# Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour

## TL;DR

This paper proposes a method to ensure AI systems operate within explicit moral bounds by monitoring their inputs and outputs, enhancing transparency, trust, and compliance with human values.

## Contribution

It introduces a 'glass-box' approach that maps moral values into verifiable norms, allowing for system verification across diverse AI architectures.

## Key findings

- Enables verification of AI systems against moral norms
- Improves explainability of AI moral behavior
- Supports compliance checking with different moral interpretations

## Abstract

Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to improve people's lives, then people must be able to trust AI, which means being able to understand what the system is doing and why. Even though transparency is often seen as the requirement in this case, realistically it might not always be possible or desirable, whereas the need to ensure that the system operates within set moral bounds remains. In this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a "glass box" around the system by mapping moral values into explicit verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value. The focus on inputs and outputs allows for the verification and comparison of vastly different intelligent systems; from deep neural networks to agent-based systems. The explicit transformation of abstract moral values into concrete norms brings great benefits in terms of explainability; stakeholders know exactly how the system is interpreting and employing relevant abstract moral human values and calibrate their trust accordingly. Moreover, by operating at a higher level we can check the compliance of the system with different interpretations of the same value. These advantages will have an impact on the well-being of AI systems users at large, building their trust and providing them with concrete knowledge on how systems adhere to moral values.