Visible to the public Explainability in threat assessment with evidential networks and sensitivity spaces

TitleExplainability in threat assessment with evidential networks and sensitivity spaces
Publication TypeConference Paper
Year of Publication2020
AuthorsKowalski, P., Zocholl, M., Jousselme, A.-L.
Conference Name2020 IEEE 23rd International Conference on Information Fusion (FUSION)
Date Publishedjul
Keywordsartificial intelligence, belief functions, cables (electric), Cognition, Communication cables, Cost accounting, Damage Assessment, evidence theory, evidential networks, Explainability, explanation abilities, graphical models, inference mechanisms, information fusion, marine communication, marine engineering, opportunity-capability-intent threat model, probability, pubcrawl, resilience, Resiliency, Sensitivity, sensitivity spaces, sensor fusion, source quality model, telecommunication security, Threat Assessment, Uncertainty, uncertainty handling, underwater acoustic communication, Underwater cables, underwater communication cables, vessel
AbstractOne of the main threats to the underwater communication cables identified in the recent years is possible tampering or damage by malicious actors. This paper proposes a solution with explanation abilities to detect and investigate this kind of threat within the evidence theory framework. The reasoning scheme implements the traditional “opportunity-capability-intent” threat model to assess a degree to which a given vessel may pose a threat. The scenario discussed considers a variety of possible pieces of information available from different sources. A source quality model is used to reason with the partially reliable sources and the impact of this meta-information on the overall assessment is illustrated. Examples of uncertain relationships between the relevant variables are modelled and the constructed model is used to investigate the probability of threat of four vessels of different types. One of these cases is discussed in more detail to demonstrate the explanation abilities. Explanations about inference are provided thanks to sensitivity spaces in which the impact of the different pieces of information on the reasoning are compared.
Citation Keykowalski_explainability_2020