Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for April 03, 2019
-
PhD Defense - Shahrzad Gholami
Wed, Apr 03, 2019 @ 10:30 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
Ph.D. Defense - Shahrzad Gholami
Wed, April 3, 2019
10:30 AM - 12:00 Noon
Location: EEB 132
Title:
Predicting and Planning against Real-world Adversaries: An End-to-end Pipeline to Combat Illegal Wildlife Poachers on a Global Scale
PhD Candidate: Shahrzad Gholami
Date, Time, and Location: Wednesday, April 3, 2019 at 10:30 am in EEB 132
Committee: Prof. Milind Tambe (chair), Prof. Aram Galstyan, and Prof. Emilio Ferrara, Prof. Richard John, Prof. Sze-Chuan Suen
Abstract:
Security is a global concern and a unifying theme in various security projects is strategic reasoning where the mathematical framework of machine learning and game theory can be integrated and applied. For example, in the environmental sustainability domain, the problem of protecting endangered wildlife from attacks (i.e., poachers' strikes) can be abstracted as a game between defender(s) and attacker(s). Applying previous research on security games to sustainability domains (denoted as Green Security Games) introduce several novel challenges that I address in my thesis to create computationally feasible and accurate algorithms in order to model complex adversarial behavior based on the real-world data and to generate optimal defender strategy. My thesis provides four main contributions to the emerging body of research in using machine learning and game theory framework for the fundamental challenges existing in the environmental sustainability domain, namely (i) novel spatio-temporal and uncertainty-aware machine learning models for complex adversarial behavior based on the imperfect real-world data, (ii) the first large-scale field test evaluation of the machine learning models in the adversarial settings concerning the environmental sustainability, (iii) a novel multi-expert online learning model for constrained patrol planning, and (iv) the first game theoretical model to generate optimal defender strategy against collusive adversaries. In regard to the first contribution, I developed bounded rationality models for adversaries based on the real-world data that account for the naturally occurring uncertainty in past attack evidence collected by defenders. To that end, I proposed two novel predictive behavioral models, which I improved progressively. The second major contribution of my thesis is a large-scale field test evaluation of the proposed adversarial behavior model beyond the laboratory. Particularly, my thesis is motivated by the challenges in wildlife poaching, where I directed the defenders (i.e., rangers) to the hotspots of adversaries that they would have missed. During these experiments across multiple vast national parks, several snares and snared animals were detected, and poachers were arrested, potentially more wildlife saved. The algorithm I proposed, that combines machine learning and game-theoretic patrol planning is planned to be deployed at 600 national parks around the world in the near future to combat poaching. The third contribution in my thesis introduces a novel multi-expert online learning model for constrained and randomized patrol planning, which benefits from several expert planners where insufficient or imperfect historical records of past attacks are available to learn adversarial behavior. The final contribution of my thesis is developing an optimal solution against collusive adversaries in security games assuming both rational and boundedly rational adversaries. I conducted human subject experiments on Amazon Mechanical Turk involving 700 human subjects using a web-based game that simulates collusive security games.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
CS Colloquium: Mukund Raghothaman (University of Pennsylvania) - Precise Program Reasoning using Probabilistic Methods
Wed, Apr 03, 2019 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Mukund Raghothaman, University of Pennsylvania
Talk Title: Precise Program Reasoning using Probabilistic Methods
Series: CS Colloquium
Abstract: The enormous rise in the scale, scope, and complexity of software projects has created a thriving marketplace for program analysis and verification tools. Despite routine adoption by industry, developing such tools remains challenging, and their designers must carefully balance tradeoffs between false alarms, missed bugs, and scalability to large codebases. Furthermore, when tools fail to verify some program property, they only provide coarse estimates of alarm relevance, potential severity, and of the likelihood of being a real bug, thereby limiting their usefulness in software projects with large teams.
I will present a framework that extends contemporary program reasoning systems with rich probabilistic models. These models emerge naturally from the program structure, and probabilistic inference refines the deductive process of the underlying system. In experiments with large programs, such probabilistic graphical representations of program structure enable an order-of-magnitude reduction in false alarm rates and invocations of expensive reasoning engines such as SMT solvers.
To the analysis user, these techniques offer a lens by which to focus their attention on the most important alarms and a uniform method for the tool to interactively generalize from human feedback. To the analysis designer, they offer novel opportunities to leverage data-driven approaches in analysis design. And to researchers, they offer new challenges while performing inference in models of unprecedented size. I will conclude by describing how these ideas promise to underpin the next generation of intelligent programming systems, with applications in diverse areas such as program synthesis, differentiable programming, and fault localization in complex systems.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Mukund Raghothaman is a postdoctoral researcher at the University of Pennsylvania. His research spans the areas of programming languages, software verification, and program synthesis, with the ultimate goal to help programmers create better software with less effort. He previously obtained a Ph.D. in 2017, also from the University of Pennsylvania, where he developed programming abstractions for data stream processing systems.
Host: Jyotirmoy Deshmukh
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
