Towards a Taxonomy for the Opacity of AI Systems

Abstract

The research program of eXplainable AI (XAI) has been developed with the aim of providing tools and methods for reducing opacity and making AI systems more humanly understandable. Unfortunately, the majority of XAI scholars actually classify a system as more or less opaque by confronting it with traditional AI systems such as linear regression models or rules-based systems, which are usually assumed to be the prototype of transparent systems. In doing so, the concept of opacity remains unexplained. To overcome this issue, we view opacity as a concept whose meaning depends on the context of application, and on the purposes and characteristics of its users. Based on this, in this work, we distinguish between access opacity, link opacity and semantic opacity, hence providing the groundwork for a taxonomy of the concept of opacity for AI systems.

(Un)making AI Magic: A Design Taxonomy

“…They embody a level of complexity that is hard for experts -let alone the general public -to grasp [18]. This complexity renders AI algorithms inherently opaque [5,74,96], in their structure, their internal patterns, and their links to the world [39]: "when a computer learns and consequently builds its own representation of a classification decision, it does so without regard for human comprehension" [16]. This gap of comprehension is the space through which magic flows [4], opening space for ambiguity and unexpectedness, and leading to truly enchanting experiences [85].…”