In recent years, AI-based applications have increasingly been used in real-world domains. For example, game theorybased decision aids have been successfully deployed in various security settings to protect ports, airports, and wildlife. This paper describes our unique problem-to-project educational approach that used games rooted in real-world issues to teach AI concepts to diverse audiences. Specifically, our educational program began by presenting real-world security issues, and progressively introduced complex AI concepts using lectures, interactive exercises, and ultimately hands-on games to promote learning. We describe our experience in applying this approach to several audiences, including students of an urban public high school, university undergraduates, and security domain experts who protect wildlife. We evaluated our approach based on results from the games and participant surveys.

Motivated by the problem of protecting endangered animals, there has been a surge of interests in optimizing patrol planning for conservation area protection. Previous efforts in these domains have mostly focused on optimizing patrol routes against a specific boundedly rational poacher behavior model that describes poachers’ choices of areas to attack. However, these planning algorithms do not apply to other poaching prediction models, particularly, those complex machine learning models which are recently shown to provide better prediction than traditional bounded-rationality-based models. Moreover, previous patrol planning algorithms do not handle the important concern whereby poachers infer the patrol routes by partially monitoring the rangers’ movements. In this paper, we propose OPERA, a general patrol planning framework that: (1) generates optimal implementable patrolling routes against a black-box attacker which can represent a wide range of poaching prediction models; (2) incorporates entropy maximization to ensure that the generated routes are more unpredictable and robust to poachers’ partial monitoring. Our experiments on a real-world dataset from Uganda’s Queen Elizabeth Protected Area (QEPA) show that OPERA results in better defender utility, more efficient coverage of the area and more unpredictability than benchmark algorithms and the past routes used by rangers at QEPA.

Wildlife species such as tigers and elephants are under the threat of poaching. To combat poaching, conservation agencies (“defenders”) need to (1) anticipate where the poachers are likely to poach and (2) plan effective patrols. We propose an anti-poaching tool CAPTURE (Comprehensive Anti-Poaching tool with Temporal and observation Uncertainty REasoning), which helps the defenders achieve both goals. CAPTURE builds a novel hierarchical model for poacher-patroller interaction. It considers the patroller’s imperfect detection of signs of poaching, the complex temporal dependencies in the poacher's behaviors and the defender’s lack of knowledge of the number of poachers. Further, CAPTURE uses a new game-theoretic algorithm to compute the optimal patrolling strategies and plan effective patrols. This paper investigates the computational challenges that CAPTURE faces. First, we present a detailed analysis of parameter separation and target abstraction, two novel approaches used by CAPTURE to efficiently learn the parameters in the hierarchical model. Second, we propose two heuristics – piece-wise linear approximation and greedy planning – to speed up the computation of the optimal patrolling strategies. We discuss in this paper the lessons learned from using CAPTURE to analyze real-world poaching data collected over 12 years in Queen Elizabeth National Park in Uganda.

This paper focuses on new challenges in influence maximization inspired by non-profits’ use of social networks to effect behavioral change in their target populations. Influence maximization is a multiagent problem where the challenge is to select the most influential agents from a population connected by a social network. Specifically, our work is motivated by the problem of spreading messages about HIV prevention among homeless youth using their social network. We show how to compute solutions which are provably close to optimal when the parameters of the influence process are unknown. We then extend our algorithm to a dynamic setting where information about the network is revealed at each stage. Simulation experiments using real world networks collected by the homeless shelter show the advantages of our approach.

We consider the problem of dynamically allocating screening resources of different efficacies (e.g., magnetic or X-ray imaging) at checkpoints (e.g., at airports or ports) to successfully avert an attack by one of the screenees. Previously, the Threat Screening Game model was introduced to address this problem under the assumption that screenee arrival times are perfectly known. In reality, arrival times are uncertain, which severely impedes the implementability and performance of this approach. We thus propose a novel framework for dynamic allocation of threat screening resources that explicitly accounts for uncertainty in the screenee arrival times. We model the problem as a multistage robust optimization problem and propose a tractable solution approach using compact linear decision rules combined with robust reformulation and constraint randomization. We perform extensive numerical experiments which showcase that our approach outperforms (a) exact solution methods in terms of tractability, while incurring only a very minor loss in optimality, and (b) methods that ignore uncertainty in terms of both feasibility and optimality.

In recent years, there have been a number of successful cyber attacks on enterprise networks by malicious actors. These attacks generate alerts which must be investigated by cyber analysts to determine if they are an attack. Unfortunately, there are magnitude more alerts than cyber analysts - a trend expected to continue into the future creating a need to find optimal assignments of the incoming alerts to analysts in the presence of a strategic adversary. We address this challenge with the four following contributions: (1) a cyber allocation game (CAG) model for the cyber network protection domain, (2) an NP-hardness proof for computing the optimal strategy for the defender, (3) techniques to find the optimal allocation of experts to alerts in CAG in the general case and key special cases, and (4) heuristics to achieve significant scale-up in CAGs with minimal loss in solution quality.

Many homeless shelters conduct interventions to raise awareness about HIV (human immunodeficiency virus) among homeless youth. Due to human and financial resource shortages, these shelters need to choose intervention attendees strategically, in order to maximize awareness through the homeless youth social network. In this work, we propose HEALER (hierarchical ensembling based agent which plans for effective reduction in HIV spread), an agent that recommends sequential intervention plans for use by homeless shelters. HEALER's sequential plans (built using knowledge of homeless youth social networks) select intervention participants strategically to maximize influence spread, by solving POMDPs (partially observable Markov decision process) on social networks using heuristic ensemble methods. This paper explores the motivations behind HEALER’s design, and analyzes HEALER’s performance in simulations on real-world networks. First, we provide a theoretical analysis of the DIME (dynamic influence maximization under uncertainty) problem, the main computational problem that HEALER solves. HEALER relies on heuristic methods for solving the DIME problem due to its computational hardness. Second, we explain why heuristics used inside HEALER work well on real-world networks. Third, we present results comparing HEALER to baseline algorithms augmented by HEALER’s heuristics. HEALER is currently being tested in real-world pilot studies with homeless youth in Los Angeles.

Wildlife conservation organizations task rangers to deter and capture wildlife poachers. Since rangers are responsible for patrolling vast areas, adversary behavior modeling can help more effectively direct future patrols. In this innovative application track paper, we present an adversary behavior modeling system, INTERCEPT (INTERpretable Classification Ensemble to Protect Threatened species), and provide the most extensive evaluation in the AI literature of one of the largest poaching datasets from Queen Elizabeth National Park (QENP) in Uganda, comparing INTERCEPT with its competitors; we also present results from a month-long test of INTERCEPT in the field. We present three major contributions. First, we present a paradigm shift in modeling and forecasting wildlife poacher behavior. Some of the latest work in the AI literature (and in Conservation) has relied on models similar to the Quantal Response model from Behavioral Game Theory for poacher behavior prediction. In contrast, INTERCEPT presents a behavior model based on an ensemble of decision trees (i) that more effectively predicts poacher attacks and (ii) that is more effectively interpretable and verifiable. We augment this model to account for spatial correlations and construct an ensemble of the best models, significantly improving performance. Second, we conduct an extensive evaluation on the QENP dataset, comparing 41 models in prediction performance over two years. Third, we present the results of deploying INTERCEPT for a one-month field test in QENP - a first for adversary behavior modeling applications in this domain. This field test has led to finding a poached elephant and more than a dozen snares (including a roll of elephant snares) before they were deployed, potentially saving the lives of multiple animals - including endangered elephants.

The field of influence maximization (IM) has made rapid advances, resulting in many sophisticated algorithms for identifying “influential” members in social networks. However, in order to engender trust in IM algorithms, the rationale behind their choice of “influential” nodes needs to be explained to its users. This is a challenging open problem that needs to be solved before these algorithms can be deployed on a large scale. This paper attempts to tackle this open problem via four major contributions: (i) we propose a general paradigm for designing explanation systems for IM algorithms by exploiting the tradeoff between explanation accuracy and interpretability; our paradigm treats IM algorithms as black boxes, and is flexible enough to be used with any algorithm; (ii) we utilize this paradigm to build XplainIM, a suite of explanation systems; (iii) we illustrate the usability of XplainIM by explaining solutions of HEALER (a recent IM algorithm) among ∼200 human subjects on Amazon Mechanical Turk (AMT); and (iv) we provide extensive evaluation of our AMT results, which shows the effectiveness of XplainIM.

Despite significant research in Security Games, limited efforts have been made to handle game domains with continuous space. Addressing such limitations, in this paper we propose: (i) a continuous space security game model that considers infinitesize action spaces for players; (ii) OptGradFP, a novel and general algorithm that searches for the optimal defender strategy in a parametrized search space; (iii) OptGradFP-NN, a convolutional neural network based implementation of OptGradFP for continuous space security games; (iv) experiments and analysis with OptGradFP-NN. This is the first time that neural networks have been used for security games, and it shows the promise of applying deep learning to complex security games which previous approaches fail to handle.

This paper focuses on a topic that is insufficiently addressed in the literature, i.e., challenges faced in transitioning agents from an emerging phase in the lab, to a deployed application in the field. Specifically, we focus on challenges faced in transitioning HEALER and DOSIM, two agents for social influence maximization, which assist service providers in maximizing HIV awareness in real-world homeless-youth social networks. These agents recommend key "seed" nodes in social networks, i.e., homeless youth who would maximize HIV awareness in their real-world social network. While prior research on these agents published promising simulation results from the lab, this paper illustrates that transitioning these agents from the lab into the real-world is not straightforward, and outlines three major lessons. First, it is important to conduct real-world pilot tests; indeed, due to the health-critical nature of the domain and complex influence spread models used by these agents, it is important to conduct field tests to ensure the real-world usability and effectiveness of these agents. We present results from three real-world pilot studies, involving 173 homeless youth in an American city. These are the first such pilot studies which provide headto-head comparison of different agents for social influence maximization, including a comparison with a baseline approach. Second, we present analyses of these real-world results, illustrating the strengths and weaknesses of different influence maximization approaches we compare. Third, we present research and deployment challenges revealed in conducting these pilot tests, and propose solutions to address them. These challenges and proposed solutions are instructive in assisting the transition of agents focused on social influence maximization from the emerging to the deployed application phase.

This paper presents HEALER, a software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth. HEALER’s sequential plans (built using knowledge of social networks of homeless youth) choose intervention participants strategically to maximize influence spread, while reasoning about uncertainties in the network. While previous work presents influence maximizing techniques to choose intervention participants, they do not address two real-world issues: (i) they completely fail to scale up to real-world sizes; and (ii) they do not handle deviations in execution of intervention plans. HEALER handles these issues via two major contributions: (i) HEALER casts this influence maximization problem as a POMDP and solves it using a novel planner which scales up to previously unsolvable real-world sizes; and (ii) HEALER allows shelter officials to modify its recommendations, and updates its future plans in a deviationtolerant manner. HEALER was deployed in the real world in Spring 2016 with considerable success.

Poaching is considered a major driver for the population drop of key species such as tigers, elephants, and rhinos, which can be detrimental to whole ecosystems. While conducting foot patrols is the most commonly used approach in many countries to prevent poaching, such patrols often do not make the best use of the limited patrolling resources. This paper presents PAWS, a game-theoretic application deployed in Southeast Asia for optimizing foot patrols to combat poaching. In this paper, we report on the significant evolution of PAWS from a proposed decision aid introduced in 2014 to a regularly deployed application. We outline key technical advances that lead to PAWS’s regular deployment: (i) incorporating complex topographic features, e.g., ridgelines, in generating patrol routes; (ii) handling uncertainties in species distribution (game theoretic payoffs); (iii) ensuring scalability for patrolling large-scale conservation areas with fine-grained guidance; and (iv) handling complex patrol scheduling constraints.

Conservation agencies worldwide must make the most efficient use of their limited resources to protect natural resources from over-harvesting and animals from poaching. Predictive modeling, a tool to increase efficiency, is seeing increased usage in conservation domains such as to protect wildlife from poaching. Many works in this wildlife protection domain, however, fail to train their models on real-world data or test their models in the real world. My thesis proposes novel poacher behavior models that are trained on real-world data and are tested via first-of-their-kind tests in the real world. First, I proposed a paradigm shift in traditional adversary behavior modeling techniques from Quantal Response-based models to decision tree-based models. Based on this shift, I proposed an ensemble of spatially-aware decision trees, INTERCEPT, that outperformed the prior stateof-the-art and then also presented results from a one-month pilot field test of the ensemble’s predictions in Uganda’s Queen Elizabeth Protected Area (QEPA). This field test represented the first time that a machine learning-based poacher behavior modeling application was tested in the field. Second, I proposed a hybrid spatio-temporal model that led to further performance improvements. To validate this model, I designed and conducted a large-scale, eight-month field test of this model’s predictions in QEPA. This field test, where rangers patrolled over 450 km in the largest and longest field test of a machine learning-based poacher behavior model to date in this domain, successfully demonstrated the selectiveness of the model’s predictions; the model successfully predicted, with statistical significance, where rangers would find more snaring activity and also where rangers would not find as much snaring activity. I also conducted detailed analysis of the behavior of my predictive model. Third, beyond wildlife poaching, I also provided novel graph-aware models for modeling human adversary behavior in wildlife or other contraband smuggling networks and tested them against human subjects. Lastly, I examined human considerations of deployment in new domains and the importance of easily-interpretable models and results. While such interpretability has been a recurring theme in all my thesis work, I also created a game-theoretic inspection strategy application that generated randomized factory inspection schedules and also contained visualization and explanation components for users.

Worldwide, conservation agencies employ rangers to protect conservation areas from poachers. However, agencies lack the manpower to have rangers effectively patrol these vast areas frequently. While past work has modeled poachers’ behavior so as to aid rangers in planning future patrols, those models’ predictions were not validated by extensive field tests. In this paper, we present a hybrid spatio-temporal model that predicts poaching threat levels and results from a five-month field test of our model in Uganda’s Queen Elizabeth Protected Area (QEPA). To our knowledge, this is the first time that a predictive model has been evaluated through such an extensive field test in this domain. We present two major contributions. First, our hybrid model consists of two components: (i) an ensemble model which can work with the limited data common to this domain and (ii) a spatio-temporal model to boost the ensemble’s predictions when sufficient data are available. When evaluated on real-world historical data from QEPA, our hybrid model achieves significantly better performance than previous approaches with either temporally-aware dynamic Bayesian networks or an ensemble of spatially-aware models. Second, in collaboration with the Wildlife Conservation Society and Uganda Wildlife Authority, we present results from a five-month controlled experiment where rangers patrolled over 450 sq km across QEPA. We demonstrate that our model successfully predicted (1) where snaring activity would occur and (2) where it would not occur; in areas where we predicted a high rate of snaring activity, rangers found more snares and snared animals than in areas of lower predicted activity. These findings demonstrate that (1) our model’s predictions are selective, (2) our model’s superior laboratory performance extends to the real world, and (3) these predictive models can aid rangers in focusing their efforts to prevent wildlife poaching and save animals.

This paper focuses on new challenges in influence maximization inspired by non-profits’ use of social networks to effect behavioral change in their target populations. Influence maximization is a multiagent problem where the challenge is to select the most influential agents from a population connected by a social network. Specifically, our work is motivated by the problem of spreading messages about HIV prevention among homeless youth using their social network. We show how to compute solutions which are provably close to optimal when the parameters of the influence process are unknown. We then extend our algorithm to a dynamic setting where information about the network is revealed at each stage. Simulation experiments using real world networks collected by the homeless shelter show the advantages of our approach.

Advances in computational game theory have led to several successfully deployed applications in security domains. These gametheoretic approaches and security applications learn game payoff values or adversary behaviors from annotated input data provided by domain experts and practitioners in the field, or collected through experiments with human subjects. Beyond these traditional methods, unmanned aerial vehicles (UAVs) have become an important surveillance tool used in security domains to collect the required annotated data. However, collecting annotated data from videos taken by UAVs efficiently, and using these data to build datasets that can be used for learning payoffs or adversary behaviors in game-theoretic approaches and security applications, is an under-explored research question. This paper presents VIOLA, a novel labeling application that includes (i) a workload distribution framework to efficiently gather human labels from videos in a secured manner; (ii) a software interface with features designed for labeling videos taken by UAVs in the domain of wildlife security. We also present the evolution of VIOLA and analyze how the changes made in the development process relate to the efficiency of labeling, including when seemingly obvious improvements surprisingly did not lead to increased efficiency. VIOLA enables collecting massive amounts of data with detailed information from challenging security videos such as those collected aboard UAVs for wildlife security. VIOLA will lead to the development of a new generation of game-theoretic approaches for security domains, including approaches that integrate deep learning and game theory for real-time detection and response.

Whereas previous real-world game-theoretic applications in security focused on protection of critical infrastructure in the absence of past attack data, more recent work has focused on datadriven security and sustainability applications for protecting the environment, including forests, fish and wildlife. One key challenge in such “Green Security Game” (GSG) domains is to model the adversary’s decision making process based on available attack data. This thesis, for the first time, explores the suitability of different adversary behavior modeling approaches in such domains that differ in the type and amount of historical data available. The first contribution is to provide a detailed comparative study, based on actual human subject experiments, of competing adversary behavior models in domains where attack data is available in plenty (e.g., via a large number of sensors). This thesis demonstrates a new human behavior model, SHARP, which mitigates the limitations of previous models in three key ways. First, SHARP reasons based on successes or failures of the adversary’s past actions to model adversary adaptivity. Second, SHARP reasons about similarity between exposed and unexposed areas of the attack surface to handle the adversary’s lack of exposure to enough of the attack surface. Finally, SHARP integrates a non-linear probability weighting function to capture the adversary’s true weighting of probabilities.The second contribution relates to domains requiring predictions over a large set of targets by learning from limited (and in some cases, noisy) data. One example dataset on which we demonstrate our approaches to handle such challenges is a real-world poaching dataset collected over a large geographical area at the Queen Elizabeth National Park in Uganda. This data is too sparse to construct a detailed model. The second contribution of this thesis delivers a surprising result by presenting an adversary behavior modeling system, INTERCEPT, which is based on an ensemble of decision trees (i) that effectively learns and predicts poacher attacks based on limited noisy attack data over a large set of targets, and (ii) has fast execution speed. This has led to a successful month-long test of INTERCEPT in the field, a first for adversary behavior modeling applications in the wildlife conservation domain. Finally, for the my third contribution, we examine one common assumption in adversary behavior modeling that the adversary perfectly observes the defender’s randomized protection strategy. However, in domains such as wildlife conservation, the adversary only observes a limited sequence of defender patrols and forms beliefs about the defender’s strategy. In the absence of a comparative analysis and a principled study of the strengths and weaknesses of belief models, no informed decision could be made to incorporate belief models in adversary behavior models such as SHARP and INTERCEPT. This thesis provides the first-of-its-kind systematic comparison of existing and new proposed belief models and demonstrates based on human subjects experiments data that identifying heterogeneous belief update behavior is essential in making effective predictions. We also propose and evaluate customized models for settings that differ in the type of belief data available and quantify the value of having such historical data on the accuracy of belief prediction.

Stackelberg Security Games (SSG) have been widely applied for solving real-world security problems — with a significant research emphasis on modeling attackers’ behaviors to handle their bounded rationality. However, access to real-world data (used for learning an accurate behavioral model) is often limited, leading to uncertainty in attacker’s behaviors while modeling. This paper therefore focuses on addressing behavioral uncertainty in SSG with the following main contributions: 1) we present a new uncertainty game model that integrates uncertainty intervals into a behavioral model to capture behavioral uncertainty; and 2) based on this game model, we propose a novel robust algorithm that approximately computes the defender’s optimal strategy in the worst-case scenario of uncertainty. We show that our algorithm guarantees an additive bound on its solution quality.

Security is an important concern worldwide. Stackelberg Security Games have been used successfully in a variety of security applications, to optimally schedule limited defense resources by modeling the interaction between attackers and defenders. Prior research has suggested that it is possible to classify adversary behavior into distinct groups of adversaries based on the ways humans explore their decision alternatives. However, despite the widespread use of Stackelberg Security Games, there has been little research on how adversaries adapt to defense strategies over time (i.e., dynamics of behavior). In this paper, we advance this work by showing how adversaries’ behavior changes as they learn the defenders’ behavior over time. Furthermore, we show how behavioral game theory models can be modified to capture learning dynamics using a Bayesian Updating modeling approach. These models perform similarly to a cognitive model known as Instance-Based-Learning to predict learning patterns.