Spatio-Temporal Game Theory and Real-Time Machine Learning for Adversarial Groups in the Wild
Abstract
The rise of extremist organizations such as ISIS and Jabhat al-Nusra represents a significant threat in both local and international settings. Threats posed by extremist organizations demand a robust response grounded in a rich qualitative understanding of how such organizations emerge and function as well as a quantitative basis for predicting their behavior. Specifically, our proposed research will attempt to reveal how social, spatial and situational strategic factors underlie the violent action of extremist groups. Ultimately, the models and methods developed will contribute to translating sparse, heterogeneous data into predictions of adversarial behavior and long-term trajectories of adversarial groups.We will collect and analyze a unique multimodal dataset consisting of qualitative ethnographic records, social organization and behavior, experimental field methods in ~wild~ settings and rigorous mathematical and computational methods. Our highly integrated methodological approach includes three principal tasks: (1) ethnographic study of criminal street gangs; (2) experimental testing of gang decision making with mobile game platforms to build game theoretic models of gang decision making; and (3) machine learning for predicting gang behaviors and trajectories, that will also provide a substrate for game theoretic models.1. Gang Ethnography: We will use open-ended and semi-structured interviews to probe issues of within-group trust and its role in autonomy of action, mistrust and antagonistic interactions with rival gangs. These interviews will also probe the quality and quantity of information that gang members have about the actions of their own group and that of rivals, especially police as asymmetrical rivals, and how their willingness to use violence varies with both the surrounding audience and the socio-cultural landscape. Ethnographic data will be incorporated into game theoretic and machine learning models of adversarial action.2. Game Theory in the Wild: We propose to develop formal mathematical and computational methods to analyze the strategic decision-making in adversarial individuals and groups. We will deploy several smartphone-based mobile games to examine how cooperating and noncooperating adversaries act in the face of pervasive imperfect information. Our novel approach incorporates the development and implementation of a smartphone-based mobile platform for game theoretic experimentation in real-world settings to obtain insights into the cognitive and emotional state of gang members. We will experimentally manipulate strategic match-making, the spatial location of game play and the temporal dynamics of game play. Machine learning models built upon the results of this game play will provide a rich substrate on which game theoretic models will be built to describe human player behaviors.3. Machine Learning Adversarial Behavior: We propose to develop novel machine learning methods focused on inferring societal-scale adversarial behavior given sparse, heterogeneous socio-cultural and environmental data. We will develop methods for training deep neural networks to discover, model, and disentangle the components of latent strategy phenotypes. Our machine learning approach will be able to infer contextual states from heterogeneous data, learn adversarial strategies from sequential activity data in games, and transfer adversarial strategies learned from game play to practical scenarios.Our team brings to the project expertise in the ethnographic study of gangs (Jorja Leap, Co-PI), analysis of criminal event patterning and predictive policing (Jeff Brantingham, Co-PI), game theory for security problems (Milind Tambe, PI), and machine learning for latent variable inference and anomaly detection (Yan Liu, Co-PI).
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Mar 03, 2017
- Source ID
- N000141712281
Entities
People
- Milind Tambe
Organizations
- Office of Naval Research
- United States Navy
- University of Southern California