BIROn - Birkbeck Institutional Research Online

    Forecasting cyber threats and pertinent mitigation technologies

    Almahmoud, Zaid and Yoo, Paul and Damiani, E. and Choo, K.-K.R. and Yeun, C.Y. (2025) Forecasting cyber threats and pertinent mitigation technologies. Technological Forecasting and Social Change 210 , ISSN 0040-1625.

    This is the latest version of this item.

    [img]
    Preview
    Text
    54443.pdf - Published Version of Record
    Available under License Creative Commons Attribution.

    Download (2MB) | Preview

    Abstract

    Geopolitical instability is exacerbating the risk of catastrophic cyber-attacks striking where defences are weak. Nev- ertheless, cyber-attack trend forecasting predominantly relies on human expertise, which is susceptible to subjectivity and potential bias. As a solution, we have recently presented a novel study that harnesses machine learning for long-term cyber-attack forecast- ing. Building upon this groundwork, our research advances to the next level, by predicting the disparity between cyber-attack trends and the trend of the relevant alleviation technologies. Our predictive analysis aims to offer strategic insights for the decision of investment in cyber security technologies. It also provides a sound foundation for the strategic decisions of national defence agencies. To achieve this objective, we have expanded our dataset, which now encompasses records spanning 42 distinct cyber-attack types and various related features, alongside data concerning the trends of 98 pertinent technologies, dating back to 2011. The dataset features were meticulously curated from diverse sources, including news articles, blogs, government advisories, as well as from platforms such as Elsevier, Twitter, and Python APIs. With our comprehensive dataset in place, we construct a graph that elucidates the intricate interplay between cyber threats and the development of pertinent alleviation technologies. To forecast the graph, we introduce a novel Bayesian adaptation of a recently proposed graph neural network model, which effectively captures and predicts these trends. We further demonstrate the efficacy of our proposed features in this context. Furthermore, our study extends its horizon by generating future data projections for the next three years, encompassing forecasts for the evolving graph, including predictions of the gap between cyber-attack trends and the trend of the associated technologies. As a consequential outcome of our forecasting efforts, we introduce the concept of “alleviation technologies cycle”, delineating the key phases in the life cycle of 98 technologies. These findings serve as a foundational resource, offering valuable guidance for future investment and strategic defence decisions within the realm of cyber security related technologies.

    Metadata

    Item Type: Article
    Keyword(s) / Subject(s): Cyber threat trend forecasting, Mitigation technology trend forecasting, Alleviation technology trend forecasting, Proactive approach, Big data analytics, Graph machine learning, Technology cycle
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Depositing User: Paul Yoo
    Date Deposited: 04 Nov 2024 14:46
    Last Modified: 04 Nov 2024 14:49
    URI: https://eprints.bbk.ac.uk/id/eprint/54443

    Available Versions of this Item

    • Forecasting cyber threats and pertinent mitigation technologies. (deposited 04 Nov 2024 14:46) [Currently Displayed]

    Statistics

    Activity Overview
    6 month trend
    14Downloads
    6 month trend
    52Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item
    Edit/View Item