On the Importance of Domain-specific Explanations in AI-based Cybersecurity Systems (Technical Report)

With the availability of large datasets and ever-increasing computing power,there has been a growing use of data-driven artificial intelligence systems,which have shown their potential for successful application in diverse areas.However, many of these systems are not able to provide information about therationale behind their decisions to their users. Lack of understanding of suchdecisions can be a major drawback, especially in critical domains such as thoserelated to cybersecurity. In light of this problem, in this paper we make threecontributions: (i) proposal and discussion of desiderata for the explanation ofoutputs generated by AI-based cybersecurity systems; (ii) a comparativeanalysis of approaches in the literature on Explainable Artificial Intelligence(XAI) under the lens of both our desiderata and further dimensions that aretypically used for examining XAI approaches; and (iii) a general architecturethat can serve as a roadmap for guiding research efforts towards thedevelopment of explainable AI-based cybersecurity systems -- at its core, thisroadmap proposes combinations of several research lines in a novel way towardstackling the unique challenges that arise in this context.