Introduction: Cybersecurity and Software Assurance Minitrack

2021 | HICSS | Citations: 0

Authors: Chamberlain, Luanne Burns; Laurel, Johns Hopkins Road

Abstract: The presence of cyber in our daily lives continues its relentless growth with c ... Expand

Abstract: The presence of cyber in our daily lives continues its relentless growth with cyber components deeply embedded across an astonishing range of applications, including medicine, finance, transportation, education, agriculture, communications, home automation, social media, voting, the power grid, and many more.Meanwhile, cyber attackers continue to hold a persistent asymmetric advantage over defenders, a situation that is ever more troubling given cyber's ubiquity. The community increasingly recognizes that the defense of cyber systems is a multi-dimensional challenge that requires new approaches.The papers in this minitrack provide outstanding examples of the kind of diverse thinking required to strengthen the foundations of cyber defense. The papers cover a range of topics including data sovereignty, moving target defense, vulnerability prediction, malware detection, and attack pattern analysis.In the first paper, Utilizing Remote Evaluation for Providing Data Sovereignty in Data-sharing Ecosystems, authors Favian Bruckner and Falk Howar describe a remote processing approach that arranges for client/customer applications to "travel" to data rather than the other way around. The data processed by the applications remains safeguarded in a controlled environment, with only summary results transmitted back to consuming organizations.In the second paper, The use of partially observable Markov decision processes to optimally implement moving target defense, authors Ashley McAbee, Murali Tummala, and John McEachen discuss an implementation of a partially observable Markov decision process to select among moving target defense options during live attacks. The paper illustrates the approach with a five-state attack sequence. Collapse

Topics: packaged software Docker database system

Methods: partially observable Markov decision process

“Level Up”: Leveraging Skill and Engagement to Maximize Player Game-Play in Online Video Games

2019 | Information Systems Research | Citations: 0

Authors: Huang, Yan; Jasin, Stefanus; Manchanda, Puneet

Abstract: We propose a novel two-stage data-analytic modeling approach combining theories, ... Expand

Abstract: We propose a novel two-stage data-analytic modeling approach combining theories, statistical analysis, and optimization techniques to model player engagement as a function of motivation to maximize customer game-play via matching in the large and growing online video game industry. In the first stage, we build a hidden Markov model (HMM) based on theories of customer engagement and gamer motivation to capture the evolution of gamers’ latent engagement state and state-dependent participation behavior. We then calibrate the HMM using a longitudinal data set, obtained from a major international video gaming company, that contains detailed information on 1,309 randomly sampled gamers’ playing histories over a period of 29 months comprising more than 700,000 unique game rounds. We find that high-, medium-, and low-engagement-state gamers respond differently to motivations, such as feelings of effectance and need for challenge. In the second stage, we use the results from the first stage to develop a matching algorithm that learns (infers) the gamer’s current engagement state “on the fly” and exploits that learning to match the gamer to a round to maximize game-play. Our algorithm increases gamer game-play volume and frequency by 4%–8% conservatively, leading to economically significant revenue gains for the company. Collapse

Topics: video game analytical information system decision making advertising management collaborative filtering

Methods: computational algorithm robustness check experiment simulation optimization model

Theories: motivation theory self determination theory

Treatment Recommendation in Critical Care: A Scalable and Interpretable Approach in Partially Observable Health States

2018 | International Conference on Information Systems | Citations: 0

Authors: Utomo, Chandra Prasetyo; Li, Xue; Chen, Weitong

Abstract: Intensive care unit (ICU) generates huge amount of medical data. These records a ... Expand

Abstract: Intensive care unit (ICU) generates huge amount of medical data. These records are valuable to expand medical knowledge, improve healthcare delivery, and increase survival rate. Optimal treatment recommendation is one of the most important applications. As ICU data contains non-optimal treatments, this problem cannot be solved effectively by supervised learning approaches. In addition, there are three major challenges: partial observability in patient state, indeterminism in treatment effect, and limited learning cases. In this study, we propose a novel method based on reinforcement learning approach to alleviate those challenges. We introduce a patient sequence model as a representation of each ICU stay. We consider uncertainty in patient states and treatment effects in our algorithm. Initial results with a real ICU database show that the method has a better explainability. This advantage is an important aspect to communicating with domain experts, guiding the research in right direction, and increasing its applicability. Collapse

Topics: database system healthcare data missing data electronic health record recommender system

Methods: reinforcement learning computational algorithm literature study partially observable Markov decision process Markov decision process

On Evaluating Information Revelation Policies in Procurement Auctions: A Markov Decision Process Approach

2010 | Information Systems Research | Citations: 15

Authors: Greenwald, Amy; Kannan, Karthik; Krishnan, Ramayya

Abstract: Each market session in a reverse electronic marketplace features a procurer and ... Expand

Abstract: Each market session in a reverse electronic marketplace features a procurer and many suppliers. An important attribute of a market session chosen by the procurer is its information revelation policy. The revelation policy determines the information (such as the number of competitors, the winning bids, etc.) that will be revealed to participating suppliers at the conclusion of each market session. Suppliers participating in multiple market sessions use strategic bidding and fake their own cost structure to obtain information revealed at the end of each market session. The information helps to reduce two types of uncertainties encountered in future market sessions, namely, their opponents' cost structure and an estimate of the number of their competitors. Whereas the first type of uncertainty is present in physical and e-marketplaces, the second type of uncertainty naturally arises in IT-enabled marketplaces. Through their effect on the uncertainty faced by suppliers, information revelation policies influence the bidding behavior of suppliers which, in turn, determines the expected price paid by the procurer. Therefore, the choice of information revelation policy has important consequences for the procurer. This paper develops a partially observable Markov decision process model of supplier bidding behavior and uses a multiagent e-marketplace simulation to analyze the effect that two commonly used information revelation policies—complete information policy and incomplete information policy—have on the expected price paid by the procurer. We find that the expected price under the complete information policy is lower than that under the incomplete information policy. The integration of ideas from the multiagents literature, the machine-learning literature, and the economics literature to develop a method to evaluate information revelation policies in e-marketplaces is a novel feature of this paper. Collapse

Topics: IT policy electronic market website decision making Java

Methods: computational algorithm simulation experiment mathematical model statistical hypothesis test

Theories: game theory

A Computational Approach to Compare Information Revelation Policies

2003 | International Conference on Information Systems | Citations: 0

Authors: Greenwald, Amy; Kannan, Karthik; Krishnan, Ramayya

Abstract: Revelation policies in an electronic marketplace differ in terms of the level of ... Expand

Abstract: Revelation policies in an electronic marketplace differ in terms of the level of competitive information disseminated to participating sellers. Since sellers who repeatedly compete against one another learn based on the information revealed and alter their future bidding behavior, revelation policies affect welfare parameters—consumer surplus, producer surplus, and social welfare—of the market. Although different revelation policies are adopted in several traditional and Web-based marketplaces, prior work has not studied the implications of these policies on the performance of a market. Collapse

Topics: electronic market procurement management

Methods: computational algorithm mathematical model machine learning Markov decision process nonparametric test

Theories: game theory