Using AI to Improve Sustainable Agricultural Practices: A Literature Review and Research Agenda

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

Authors: Lakshmi, Vijaya; Corbett, Jacqueline

Abstract: The world is confronted with the grand challenge of food insecurity amidst grow ... Expand

Abstract: The world is confronted with the grand challenge of food insecurity amidst growing populations and the climate crisis. Artificial intelligence (AI) deployed in agricultural decision support systems (AgriDSS) raises both hopes and concerns for increasing agricultural productivity in sustainable ways. We conduct a scoping review to uncover the roadblocks to the use of AI-supported AgriDSS in sustainable agriculture. Based on the corpus of 121 articles, we find that the effective use of AI-supported AgriDSS is hindered at technical, social, ethical, and ecological levels. Then, drawing on the experiential learning perspective, we propose how conjoint experiential learning (CEL) can enhance sustainable agricultural practices by enhancing both AI and human learning and overcoming roadblocks in using AgriDSS. Based on this conceptual framework, we build a research agenda that suggests blind spots and possible directions for future research. Collapse

Topics: artificial intelligence decision support system human computer interaction human in the loop decision making

Methods: literature sample literature study computational algorithm qualitative coding artificial neural network

Deep Learning for Information Systems Research

2023 | Journal of Management Information Systems | Citations: 1

Authors: Samtani, Sagar; Zhu, Hongyi; Padmanabhan, Balaji; Chai, Yidong; Chen, Hsinchun; Nunamaker Jr., Jay F.

Abstract: Modern artificial intelligence (AI) is heavily reliant on deep learning (DL), an ... Expand

Abstract: Modern artificial intelligence (AI) is heavily reliant on deep learning (DL), an emerging class of algorithms that can automatically detect non-trivial patterns from petabytes of rapidly evolving "Big Data." Although the information systems (IS) discipline has embraced DL, questions remain about DL's interface with a domain and theory and DL contribution types. In this paper, we present a DL information systems research (DL-ISR) schematic that reviews DL while considering the role of the application environment and knowledge base, summarizes extant DL research in IS, a knowledge contribution framework (KCF) to position DL contributions, and ten guidelines to help IS scholars design, execute, and present DL for computational, behavioral, or economic IS research. We illustrate a research contribution to DL for cybersecurity. This article's contribution to theory resides in the conceptual DL-ISR schematic and KCF, while its contributions to practice are based on its practical guidelines for executing DL-based projects. Collapse

Topics: knowledge base IT security artificial intelligence darknet IT security threat

Methods: Cross-Industry Standard Process for Data Mining data transformation autoencoder computational algorithm econometric modeling

The Professionalization of Hackers: A Content Analysis of 30 Years of Hacker Communication

2023 | Communications of the Association for Information Systems | Citations: 2

Authors: Ulrich, Frank; Müller, Sune; Flowers, Stephen

Abstract: Underground hacking has evolved from its early countercultural roots to become ... Expand

Abstract: Underground hacking has evolved from its early countercultural roots to become a complex and varied phenomenon. By combining a historical review of the literature with a content analysis of 30 years of underground hacker communication, we show that hacking has evolved in three waves to embrace learning and creativity, intrusion and crime, as well as politics and cyberwarfare. We uncover a paradoxical relationship between hackers and society at large where underground hacking is considered a digital crime while at the same time inspiring and driving corporate innovation, cybersecurity, and even cyberwarfare. The outcome of our research provides a nuanced picture of the hacker underground by highlighting differences between competing discursive themes across time. Moreover, by translating these themes into a set of six contrasting personas of IS professionals, we discuss how knowledge, technologies, and creative practices of underground hackers are being professionalized. We use this discussion to provide implications and a research agenda for IS studies in cybersecurity, innovation, and cyberwarfare. Collapse

Topics: innovation management IT security criminality cyberwarfare IT workforce

Methods: qualitative content analysis theory development synthesis archival research literature study

Theories: management theory

A text-mining based cyber-risk assessment and mitigation framework for critical analysis of online hacker forums

2022 | Decision Support Systems | Citations: 0

Authors: Biswas, Baidyanath; Mukhopadhyay, Arunabha; Bhattacharjee, Sudip; Kumar, Ajay; Delen, Dursun

Abstract: Online hacker communities are meeting spots for aspiring and seasoned cybercrimi ... Expand

Abstract: Online hacker communities are meeting spots for aspiring and seasoned cybercriminals where they engage in technical discussions, share exploits and relevant hacking tools to be used in launching cyber-attacks on business organizations. Sometimes, the affected organizations can detect these attacks in advance, with the help of cyberthreat intelligence derived from the explicit and implicit features of hacker communication in these forums. Herein, we proposed a novel text-mining based cyber-risk assessment and mitigation framework, which performs the following critical tasks. (i) Cyber-risk Assessment - to identify hacker expertise (i.e., newbie, beginner, inter­ mediate, and advanced) using explicit and implicit features applying various classification algorithms. Among these features, cybersecurity keywords, sharing of attachments, and sentiments emerged as significant. Further, we found that expert hackers demonstrate leadership in the online forums that eventually serve as communities of practice. Consequently, novice hackers gradually develop their cyber-attack skills through prolonged observa­ tions, interactions, and external influences in this social learning process. (ii) Cyber-risk mitigation – computes financial impact for every {hacker expertise, attack-type} combination, and then by ranking them on a {likelihood, impact} decision-matrix to prioritize mitigation strategies in affected organizations. Through these novel rec­ ommendations, our framework can guide managers to decide on appropriate cybersecurity controls using an {expected loss, probability, attack-type, hacker expertise} metric against financial losses due to cyber-attacks. Collapse

Topics: IT security IT security threat darknet source code logistics management

Methods: classification method sentiment analysis decision tree classification term frequency–inverse document frequency literature study

Theories: social exchange theory social practice theory

AI-Based Vehicular Network toward 6G and IoT: Deep Learning Approaches

2022 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Chen, Mu-Yen; Fan, Min-Hsuan; Huang, Li-Xiang

Abstract: In recent years, vehicular networks have become increasingly large, heterogeneou ... Expand

Abstract: In recent years, vehicular networks have become increasingly large, heterogeneous, and dynamic, making it difficult to meet strict requirements of ultralow latency, high reliability, high security, and massive connections for next generation (6G) networks. Recently, deep learning (DL) has emerged as a powerful artificial intelligence (AI) technique to optimize the efficiency and adaptability of vehicle and wireless communication. However, rapidly increasing absolute numbers of vehicles on the roads are leading to increased automobile accidents, many of which are attributable to drivers interacting with their mobile phones. To address potentially dangerous driver behavior, this study applies deep learning approaches to image recognition to develop an AI-based detection system that can detect potentially dangerous driving behavior. Multiple convolutional neural network (CNN)-based techniques including VGG16, VGG19, Densenet, and Openpose were compared in terms of their ability to detect and identify problematic driving. Collapse

Topics: extensible markup language enterprise architecture Python open source evaluation criteria

Methods: machine learning deep learning experiment convolutional neural network TensorFlow

Cross-Lingual Cybersecurity Analytics in the International Dark Web with Adversarial Deep Representation Learning

2022 | Management Information Systems Quarterly | Citations: 0

Authors: Ebrahimi, Mohammadreza; Chai, Yidong; Samtani, Sagar; Chen, Hsinchun

Abstract: International dark web platforms operating within multiple geopolitical regions ... Expand

Abstract: International dark web platforms operating within multiple geopolitical regions and languages host a myriad of hacker assets such as malware, hacking tools, hacking tutorials, and malicious source code. Cybersecurity analytics organizations employ machine learning models trained on human-labeled data to automatically detect these assets and bolster their situational awareness. However, the lack of human-labeled training data is prohibitive when analyzing foreign-language dark web content. In this research note, we adopt the computational design science paradigm to develop a novel IT artifact for cross-lingual hacker asset detection (CLHAD). CLHAD automatically leverages the knowledge learned from English content to detect hacker assets in non-English dark web platforms. CLHAD encompasses a novel Adversarial deep representation learning (ADREL) method, which generates multilingual text representations using generative adversarial networks (GANs). Drawing upon the state of the art in cross-lingual knowledge transfer, ADREL is a novel approach to automatically extract transferable text representations and facilitate the analysis of multilingual content. We evaluate CLHAD on Russian, French, and Italian dark web platforms and demonstrate its practical utility in hacker asset profiling, and conduct a proof-of-concept case study. Our analysis suggests that cybersecurity managers may benefit more from focusing on Russian to identify sophisticated hacking assets. In contrast, financial hacker assets are scattered among several dominant dark web languages. Managerial insights for security managers are discussed at operational and strategic levels. Collapse

Topics: darknet IT security knowledge sharing shapley additive explanation spoofing

Methods: machine learning design science design artifact case study deep learning

Artificial Intelligence for Cybersecurity: Towards Taxonomy-based Archetypes and Decision Support

2022 | International Conference on Information Systems | Citations: 0

Authors: Gerlach, Jana; Werth, Oliver; Breitner, Michael H.

Abstract: Cybersecurity is a critical success factor for more resilient companies, organi ... Expand

Abstract: Cybersecurity is a critical success factor for more resilient companies, organizations, and societies against cyberattacks. Artificial intelligence (AI)-driven cybersecurity solutions have the ability to detect and respond to cyber threats and attacks and other malicious activities. For this purpose, the most important resource is security-relevant data from networks, cloud systems, clients, e-mails, and previous cyberattacks. AI, the key technology, can automatically detect, for example, anomalies and malicious behavior. Consequently, the market for AI-driven cybersecurity solutions is growing significantly. We develop a taxonomy of AI-driven cybersecurity business models by classifying 229 real-world services. Building on that, we derive four specific archetypes using a cluster analysis toward a comprehensive academic knowledge base of business model elements.To reduce complexity and simplify the results of the taxonomy and archetypes, we propose DETRAICS, a decision tree for AI-driven cybersecurity services. Practitioners, decision-makers, and researchers benefit from DETRAICS to select the most suitable AIdriven service. Collapse

Topics: IT security artificial intelligence business model strategic management value creation

Methods: decision tree classification qualitative interview cluster analysis machine learning theoretical contribution

Discovering Emerging Threats in the Hacker Community: A Nonparametric Emerging Topic Detection Framework

2022 | Management Information Systems Quarterly | Citations: 0

Authors: Li, Weifeng; Chen, Hsinchun

Abstract: The prevalence and rapid growth of cybercrime are largely attributed to hacker c ... Expand

Abstract: The prevalence and rapid growth of cybercrime are largely attributed to hacker communities on the dark web, where cybercriminals extensively exchange hacking resources, share hacking knowledge, and organize cyberattacks. Such streams of hacker-generated content constitute an invaluable data source for developing threat intelligence that can inform organizations of cybersecurity risks and facilitate proactive cyber defense. Drawing upon the design science paradigm, we propose a novel nonparametric emerging topic detection (NPETD) framework for detecting emerging topics in streams of hacker-generated content. Our framework extends the state-of-the-art nonparametric topic model to inductively model topics without having to specify the number of topics a priori. Moreover, our framework features an efficient algorithm to jointly infer topics and detect topic emergence. We conducted experiments to rigorously evaluate the effectiveness and efficiency of our framework in comparison with the state-of-the-art baseline methods. Our framework outperformed the baseline methods in detecting the listings of emerging threats in darknet marketplaces on recall, F-measure, topic coherence, and processor time. The practical utility of our framework is further demonstrated in a major hacker forum, where we identified several notable emerging topics with important implications for victim companies and law enforcement. The proposed framework contributes to cybersecurity, topic detection and tracking, and design science. Collapse

Topics: darknet IT security denial of service attack malware Wikipedia

Methods: topic model computational algorithm machine learning experiment design science

Linking Exploits from the Dark Web to Known Vulnerabilities for Proactive Cyber Threat Intelligence: An Attention-Based Deep Structured Semantic Model

2022 | Management Information Systems Quarterly | Citations: 0

Authors: Samtani, Sagar; Chai, Yidong; Chen, Hsinchun

Abstract: Black hat hackers use malicious exploits to circumvent security controls and tak ... Expand

Abstract: Black hat hackers use malicious exploits to circumvent security controls and take advantage of system vulnerabilities worldwide, costing the global economy over $450 billion annually. While many organizations are increasingly turning to cyber threat intelligence (CTI) to help prioritize their vulnerabilities, extant CTI processes are often criticized as being reactive to known exploits. One promising data source that can help develop proactive CTI is the vast and ever-evolving Dark Web. In this study, we adopted the computational design science paradigm to design a novel deep learning (DL)- based exploit-vulnerability attention deep structured semantic model (EVA-DSSM) that includes bidirectional processing and attention mechanisms to automatically link exploits from the Dark Web to vulnerabilities. We also devised a novel device vulnerability severity metric (DVSM) that incorporates the exploit post date and vulnerability severity to help cybersecurity professionals with their device prioritization and risk management efforts. We rigorously evaluated the EVA-DSSM against state-of-theart non-DL and DL-based methods for short text matching on 52,590 exploit-vulnerability linkages across four testbeds: web application, remote, local, and denial of service. Results of these evaluations indicate that the proposed EVA-DSSM achieves precision at 1 scores 20% - 41% higher than non-DL approaches and 4% - 10% higher than DL-based approaches. We demonstrated the EVA-DSSM’s and DVSM’s practical utility with two CTI case studies: openly accessible systems in the top eight U.S. hospitals and over 20,000 Supervisory Control and Data Acquisition (SCADA) systems worldwide. A complementary user evaluation of the case study results indicated that 45 cybersecurity professionals found the EVADSSM and DVSM results more useful for exploit-vulnerability linking and risk prioritization activities than those produced by prevailing approaches. Given the rising cost of cyberattacks, the EVA-DSSM and DVSM have important implications for analysts in security operations centers, incident response teams, and cybersecurity vendors. Collapse

Topics: IT security web application information retrieval darknet PHP

Methods: computational algorithm case study experiment usability testing Okapi BM25

Online Black-Markets: An Investigation of a Digital Infrastructure in the Dark

2022 | Information Systems Frontiers | Citations: 0

Authors: Spagnoletti, Paolo; Ceci, Federica; Bygstad, Bendik

Abstract: This paper investigates the functioning of Online Black-Markets (OBMs), i.e. a d ... Expand

Abstract: This paper investigates the functioning of Online Black-Markets (OBMs), i.e. a digital infrastructure operating in the Dark Net that enables the exchange of illegal goods such as drugs, weapons and fake digital identities. OBMs exist notwithstanding adverse conditions such as police interventions, scams and market breakdowns. Relying on a longitudinal case study, we focus on the dynamics of interactions among actors and marketplace technologies and we identify three mechanisms explaining OBMs operations. In particular, we show that OBMs infrastructure is the result of commoditization, platformization and resilience processes. Our contribution relies on the identification of community-based mechanisms that generate the OBMs infrastructure, extending the current understanding of e-commerce and social commerce. Collapse

Topics: information technology infrastructure digital ecosystem electronic commerce anonymity computer crime

Methods: longitudinal research qualitative interview longitudinal case study triangulation mixed method

Theories: transaction cost economics