on Autonomous Agents and Multiagent Systems (AAMAS)	2012
An Overview of Recent Application Trends at the AAMAS conference: Security, Sustainability and Safety	Manish Jain, Bo An, Milind Tambe	AI Magazine (to appear)	2012
GUARDS and PROTECT: Next Generation Applications of Security Games	Bo An, James Pita, Eric Shieh, Milind Tambe, Christopher Kiekintveld, Janusz Marecki	ACM SIGecom Exchanges, Vol. 10, No. 1	2011

PROTECT in News

* CREATE News
* Aug 1, 2011

CREATE's ARMOR research team, led by Dr. Milind Tambe, was presented the Commander, First Coast Guard District's Operational Excellence Award for their work on the PROTECT project being carried out at Boston Harbor.

Rear Admiral Daniel Neptun presented the award to Drs. Milind Tambe and Isaac Maya, along with commendations to United States Coast Guard (USCG) personnel, for the scheduling software developed to intelligently randomize boat patrols of critical infrastructure around Boston Harbor.
To continue reading the full article, please click here.



Port of Boston Not Playing Games with Its Security

* By Laura Williams
* Apr 25, 2011

Studying robot interactions is not typically a career path that leads to a central role in infrastructure security – after all, the Department of Homeland Security doesn’t trust just anyone with vital information about the nation’s critical structures.

Unlikely though it was, it was exactly that research interest that led Milind Tambe, a computer science professor at the University of Southern California, to a project helping the U.S. Coast Guard create a complex patrol schedule that the Port of Boston has been piloting for the past month.

In 2002, Tambe and a student began working on a game-theory algorithm to optimize interactions between robots, and their result turned out to be that randomized interactions worked most effectively. At a 2004 conference, though, this finding received a chilly reception.

“We were so fascinated by the randomization process itself that we didn’t want to give it up,” Tambe said, and so they continued their exploration.
To continue reading the full article, please click here.



USC Engineering Anti-Terrorism System Begins Tests in Boston Harbor

Coast Guard testing a computer application designed for airports that makes security activity impossible for observers to predict

April 12, 2011 —

It began with Viterbi School work on randomizing airport security police patrol routines at Los Angeles International Airport while still maintaining the same level of protection. The example spread across the nation, and is now methodically and unpredictably at work in the waters off Massachusetts.

The new PROTECT system schedules the operations of Coast Guard response vessels in a way that make it impossible for observers to predict their activities, while still maintaining the same degree of surveillance.

After months of study, PROTECT (Port Resilience Operational / Tactical Enforcement to Combat Terrorism) began a two-month trial around Boston Harbor April 4, 2011.
To continue reading the full article, please click here.

Funded by:
USC CREATE

If you have any questions about the contents of this page please contact Eric Shieh  eshieh [at] usc [dot] edu