Epistemology for Cyber Security: A Controlled Natural Language Approach

In this paper we introduce a new Controlled Natural Language (CNL) known as “Noam”. It is used to express cyber security knowledge and for reasoning over it. The approach follows examples set by other domain-specific languages and constrained grammars, but is highly unusual due to its singular focus on cyber security. Like most CNLs Noam is both human-readable and machine-solvable, thus fulfilling important assurance requirements with respect to transparency and explainability. The language seeks to address a growing problem faced by security engineers and architects; namely, that their endeavours are constrained by the complexity and sheer interconnectedness of the systems they protect. This is further compounded by year-on-year vulnerability disclosure rates and diversification of the Tactics, Techniques and Procedures used by threat actors. Our approach is analogical in which the Noam CNL is used to construct a system model, instrument it with data from the real environment and apply functional programming techniques in order to ‘solve-for’ certain conditions of interest. The intention is to demonstrate the value of CNLs and semantic reasoning within cyber security, framed in the context of improving the information available to security engineers, architects and other decision-makers.