Introduction to the Artificial Intelligence in Government Minitrack

2023 | HICSS | Citations: 0

Authors: Carter, L.; Liu, D.; Gasco-Hernandez, M.

Abstract: ... Expand

Abstract: Collapse

Topics: artificial intelligence privacy decision support system

Methods: structured literature research federated learning bibliometric analysis qualitative content analysis design artifact

Theories: argumentation theory

A privacy-preserving decentralized credit scoring method based on multi-party information

2023 | Decision Support Systems | Citations: 0

Authors: He, Haoran; Wang, Zhao; Jain, Hemant; Jiang, Cuiqing; Yang, Shanlin

Abstract: With society's wide-scale adoption of information technology, significant inform ... Expand

Abstract: With society's wide-scale adoption of information technology, significant information about borrowers is distributed across various parties, information that can be jointly used to improve credit scoring. However, use of such information faces many challenges, such as the problems of preserving privacy and information redun­ dancy. To address these challenges in leveraging multi-source information for credit scoring, we propose a decentralized multi-party method based on logistic regression. Specifically, we formulate a logistic regression model using the vertical federated learning paradigm. To preserve data privacy during multi-party collaborative model training, we use additively homomorphic encryption based on the second-order Taylor series expansion of the loss function and its gradient. To address information redundancy and to improve the performance of the credit scoring model, we use the proposed HE-DPGD algorithm to estimate the distributed coefficients in a privacy-preserving setting. Empirical evaluation shows that the proposed method can leverage information from multiple parties securely and effectively. Collapse

Topics: privacy homomorphic encryption logistics management online lending missing data

Methods: computational algorithm machine learning federated learning logistic regression experiment

STRUCTURING FEDERATED LEARNING APPLICATIONS – A LITERATURE ANALYSIS AND TAXONOMY

2023 | European Conference On Information Systems | Citations: 0

Authors: Karnebogen, Philip; Kaymakci, Can; Willburger, Lukas; Häckel, Björn; Sauer, Alexander

Abstract: Ensuring data privacy is an essential objective competing with the ever-rising ... Expand

Abstract: Ensuring data privacy is an essential objective competing with the ever-rising capabilities of machine learning approaches fueled by vast amounts of centralized data. Federated learning addresses this conflict by moving the model to the data and ensuring the data itself does not leave a client's device. However, maintaining privacy impels new challenges concerning algorithm performance or fairness of the algorithm's results that remain uncovered from a sociotechnical perspective. We tackle this research gap by conducting a structured literature review and analyzing 152 articles to develop a taxonomy of federated learning applications with nine dimensions and 24 characteristics. Our taxonomy illustrates how different attributes of federated learning may affect the trade-off between an algorithm's privacy, performance, and fairness. Despite an increasing interest in the technical implementation of federated learning, our work is one of the first to emphasize an information systems perspective on this emerging and promising topic. Collapse

Topics: privacy online learning system computer hardware business-to-business decision support

Methods: literature sample structured literature research literature study federated learning computational algorithm

Data Portability

2023 | Business & Information Systems Engineering | Citations: 0

Authors: Kranz, Johann; Kuebler-Wachendorff, Sophie; Syrmoudis, Emmanuel; Grossklags, Jens; Mager, Stefan; Luzsa, Robert; Mayr, Susanne

Abstract: ... Expand

Abstract: Collapse

Topics: privacy social network search engine electronic market

Methods: federated learning machine learning design science field experiment

Enabling Privacy-Preserving Prediction for Length of Stay in ICU - A Multimodal Federated-Learning-based Approach

2023 | European Conference On Information Systems | Citations: 0

Authors: Wang, Tongnian; Guo, Yuanxiong; Choo, Kim-Kwang

Abstract: While the proliferation of data-driven machine learning approaches has resulted ... Expand

Abstract: While the proliferation of data-driven machine learning approaches has resulted in new opportunities for precision healthcare, there are a number of challenges associated with fully utilizing medical data, for example partly due to the heterogeneity of data modalities in electronic health records. Moreover, medical data often sits in data silos due to various regulatory, privacy, ethical, and legal considerations, which complicates efforts to fully utilize machine learning. Motivated by these challenges, we focus on clinical care-length of stay prediction and propose a Multimodal Federated Learning approach. The latter is designed to leverage both privacy-preserving federated learning and multimodal data to facilitate length of stay prediction. By applying this approach to a real-world medical dataset, we demonstrate the predictive power of our approach as well as how it can address the earlier discussed challenges. The findings also suggest the potential of the proposed multimodal federated learning approach for other similar healthcare settings. Collapse

Topics: privacy health information system healthcare data data governance artificial intelligence

Methods: longitudinal research federated learning time series analysis design science computational algorithm

Barriers and Opportunities In Cyber Risk And Compliance Management For Data-Driven Supply Chains

2022 | HICSS | Citations: 0

Authors: Afrifah, Williams; Epiphaniou, Dr Gregory; Ersotelos, Nikolaos; Maple, Carsten

Abstract: In today's highly competitive market, where globalisation, mass production, and ... Expand

Abstract: In today's highly competitive market, where globalisation, mass production, and specialisation characterise the interconnected industrialised society, integrated Supply Chains (SCs) are more important than ever. Decision-makers rely on precise SC data, and even the slightest interruption in the data flow can substantially impact the quality of the decisions. This dependency has inadvertently driven device connectivity towards an Industrial Internet of Things (IIoT) approach in the complete interconnection paradigm. While interconnectivity between devices has accelerated, IIoT and Industry 4.0, SC security measures have not kept pace. This conflict is exacerbated further where there is a need to process Personal Data produced by IIoT systems while maintaining data Confidentiality, Integrity and Availability (CIA). This paper provides an extensive review of academic sources and consulting reports and presents a comprehensive analysis of the relevance of personal data in managing Industry 4.0 SC complexity and visibility. The paper further examines the role that advancements in Blockchain and artificial intelligence (AI) can play in mitigating SC security management risks. Collapse

Topics: artificial intelligence industry 4.0 production management blockchain data management

Methods: archival research federated learning

Towards a Model for Inclusive Healthcare Access post COVID-19

2022 | HICSS | Citations: 0

Authors: Bhatt, Paras; Akanfe, Oluwafemi; Guo, Yuanxiong; Gong, Yanmin

Abstract: The devastation caused by the COVID-19 pandemic has exposed years of cyclic ineq ... Expand

Abstract: The devastation caused by the COVID-19 pandemic has exposed years of cyclic inequalities faced by disadvantaged and minority communities. Unequal access to healthcare and a lack of financial resources further exacerbates their suffering, especially during a pandemic. In such critical conditions, information technology-based healthcare services can be an efficient way of increasing access to healthcare for these communities. In this paper, we put forward a decision model for guiding the distribution of IT-based healthcare services for racial minorities. We augment the Health Belief Model by adding financial and technology beliefs. We posit that financial inclusion of minority populations increases their ability to access technology and, by extension, IT-based healthcare services. Financial inclusion and the use of secure private technologies like federated learning can indeed enable greater access to healthcare services for minorities. Therefore, we incorporate financial, health, and technology tools to develop a model for equitable delivery of healthcare services and test its applicability in different use-case scenarios. Collapse

Topics: information system use self efficacy privacy healthcare data information privacy concern

Methods: conceptual modelling federated learning literature study computational algorithm survey

Theories: health belief model

Credit Risk Modeling without Sensitive Features: An Adversarial Deep Learning Model for Fairness and Profit

2022 | International Conference on Information Systems | Citations: 0

Authors: Hu, Xiyang; Huang, Yan; Li, Beibei; Lu, Tian

Abstract: We propose an adversarial deep learning model for credit risk modeling. We make ... Expand

Abstract: We propose an adversarial deep learning model for credit risk modeling. We make use of sophisticated machine learning model's ability to triangulate (i.e., infer the sensitive group affiliation by using only permissible features), which is often deemed "troublesome" in fair machine learning research, in a positive way to increase both borrower welfare and lender profits while improving fairness. We train and test our model on a dataset from a real-world microloan company. Our model significantly outperforms regular deep neural networks without adversaries and the most popular credit risk model XGBoost, in terms of both improving borrowers' welfare and lenders' profits. Our empirical findings also suggest that the traditional AUC metric cannot reflect a model's performance on the borrowers' welfare and lenders' profits. Our framework is ready to be customized for other microloan firms, and can be easily adapted to many other decision-making scenarios. Collapse

Topics: decision making electronic commerce mobile phone privacy IS economics

Methods: machine learning XGBoost triangulation artificial neural network deep learning

TRACING DOWN THE VALUE OF CO-CREATION IN FEDERATED AI ECOSYSTEMS

2022 | European Conference On Information Systems | Citations: 0

Authors: Röder, Marco; Kowalczyk, Peter; Thiesse, Frédéric

Abstract: Methods and software components for developing novel IT solutions based on arti ... Expand

Abstract: Methods and software components for developing novel IT solutions based on artificial intelligence (AI) technology are broadly available to organizations of any size. However, as AI typically requires large amounts of data, smaller organizations are at a disadvantage compared to large competitors as the latter often have more training and test data at their disposal. Collaboration and data sharing between multiple smaller actors might offer a solution to this issue, but also poses a potential risk to privacy and confidentiality. Our research considers the concept of federated learning, which enables collaborative training without exchanging the actual data. Still, the benefits of value co-creation within federated AI ecosystems are unclear. To shed light on this topic, we present a data-driven analysis using the example of sales forecasting in retail. We show that three types of benefits can be expected in federated AI ecosystems, namely collaboration, privacy preservation, and generalizability. Collapse

Topics: artificial intelligence privacy fraud detection predictive maintenance value creation

Methods: computational algorithm time series analysis longitudinal research literature study federated learning

Theories: service-dominant logic

An Architecture for Federated Learning Enabled Collaborative Intrusion Detection System

2021 | Americas Conference on Information Systems | Citations: 0

Authors: McOsker, Caitlin; Handlin, Michael; Li, Lei; Shahriar, Hossain; Zhao, Liang

Abstract: Intrusion Detection Systems (IDSs) are essential part of a security solution to ... Expand

Abstract: Intrusion Detection Systems (IDSs) are essential part of a security solution to monitor the network traffics and detect malicious attacks. In a collaborative IDS, multiple IDSs work together to effectively detect large scaled and across platforms or operating systems attacks. However, the participating nodes in a CIDS may hesitate to share their network traffic data due to privacy concerns. In this paper, we propose a federated learning enabled CIDS architecture leveraging its privacy-reserving feature. An unsupervised machine learning algorithm, Self-Organizing Maps (SOM), is adopted as the intrusion detection method. Based on our knowledge, this research is the first attempt incorporating SOM and federated learning into CIDS. We believe that the proposed framework can greatly improve both precision and recall of the intrusion detection. This paper is research in progress. We are in the process of developing a preliminary research prototype and designing experiments for validations. KeywordsCollaborative intrusion detection system, unsupervised learning, federated learning, anomaly detection. Collapse

Topics: privacy intrusion detection system zero-day vulnerability open source open source software project

Methods: machine learning federated learning experiment design artifact computational algorithm