Multi-aspect rule-based AI: Methods, taxonomy, challenges and directions towards automation, intelligence and transparent cybersecurity modeling for critical infrastructures

Abstract

Critical infrastructure (CI) typically refers to the essential physical and virtual systems, assets, and services that are vital for the functioning and well-being of a society, economy, or nation. However, the rapid proliferation and dynamism of today’s cyber threats in digital environments may disrupt CI functionalities, which would have a debilitating impact on public safety, economic stability, and national security. This has led to much interest in effective cybersecurity solutions regarding automation and intelligent decision-making, where AI-based modeling is potentially significant. In this paper, we take into account “Rule-based AI” rather than other black-box solutions since model transparency, i.e., human interpretation, explainability, and trustworthiness in decision-making, is an essential factor, particularly in cybersecurity application areas. This article provides an in-depth study on multi-aspect rule based AI modeling considering human interpretable decisions as well as security automation and intelligence for CI. We also provide a taxonomy of rule generation methods by taking into account not only knowledge-driven approaches based on human expertise but also data-driven approaches, i.e., extracting insights or useful knowledge from data, and their hybridization. This understanding can help security analysts and professionals comprehend how systems work, identify potential threats and anomalies, and make better decisions in various real-world application areas. We also cover how these techniques can address diverse cybersecurity concerns such as threat detection, mitigation, prediction, diagnosis for root cause findings, and so on in different CI sectors, such as energy, defence, transport, health, water, agriculture, etc. We conclude this paper with a list of identified issues and opportunities for future research, as well as their potential solution directions for how researchers and professionals might tackle future generation cybersecurity modeling in this emerging area of study.