Abstract
In 2021, the UK's National AI Strategy recommended that UK Government’s official Public Sector Guidance on AI Ethics and Safety be transformed into a series of practice-based workbooks. The result is the AI Ethics and Governance in Practice Programme. This series of eight workbooks provides end-to-end guidance on how to apply principles of AI ethics and safety to the design, development, deployment, and maintenance of AI systems. It provides public sector organisations with a Process Based Governance (PBG) Framework designed to assist AI project teams in ensuring that the AI technologies they build, procure, or use are ethical, safe, and responsible.
This is the sixth workbook in the series, exploring AI Safety in Practice.
Project teams frequently engage in tasks pertaining to the technical safety and sustainability of their AI projects. In doing so, they need to ensure that their resultant models are reproducible, robust, interpretable, reliable, performant, and secure. The issue of AI safety is of paramount importance, because possible failures have the potential to produce harmful outcomes and undermine public trust. This work of building safe AI outputs is an ongoing process requiring reflexivity and foresight. To aid teams in this, the workbook introduces the core components of AI Safety (reliability, performance, robustness, and security), and helps teams develop anticipatory and reflective skills which are needed to responsibly apply these in practice.
You can download a summary of the workbook below, alongside the full workbook.