Vulnerability Time Series Forecasting: A Comparative Study of Hierarchical and Non-Hierarchical Approaches
Open Access
- 28 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 58658-58670
Abstract
Cybersecurity has become an increasing priority in large organizations due to the rapid evolution of digital threats. With increasingly sophisticated attacks, vulnerability management emerges as one of the main strategies to protect systems and data. However, the complexity and dynamics of threats make management processes challenging, requiring efficient and adaptable approaches. Artificial Intelligence (AI) and Machine Learning (ML) are promising tools to anticipate and mitigate these threats, offering predictive capabilities based on historical data. This article proposes the use of time series in a hierarchical manner for the forecasting of vulnerabilities in systems. The proposed methodology aims to deal with the complexity of the data, allowing a hierarchical structure to understand and capture the interdependencies and patterns among different levels more completely. The evaluation is carried out with different ML models, such as LSTM, RNN, MLP, among others, comparing the performance of hierarchical and non-hierarchical approaches. The results indicate that, in a hierarchical structure, especially LSTM, shows superior performance in vulnerability forecasting. However, in some scenarios, when using reconcilers, models like N-BEATS also demonstrate good results.Keywords
Funding Information
- Article Processing Charge funded by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—CAPES (00x0ma614)
This publication has 17 references indexed in Scilit:
- A cyber risk prediction model using common vulnerabilities and exposuresExpert Systems with Applications, 2023
- HiRAM: A hierarchical risk assessment model and its implementation for an industrial Internet of Things in the cloudSoftware Testing, Verification and Reliability, 2023
- A holistic and proactive approach to forecasting cyber threatsScientific Reports, 2023
- Explainable artificial intelligence for cybersecurity: a literature surveyAnnals of Telecommunications, 2022
- Machine learning applications in hierarchical time series forecasting: Investigating the impact of promotionsInternational Journal of Forecasting, 2022
- Model selection in reconciling hierarchical time seriesMachine Learning, 2022
- Internet of Things Applications, Security Challenges, Attacks, Intrusion Detection, and Future Visions: A Systematic ReviewIEEE Access, 2021
- Design and Development of Industrial Cyber-Physical System Testbed2020
- An investigation of aggregate variable time series forecast strategies with specific subaggregate time series statistical correlationComputers & Operations Research, 1999
- Cognitron: A self-organizing multilayered neural networkBiological Cybernetics, 1975