Unsupervised Threat Hunting using Continuous Bag of Terms and Time (CBoTT)

2023 | International Conference on Information Systems | Citations: 0

Authors: Kayhan, Varol; Shivendu, Shivendu; Behnia, Rouzbeh; Daniel, Clinton; Agrawal, Manish

Abstract: Threat hunting is sifting through system logs to detect malicious activities th ... Expand

Abstract: Threat hunting is sifting through system logs to detect malicious activities that might have bypassed existing security measures. It can be performed in several ways, one of which is based on detecting anomalies. We propose an unsupervised framework, called continuous bag-of-terms-and-time (CBoTT), and publish its application programming interface (API) to help researchers and cybersecurity analysts perform anomaly-based threat hunting among SIEM logs geared toward process auditing on endpoint devices. Analyses show that our framework consistently outperforms benchmark approaches. When logs are sorted by likelihood of being an anomaly (from most likely to least), our approach identifies anomalies at higher percentiles (between 1.82-6.46) while benchmark approaches identify the same anomalies at lower percentiles (between 3.25-80.92). This framework can be used by other researchers to conduct benchmark analyses and cybersecurity analysts to find anomalies in SIEM logs. Collapse

Topics: IT security application programming interface Hadoop Distributed File System website web analytics

Methods: natural language processing artificial neural network support vector machine term frequency–inverse document frequency DBSCAN

Towards a Scalable Digital Skills Training Architecture for Resource-Constrained Environments: The Case of Ayitic Goes Global in Haiti

2023 | Communications of the Association for Information Systems | Citations: 0

Authors: Rao, Lila; McNaughton, Maurice; Verma, Sameer

Abstract: In developing countries such as Haiti, which are marked by high unemployment an ... Expand

Abstract: In developing countries such as Haiti, which are marked by high unemployment and gender inequality, online education has the potential to change lives. Returns on education are particularly high in Information Communications Technology (ICT)-intensive jobs and IT outsourcing offers opportunities for remote employment, providing alternatives for economic diversification and job creation that are particularly relevant for youth and women. However, the problem faced by many developing countries, is that traditional models, frameworks, architectures, and platforms for online learning do not lend themselves well to their context and, therefore, it is important to develop context-specific platforms. This need for suitable platforms has motivated the research question that this paper seeks to address, that is: What is the appropriate architecture that supports learning strategies for delivering scalable digital skills training in a resource-constrained environment? We propose an architecture that was developed specifically for blended learning in resource-constrained environments and describe how a prototype for this was designed, built, and deployed in Haiti. The initial responses to the application of the architecture, including the testimonials of the participants and the interest expressed by other countries of the region in adopting the proposed architecture, have been extremely positive. Collapse

Topics: online learning system digital literacy IT skill cloud computing Google+

Methods: design process design artifact literature study

Theories: learning theory

Socialize Less Pay More: The Link Between Virtual Network Embeddedness and User Contributions

2023 | Americas Conference on Information Systems | Citations: 0

Authors: cho, Kanghyun; Nam, Kihwan

Abstract: This study examines the impact of network structure on two important business o ... Expand

Abstract: This study examines the impact of network structure on two important business outcomes of the PWYW (Pay-What-You-Want) live streaming platform, namely live chat, and tipping. Specifically, we investigate the role of network embeddedness on these outcomes by analyzing 9,524,420 transaction-broadcast records from 1,334,999 users of a leading PWYW live streaming platform in South Korea. Our analysis sheds light on how user contributions in the form of tipping and live chat change because of the extent of content consumption overlaps. Our preliminary results suggest that higher levels of network embeddedness lead to increased tipping and decreased live chatting. These findings have important implications for platform designers and streamers, as they highlight the need to consider consumption patterns across users in the design of PWYW live streaming platforms. Collapse

Topics: live streaming platform digital service streaming service web analytics online community

Methods: longitudinal research vector autoregression difference in differences propensity score matching autocorrelation analysis

Theories: social network theory

Workshop: Design- and specification methods for efficient user involvement

2022 | International Conference on Business Informatics | Citations: 0

Authors: Degen, Helmut

Abstract: Efficiency of use has been a topic of interest for human-computer interaction (H ... Expand

Abstract: Efficiency of use has been a topic of interest for human-computer interaction (HCI) and in usability from the beginning [1]. Although efficiency is directly related to productivity, a driver for business success, efficiency has not been addressed systematically in the HCI community. The paper motivates and introduces three big questions for efficiency of use: What are benefits of efficiency? What are some deficiencies? What is a path forward to address the deficiencies? A contribution of the paper is a user involvement metric taxonomy. It is a proposed technique for a human-centered design for efficiency approach used for the design and development of interactive applications. Collapse

Topics: participatory design problem solving web analytics

Methods: design methodology

A user involvement measurement technique for user involvement metrics

2022 | International Conference on Business Informatics | Citations: 0

Authors: Nagaraja, Parinitha; Degen, Helmut

Abstract: Efficiency of use has always been a topic of interest for humancomputer interact ... Expand

Abstract: Efficiency of use has always been a topic of interest for humancomputer interaction and in usability. One of the challenges is to be able to measure the efficiency or inefficiency thereof for different types of user involvement including user actions and system actions. The paper proposes a technique to measure user involvement times based on a user involvement taxonomy [1]. The technique uses tracking of mouse and keyboard events as well as the software application process start time. The measurement technique is applied to the Windows Calculator for a simple addition task. The measured times are reported. The elapsed user involvement time is 5.827 seconds. 5.216 seconds (89.5% of elapsed involvement time) is allocated to elapsed hands-on time and 0.611 seconds (10.5% of elapsed involvement time) for elapsed waiting time. The measured elapsed waiting time (0.611 seconds) and the average waiting time (0.122 seconds) are in line with Seow’s benchmark boundaries [2]. The user involvement metrics provide context for the individual measured events and make them interpretable and usable. Collapse

Topics: participatory design operating system laptop computer evaluation criteria web analytics

Methods: design methodology experiment literature study computational algorithm usability testing

Designing an IT-Based System for Optimizing Lung Cancer Management

2022 | Americas Conference on Information Systems | Citations: 0

Authors: Shah, Adnan Muhammad; Muhammad, Wazir; Ahmed, Ali; Ahmed, Saad Bin Saeed

Abstract: Digital health offers lung cancer patients to improve their health status while ... Expand

Abstract: Digital health offers lung cancer patients to improve their health status while allowing patients, providers, and administrators to coordinate data and care at individual and community levels. While technology improvements provide lung cancer patients and healthcare providers with a valuable new tool for disease management, these are yet to be widely accepted. In particular, we aim to: (1) develop a Machine Learning (ML)-based framework for data collection from active online lung cancer forums and other parameters for patients, providers and their organizations, (2) build an AI-based model to develop a cancer ontology for exploring different factors and patients' emotions associated to lung cancer management, (3) Design a mHealth app to set up a support system in terms of providing patients with information and social support, and ML models-based treatment recommendation system. The IT-based support system will provide the best and most specific treatment plan and recommendation system for lung cancer management. KeywordsLung cancer, online cancer forums, mHealth, decision support system. ConclusionScientific investigations regarding disease management in the digital oncology domain are still in the early stages. Outcomes of the study would demonstrate that combining AI with Big Data analytics plays a pivotal role in mHealth and improves health outcomes of patients with lung cancer. The advantages of employing IT (mHealth) are driving healthcare system transformation, and more important changes and benefits will emerge in the future with the following expected outcomes.(1) For patients using AI-based mHealth technology, this project will help in improving provider-patient communication and relationship, increase patient satisfaction, expand informational support to patients, families and caregivers, better and persistent self-assessment, and reduce search costs, (2) In addition, the developed mHealth technology will provide patients, families, and caregivers with social and emotional support and improve mental health, such as reducing anxiety, social isolation, depression, social class, and neuroticism, (3) Our AI-based mHealth technology supports medication adherence, minimizes clinical errors, saves time through emergencies, improves the quality of care, scientific assessment, and strengthens clinical decisions in real-time for healthcare providers in the oncological domain, (4) At the industry level, this work will better understand medical data scientists to analyze the users' conversations in OCF and other healthcare parameters accurately and help them in designing MLbased treatment recommendation system, (5) This work will assist lung cancer patients in making better insurance decisions and provide a customized cost estimate of annual health care costs. Collapse

Topics: mobile health recommender system artificial intelligence mobile application health information system

Methods: machine learning ontological modelling longitudinal research

The Cost of Fairness in AI: Evidence from E-Commerce

2022 | Business & Information Systems Engineering | Citations: 0

Authors: von Zahn, Moritz; Feuerriegel, Stefan; Kuehl, Niklas

Abstract: Contemporary information systems make widespread use of artificial intelligence ... Expand

Abstract: Contemporary information systems make widespread use of artificial intelligence (AI). While AI offers various benefits, it can also be subject to systematic errors, whereby people from certain groups (defined by gender, age, or other sensitive attributes) experience disparate outcomes. In many AI applications, disparate outcomes confront businesses and organizations with legal and reputational risks. To address these, technologies for so-called “AI fairness” have been developed, by which AI is adapted such that mathematical constraints for fairness are fulfilled. However, the financial costs of AI fairness are unclear. Therefore, the authors develop AI fairness for a real-world use case from e-commerce, where coupons are allocated according to clickstream sessions. In their setting, the authors find that AI fairness successfully manages to adhere to fairness requirements, while reducing the overall prediction performance only slightly. However, they find that AI fairness also results in an increase in financial cost. Thus, in this way the paper’s findings contribute to designing information systems on the basis of AI fairness. Collapse

Topics: artificial intelligence electronic commerce web analytics marketing management website

Methods: computational algorithm artificial neural network machine learning deep learning experiment

Theories: socio technical theory

The Phishing Funnel Model: A Design Artifact to Predict User Susceptibility to Phishing Websites

2021 | Information Systems Research | Citations: 17

Authors: Abbasi, Ahmed; Dobolyi, David; Vance, Anthony; Zahedi, Fatemeh Mariam

Abstract: Phishing is a significant security concern for organizations, threatening employ ... Expand

Abstract: Phishing is a significant security concern for organizations, threatening employees and members of the public. Phishing threats against employees can lead to severe security incidents, whereas those against the public can undermine trust, satisfaction, and brand equity. At the root of the problem is the inability of Internet users to identify phishing attacks even when using anti-phishing tools. We propose the phishing funnel model (PFM), a design artifact for predicting user susceptibility to phishing websites. PFM incorporates user, threat, and tool-related factors to predict actions during four key stages of the phishing process: visit, browse, consider legitimate, and intention to transact. We used a support vector ordinal regression with a custom kernel encompassing a cumulative-link mixed model for representing users’ decisions across funnel stages. We evaluated the efficacy of PFM in a 12-month longitudinal field experiment in two organizations involving 1,278 employees and 49,373 phishing interactions. PFM significantly outperformed competing models/methods by 8%–52% in area under the curve, correctly predicting visits to high-severity threats 96% of the time—a result 10% higher than the nearest competitor. A follow-up three-month field study revealed that employees using PFM were significantly less likely to interact with phishing threats relative to comparison models and baseline warnings. Furthermore, a cost-benefit analysis showed that interventions guided by PFM resulted in phishing-related cost reductions of nearly $1,900 per employee more than comparison prediction methods. These results indicate strong external validity for PFM. Our findings have important implications for practice by demonstrating (1) the effectiveness of predicting user susceptibility to phishing as a real-time protection strategy, (2) the value of modeling each stage of the phishing process together, rather than focusing on a single user action, and (3) the considerable impact of anti-phishing tool and threat-related factors on susceptibility to phishing. Collapse

Topics: phishing electronic mail phishing website website cost benefit analysis

Methods: survey experiment field experiment machine learning longitudinal research

Theories: technology acceptance model protection motivation theory

Trust calibration of automated security IT artifacts: A multi-domain study of phishing-website detection tools

2021 | Information & Management | Citations: 0

Authors: Chen, Yan; Zahedi, Fatemeh Mariam; Abbasi, Ahmed; Dobolyi, David

Abstract: Phishing websites become a critical cybersecurity threat affecting individuals a ... Expand

Abstract: Phishing websites become a critical cybersecurity threat affecting individuals and organizations. Phishingwebsite detection tools are designed to protect users against such sites. Nevertheless, detection tools face serious user trust and suboptimal performance issues which require trust calibration to align trust with the tool’s capabilities. We employ the theoretical framework of automation trust and reliance as a kernel theory to develop the trust calibration model for phishing-website detection tools. We test the model using a controlled lab experiment. The results of our analysis show that users’ trust in detection tools can be calibrated by trust cali­ brators. Moreover, users’ calibrated trust has significant consequences, including users’ tool reliance, use, and performance against phishing websites. Collapse

Topics: phishing website website usage intention online banking IT security

Methods: experiment laboratory experiment structural equation modeling kernel theory factor analysis

Current Requirements and Implementations in the field of Web Tracking in the pre-age of E-Privacy Regulation

2021 | European Conference On Information Systems | Citations: 0

Authors: Janßen, Christian; Diener, Matthias; Gómez, Jorge Marx

Abstract: Website operators have an interest in storing and evaluating data about their u ... Expand

Abstract: Website operators have an interest in storing and evaluating data about their users. On this basis, websites will be optimized and marketing campaigns carried out. Cookies are a standardized method of data storage in the field of web-tracking and contain a variety of different information about a user. Often personal data is stored in cookies to identify a user. At this point, the legal requirements of the ePrivacy (Cookie) Directive and the General Data Protection Regulation must be observed. The new ePrivacy Regulation has not yet come into force and is expected in 2021. This research aims to develop legal and functional-technical requirements to meet the current challenges. As a general source for the development, a literature review and qualitative expert interviews have been carried out. For the validation, we conducted a study and implemented a web scraper in order to analyze the top 100 e-commerce websites in Germany. Collapse

Topics: website electronic commerce marketing management web analytics individual characteristic

Methods: qualitative interview structured literature research literature study natural language processing