Events Calendar

CS Student Colloquium: Benjamin Ford (USC) - Beware the Soothsayer: From Attack Prediction Accuracy to Predictive Reliability in Security Games

Speaker: Benjamin Ford , USC

Talk Title: Beware the Soothsayer: From Attack Prediction Accuracy to Predictive Reliability in Security Games

Series: CS Colloquium

Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium

Interdicting the flow of illegal goods (such as drugs and ivory) is a major security concern for many countries. The massive scale of these networks, however, forces defenders to make judicious use of their limited resources. While existing solutions model this problem as a Network Security Game (NSG), they do not consider humans' bounded rationality. Previous human behavior modeling works in Security Games, however, make use of large training datasets that are unrealistic in real-world situations; the ability to effectively test many models is constrained by the time-consuming and complex nature of field deployments. In addition, there is an implicit assumption in these works that a model's prediction accuracy strongly correlates with the performance of its corresponding defender strategy (referred to as predictive reliability). If the assumption of predictive reliability does not hold, then this could lead to substantial losses for the defender. In the following paper, we (1) first demonstrate that predictive reliability is indeed strong for previous Stackelberg Security Game experiments. We also run our own set of human subject experiments in such a way that models are restricted to learning on dataset sizes representative of real world constraints. In the analysis on that data, we demonstrate that (2) predictive reliability is extremely weak for NSGs. Following that discovery, however, we identify (3) key factors that influence predictive reliability results: the training set's exposed attack surface and graph structure.

This lecture will be available to stream HERE.

Biography: Ben is a third year PhD student of Computer Science at the University of Southern California's Viterbi School of Engineering. He joined Teamcore in August 2013 and is advised by Professor Milind Tambe. Previously, he completed his B.S. and M.S. in Computer Science at the University of Massachusetts Dartmouth in 2008 and 2010, respectively. After graduation and prior to joining Teamcore, he worked at the Naval Undersea Warfare Center in Newport, RI as a Software Engineer. His primary research interests are in the application of concepts from the social sciences of Psychology, Criminology, Sociology, and Anthropology to improve the algorithms and solutions of Computer Science. Specifically, he is interested in applying human behavioral models to multi-agent systems with a large focus on human decision making. Since joining Teamcore, he has developed an interest in applying Behavioral Game Theory to the Wildlife Conservation domain to prevent wildlife poaching and smuggling.

Host: Computer Science Department

Webcast: https://bluejeans.com/846279055

Location: Henry Salvatori Computer Science Center (SAL) - 101

WebCast Link: https://bluejeans.com/846279055

Audiences: Everyone Is Invited

Contact: Assistant to CS chair