Christian Schroeder de Witt

Dr. Christian Schroeder de Witt is a pioneering researcher at the University of Oxford whose work has defined the emerging field of multi-agent security. He is known for solving the 25-year open problem of perfectly secure steganography, which was recognized as a “Biggest Discovery of the Year” by Quanta Magazine. As PI of the Oxford Witt Lab (wittlab.ai), Christian leads a global anticipatory research agenda on securing systems of AI agents, humans, and institutions against undetectable and systemic threats, bridging rigorous mathematical theory with real-world impact. He has raised over $2.2 million as PI from the Royal Academy of Engineering, Schmidt Futures, Foresight Institute, Open Philanthropy, and others, and serves as a trusted expert for organizations including RAND, BBC News, and the UK government. Christian’s anticipatory research shapes the future of AI safety, cybersecurity, and global technology policy.

AI2050 Project

In the coming years, powerful AI systems will work together, creating new security risks that may be practically infeasible—or even, in some regimes, theoretically impossible—to detect, undermining security approaches based on anomaly detection alone. Schroeder de Witt’s project explores how AI agents might exploit concealed capabilities, secretly share hidden messages, or carry out invisible attacks—and how to prevent them through secure-by-design architectures. The program blends theory and experiments to establish formal detectability limits and develop practical mitigations, including hardened interaction protocols, evaluation and red-team playbooks, and design patterns for resilient multi-agent systems. By acting now, the project aims to keep deployment practice ahead of emerging multi-agent threats.