Towards a Unified Model of Accountability Infrastructures
This work addresses the need for a consistent accountability framework in computer science, particularly for technical systems interacting with physical environments, but it is incremental as it builds on existing causality models.
The paper tackles the problem of differing accountability definitions across sciences by proposing a unified model for accountability infrastructures that captures safety, security, and privacy facets, leveraging formal causality models and demonstrating applicability to real-world use cases.
Accountability aims to provide explanations for why unwanted situations occurred, thus providing means to assign responsibility and liability. As such, accountability has slightly different meanings across the sciences. In computer science, our focus is on providing explanations for technical systems, in particular if they interact with their physical environment using sensors and actuators and may do serious harm. Accountability is relevant when considering safety, security and privacy properties and we realize that all these incarnations are facets of the same core idea. Hence, in this paper we motivate and propose a model for accountability infrastructures that is expressive enough to capture all of these domains. At its core, this model leverages formal causality models from the literature in order to provide a solid reasoning framework. We show how this model can be instantiated for several real-world use cases.