The Human Factor in AI Red Teaming: Perspectives from Social and Collaborative Computing

TL;DR

This paper explores the human factors involved in AI red teaming, highlighting challenges like bias, mental health, and the need for community-driven research to improve practices and address potential harms.

Contribution

It provides a conceptual overview of human-related issues in AI red teaming and calls for further research integrating social and collaborative computing perspectives.

Findings

Identifies biases and blindspots in red teaming practices

Highlights psychological impacts on red teamers

Calls for community efforts to address ethical and mental health challenges

Abstract

Rapid progress in general-purpose AI has sparked significant interest in "red teaming," a practice of adversarial testing originating in military and cybersecurity applications. AI red teaming raises many questions about the human factor, such as how red teamers are selected, biases and blindspots in how tests are conducted, and harmful content's psychological effects on red teamers. A growing body of HCI and CSCW literature examines related practices-including data labeling, content moderation, and algorithmic auditing. However, few, if any have investigated red teaming itself. Future studies may explore topics ranging from fairness to mental health and other areas of potential harm. We aim to facilitate a community of researchers and practitioners who can begin to meet these challenges with creativity, innovation, and thoughtful reflection.