Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Planning and learning in security games

Planning and learning in security games Planning and Learning in Security Games FRANCESCO M. DELLE FAVE, YUNDI QIAN, ALBERT X. JIANG, MATTHEW BROWN, and MILIND TAMBE University of Southern California We present two new critical domains where security games are applied to generate randomized patrol schedules. For each setting, we present the current research that we have produced. We then propose two new challenges to build accurate schedules that can be deployed effectively in the real world. The first is a planning challenge. Current schedules cannot handle interruptions. Thus, more expressive models, that allow for reasoning over stochastic actions, are needed. The second is a learning challenge. In several security domains, data can be used to extract information about both the environment and the attacker. This information can then be used to improve the defender's strategies. Categories and Subject Descriptors: I.2.8 [Artificial Intelligence]: Problem Solving, Control Methods, and Search General Terms: Algorithms, Experimentation, Security; Theory Additional Key Words and Phrases: Artificial Intelligence, Game Theory 1. INTRODUCTION In recent years, research in security games has produced a number of approaches that led to the deployment of real world applications for protecting critical infrastructure such as ports, airports and trains [Tambe 2011; Conitzer and Sandholm 2006]. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM SIGecom Exchanges Association for Computing Machinery

Loading next page...
 
/lp/association-for-computing-machinery/planning-and-learning-in-security-games-ApDOppOsq0
Publisher
Association for Computing Machinery
Copyright
Copyright © 2013 by ACM Inc.
ISSN
1551-9031
DOI
10.1145/2509013.2509019
Publisher site
See Article on Publisher Site

Abstract

Planning and Learning in Security Games FRANCESCO M. DELLE FAVE, YUNDI QIAN, ALBERT X. JIANG, MATTHEW BROWN, and MILIND TAMBE University of Southern California We present two new critical domains where security games are applied to generate randomized patrol schedules. For each setting, we present the current research that we have produced. We then propose two new challenges to build accurate schedules that can be deployed effectively in the real world. The first is a planning challenge. Current schedules cannot handle interruptions. Thus, more expressive models, that allow for reasoning over stochastic actions, are needed. The second is a learning challenge. In several security domains, data can be used to extract information about both the environment and the attacker. This information can then be used to improve the defender's strategies. Categories and Subject Descriptors: I.2.8 [Artificial Intelligence]: Problem Solving, Control Methods, and Search General Terms: Algorithms, Experimentation, Security; Theory Additional Key Words and Phrases: Artificial Intelligence, Game Theory 1. INTRODUCTION In recent years, research in security games has produced a number of approaches that led to the deployment of real world applications for protecting critical infrastructure such as ports, airports and trains [Tambe 2011; Conitzer and Sandholm 2006].

Journal

ACM SIGecom ExchangesAssociation for Computing Machinery

Published: Jun 1, 2013

There are no references for this article.