Muted registers: A feminist intersectional (re)figuring of red-teaming

About the Fellowship

Led by Dr Alex Taylor at the University of Edinburgh and partnered with Microsoft Research, this fellowship seeks to understand the practice of red-teaming to produce actionable insights for policy and governance. The focus is on collaboration, dissemination of tools, and broad public engagement.

As an emerging practice, fundamental questions remain about red-teaming and its use in building safe and responsible generative AI systems. Key inquiries include: Who works in these ‘red teams’? What conditions do red-teams operate in, and what are the lasting individual and structural consequences of these conditions? What taken-for-granted logics, norms, and values are applied in the drive to mitigate harms and improve AI safety?

Responsibilities

This fellowship will pursue a deeper understanding of and critical engagement with red-teaming to inform both organisational governance and national policies linked to Responsible AI. Grounded research will draw on scholarship in the humanities, philosophy, Black Studies, and English literature—loosely grouped under the umbrella term feminist intersectionality—to make two analytical contributions:

• Provide a means to think with/against the harms both targeted by and arising in red-teaming. Feminist intersectionality will enable a critical examination of red teams’ exposure to trauma in efforts to ‘responsibilize’ AI, and how this risks displacing harm and amplifying it in wider sociotechnical systems and structures. A central question motivating this analysis will be: “What are the individual and structural consequences of displacing harm through red-teaming, and can these consequences amount to a responsible practice?”
• Be motivated by imaginative and hopeful ways of responding to situated, ethical, and epistemic challenges. This perspective will be driven by a feminist intersectionality committed to listening to others and always provoked by the expansive question, ‘What other worlds are possible?’ With respect to red-teaming, this involves attuning to how harm is reduced to a technical problem that can be neutralised by people working in difficult conditions. The research will gather stories and accounts of the work in these conditions to foreground ‘muted registers’ (Hustak & Myers 2012)—those stories we don’t often hear or that are elided. Such registers will redirect attention in Responsible AI away from neutralising harms and toward genuinely engaging with and empowering those who feel the effects of irresponsibility in AI.

This project is committed to impacting governance within commercial organisations and national policy-making. The fellowship’s programme of work is designed to collaborate closely with Microsoft Research (MSR) and the BRAID team to translate findings for governance and policy audiences, and to develop new ways of improving working conditions for those routinely confronted with the harms reproduced by generative AI.

Tags: Alex Taylor, Microsoft Research, The University of Edinburgh

Contact: braid@ed.ac.uk