Designing Accountable Systems

Abstract

Accountability is an often called for property of technical systems. It is a requirement for algorithmic decision systems, autonomous cyber-physical systems, and for software systems in general. As a concept, accountability goes back to the early history of Liberalism and is suggested as a tool to limit the use of power. This long history has also given us many, often slightly differing, definitions of accountability. The problem that software developers now face is to understand what accountability means for their systems and how to reflect it in a system's design. To enable the rigorous study of accountability in a system, we need models that are suitable for capturing such a varied concept. In this paper, we present a method to express and compare different definitions of accountability using Structural Causal Models. We show how these models can be used to evaluate a system's design and present a small use case based on an autonomous car.

arXiv commentaccepted for publication at the ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) 2021

References in corpus (6)

• Explaining Explanations in AI
• A Modification of the Halpern-Pearl Definition of Causality
• Identifying Causal Effects with the R Package causaleffect
• From Checking to Inference: Actual Causality Computations as Optimization Problems
• Counting Markov Equivalence Classes by Number of Immoralities
• Extending Causal Models from Machines into Humans

Cited by in corpus (3)

• Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning
• Making the Unaccountable Internet: The Changing Meaning of Accounting in the Early ARPANET
• Being Accountable is Smart: Navigating the Technical and Regulatory Landscape of AI-based Services for Power Grid