Open Challenges in Multi-Agent Security by Christian Schroeder de Witt скачать в хорошем качестве

Open Challenges in Multi-Agent Security by Christian Schroeder de Witt

This lecture was delivered at the 2025 Cooperative AI Summer School. For more information, please visit: https://www.cooperativeai.com/post/co... Christian Schroeder de Witt is a Research Fellow and Stipendiary Lecturer at the University of Oxford specialising in AI security and multi-agent learning. His current research interests include high-dimensional anomaly detection, LLM reasoning, and multi-agent LLM post-training in the context of emerging abilities. Christian's contributions to undetectable threats, perfectly-secure steganography, and learning in multi-agent systems have advanced foundational AI research and garnered coverage in Quanta Magazine and Scientific American. His work also reached 2-5 million viewers on BBC Studios. He's been invited to speak on AI policy at prestigious venues including the 2023 Munich Security Forum and the 2025 Schmidt Futures x Palo Alto Networks x RAND Corporation Agent Security Convening in Santa Clara. He also collaborates with leading research institutions including Google DeepMind, Microsoft, OpenAI, and Lawrence Livermore National Laboratory. As an educator, he's developed the world’s first doctoral-level course on the Frontiers of Cooperative AI.