Related papers: Understanding and Formalizing Accountability for C…

This chapter serves as an introduction to systems engineering focused on the broad issues surrounding realizing complex integrated systems. What is a system? We pose a number of possible definitions and perspectives, but leave open the…

In view of the growing complexity of modern software architectures, formal models are increasingly used to understand why a system works the way it does, opposed to simply verifying that it behaves as intended. This paper surveys approaches…

Recent advancements in AI applications to healthcare have shown incredible promise in surpassing human performance in diagnosis and disease prognosis. With the increasing complexity of AI models, however, concerns regarding their opacity,…

Contemporary concerns over the governance of technological systems often run up against narratives about the technical infeasibility of designing mechanisms for accountability. While in recent AI ethics literature these concerns have been…

Safety-critical Autonomous Systems require trustworthy and transparent decision-making process to be deployable in the real world. The advancement of Machine Learning introduces high performance but largely through black-box algorithms. We…

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretable. We describe a…

Artificial intelligence (AI) has huge potential to improve the health and well-being of people, but adoption in clinical practice is still limited. Lack of transparency is identified as one of the main barriers to implementation, as…

Causal Models are increasingly suggested as a means to reason about the behavior of cyber-physical systems in socio-technical contexts. They allow us to analyze courses of events and reason about possible alternatives. Until now, however,…

Explainable Artificial Intelligence (XAI) methods are intended to help human users better understand the decision making of an AI agent. However, many modern XAI approaches are unintuitive to end users, particularly those without prior AI…

A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not provide explanations for their predictions. Among others, the…

This paper uses a comprehensive review of the academic and professional literature in relation to accountability in the area of cloud computing service provision. It identifies four key conceptual factors that are necessary for an…

Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or…

Quality aspects such as ethics, fairness, and transparency have been proven to be essential for trustworthy software systems. Explainability has been identified not only as a means to achieve all these three aspects in systems, but also as…

Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment. Fulfilling this goal requires both that the explanations generated by these methods are…

Multi-agent cyberphysical systems enable new capabilities in efficiency, resilience, and security. The unique characteristics of these systems prompt a reevaluation of their security concepts, including their vulnerabilities, and mechanisms…

Providing meaningful and actionable explanations to end-users is a fundamental prerequisite for implementing explainable intelligent systems in the real world. Explainability is a situated interaction between a user and the AI system rather…

We describe and implement a policy language. In our system, agents can distribute data along with usage policies in a decentralized architecture. Our language supports the specification of conditions and obligations, and also the…

Recently, requirements for the explainability of software systems have gained prominence. One of the primary motivators for such requirements is that explainability is expected to facilitate stakeholders' trust in a system. Although this…

Explainable models in Artificial Intelligence are often employed to ensure transparency and accountability of AI systems. The fidelity of the explanations are dependent upon the algorithms used as well as on the fidelity of the data. Many…