Christian Schroeder de Witt

Christian Schroeder de Witt

AI & Security Research | Strategy

University of Oxford

I am a Research Fellow and Stipendiary Lecturer at the University of Oxford specializing in AI security and multi-agent learning. My work focuses on developing frameworks to ensure the trustworthiness, safety, and security of advanced AI systems by building on deep epistemic, information-theoretic, and game-theoretic foundations.

My research addresses critical challenges in distributed artificial intelligence, drawing on my background in theoretical physics, computer science, and complex systems science. This interdisciplinary approach led to the establishment of Multi-Agent Security in 2023, a field addressing emerging safety and security concerns in systems of adaptive AI agents.

My contributions to undetectable threats, perfectly-secure steganography, and learning in multi-agent systems have advanced foundational AI research, garnering coverage in Quanta Magazine and Scientific American. Current research interests include high-dimensional anomaly detection, LLM reasoning, and multi-agent LLM post-training in the context of emerging abilities.

My work on misinformation with Adobe Research and BBC Verify recently brought me into BBC News studios, reaching 2-5 million viewers. I’ve 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. I also collaborate with leading research institutions including Google DeepMind, Microsoft, OpenAI, and Lawrence Livermore National Laboratory.

As an educator, I’ve developed the world’s first doctoral-level course on the Frontiers of Cooperative AI and serve as a Stipendiary Lecturer in Computer Science at St Catherine’s College, Oxford, where I teach undergraduate tutorial groups.

Supervision

Please contact me if you are interested in working with me. I supervise undergraduate projects, master’s theses, and co-supervise Ph.D. projects in a wide range of topics in both deep multi-agent learning,
information security, and foundational AI.

Some of my current students and mentees include:

  • Julia Karbing (DPhil student funded by OpenPhil, CAIS, and a Cooperative AI Foundation PhD Fellowship)
  • Sumeet Motwani (DPhil student funded by Eric Schmidt, and a Cooperative AI Foundation PhD Fellowship)
  • Constantin Venhoff (DPhil student funded funded by OpenAI, formerly MSc Advanced Computer Science student with me)
  • Tala Jafari (Research Assistant and an incoming Ph.D. student at MIT, formerly an MSc Advanced Computer Science student with me)

Some of my past students and mentees include:

  • Linas Nasvytis (MSc Statistics student, formerly a Research Fellow at Harvard University (Psychology and ML) and now a Ph.D. student at Stanford)
  • Yat Long Lo (MSc Computer Science student - winner of Tony Hoare Prize for best MSc Thesis in Computer Science, formerly Dyson Robot Learning Lab now Amazon AGI)
  • Khaulat Abdulhakeem (mentee, now MS Education Data Science at Stanford University)
  • Eshaan Agrawal (mentee and collaborator, formerly ORISE Fellow at the Department of Energy and now at McKinsey)
Interests
  • Multi-Agent Learning
  • Information Security
  • Reinforcement Learning
  • Agent-Based Modeling
  • Cooperative AI
Education
  • DPhil (PhD) in Engineering Science, Jan 2017 - Nov 2021

    University of Oxford, St. Catherine's College

  • MSc Computer Science - Distinction, Oct 2012 - Sep 2013

    University of Oxford, Kellogg College

  • MPhys (Physics) - First, Oct 2008 - Jul 2012

    University of Oxford, Exeter College

Recent News

All news»

[17/03/25] Super excited to receive a generous grant on the Foundations of Multi-Agent Security by the Foresight Institute

[17/02/25] Honoured to be invited to give the opening keynote on Multi-Agent Security at the Schmidt Futures x Palo Alto Networks x RAND Corporation Agentic Security Convening (Santa Clara, CA)

[16/02/25] Honoured to serve as a Lead Reviewer for Deutsche Forschungsgemeinschaft’s flagship Cluster of Excellence and Emmy Noether grant programs

[15/02/25] Congratulations to my students Julia Karbing and Sumeet Motwani for winning ultra-competitive Cooperative AI Foundation Ph.D. Fellowships (ca. 8% acceptance rate)

[17/08/24] I gave expert testimony on AI and disinformation live in-studio on BBC News - AI Decoded in front of 2-5 million viewers!

Experience

 
 
 
 
 
University of Oxford
Research Fellow (Department of Engineering Science)
Jan 2022 – Present Oxford, United Kingdom
Since 2024 working with Torr Vision Group (TVG). Funded by RAEng and UK Gov. Formerly with FLAIR (Prof. Jakob Foerster). Chair of AI4ABM community.
 
 
 
 
 
University of Oxford
Stipendiary Lecturer in Computer Science (St Catherine’s College,)
Oct 2024 – Present Oxford, United Kingdom
Teaching undergraduate tutorials at St Catherine’s College Oxford.
 
 
 
 
 
Schmidt Futures
International Strategy Forum | Fellow
Jun 2022 – Present NY, remote
Selected to work with the European Council on Foreign Affairs as one of Europe’s top 30 under 35 rising strategists in technology and geopolitics. Nominated by the Vice-Chancellor of the University of Oxford as “one of the most exemplar individuals [she has] encountered in the past ten years.”
 
 
 
 
 
MILA (Quebec)
Visiting Researcher
Aug 2022 – Present Montreal, remote
Working with Turing-Award winner Prof. Yoshua Bengio.
 
 
 
 
 
MenschDanke Group
Head of Engineering
Mar 2014 – Sep 2014 Berlin (DE)
Interim management of a team of 4 in-house developers. Full-stack development (LAMP, MEAN) and agile project management (Scrum) at Germany’s then third-largest e-Commerce (deals) venture. Negotiated long-term hardware contracts and supervised live product migrations.

Honors, Awards & Grants

Foresight Institute
Foresight Institute grant ($124k)
Awarded for work on the foundations of Multi-Agent Security
Future of Life Institute
EU GPAI Code of Practice policy grant ($10k)
Awarded for Policy contributions to the EU GPAI Code of Practice
Schmidt Futures
Schmidt Futures Virtual Institute on AI and Grand Strategy grant ($133k)
Awarded for work on AI and National security (in collaboration with BBC OSINT, and Bergen University)
OpenAI
OpenAI Superalignment Fast Grant ($327k)
Awarded for work on interpretability and weak-to-strong generalization
As an official Co-Editor, I helped with Prof. Jakob Foerster’s ERC Starter Grant.
I was awarded an EPSRC IAA Doctoral Impact Fund Award (£30k) for my DPhil thesis.
I reached the global finals (stage 4/4) of this ultra-competitive fellowship with a NASA-backed proposal on mesospheric geoengineering research.
De-Facto PI of a series of grant arising out of my ongoing personal long-term relationship with Armasuisse Science+Technology (Zurich, CH). Attracted > £190k since 2021.
Awarded for climate science research.
In Germany the top 0.5% of high school graduates get selected for funding by the German Academic Foundation (also known as German Merit Foundation).
Awarded a special prize at Brandon Festival of the Arts, and two first prizes.

Publications (Selected)

Quickly discover relevant content by filtering publications.
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
We introduce the setting of secret collusion among AI agents.
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
Communicating via Markov Decision Processes
We propose a perfectly-secure steganography algorithm for arbitrary covertext distributions.
Communicating via Markov Decision Processes
Amortized Rejection Sampling in Universal Probabilistic Programming
In this paper we develop a new and efficient amortized importance sampling estimator for rejection sampling.
Amortized Rejection Sampling in Universal Probabilistic Programming
Discovered Policy Optimisation
In this paper we explore the Mirror Learning space by meta-learning a “drift” function.
Discovered Policy Optimisation
Rainbench: Towards Data-Driven Global Precipitation Forecasting from Satellite Imagery
We introduce RainBench, a new multi-modal benchmark dataset for data-driven precipitation forecasting.
Rainbench: Towards Data-Driven Global Precipitation Forecasting from Satellite Imagery
FACMAC: Factored Multi-Agent Centralised Policy Gradients
We propose multi-agent common knowledge reinforcement learning (MACKRL).
FACMAC: Factored Multi-Agent Centralised Policy Gradients
Multi-Agent Common Knowledge Reinforcement Learning
We propose multi-agent common knowledge reinforcement learning (MACKRL).
Multi-Agent Common Knowledge Reinforcement Learning
The Starcraft Multi-Agent Challenge
We propose the StarCraft Multi-Agent Challenge (SMAC) to measure real progress in MARL.
The Starcraft Multi-Agent Challenge

Outreach

Multi-Agent Security Community (MASEC)
I co-founded the ABM community, and, as its Chair, am the main organiser of a NeurIPS 2023 workshop. We have received sponsorship from GovAI.
Multi-Agent Security Community (MASEC)
AI for Agent-Based Modelling Community (AI4ABM)
I co-founded the ABM community, and, as its Chair, have been the main organiser of workshops at ICML 2022 (sponsored by Improbable), and ICLR 2023 (sponsored by JP Morgan). Agent-Based Modelling (ABM) has seen increasing interest across various disciplines, ranging from economics and epidemiology to cybersecurity, social sciences, and climate policy.
AI for Agent-Based Modelling Community (AI4ABM)

Press

AI Could Smuggle Secret Messages in Memes
A new technique for sending hidden messages is mathematically proven to escape detection
AI Could Smuggle Secret Messages in Memes
AI-Generated Steganography
New research suggests that AIs can produce perfectly secure steganographic images
AI-Generated Steganography
Secret Messages Can Hide in AI-Generated Media
In steganography, an ordinary message masks the presence of a secret communication. Humans can never do it perfectly, but a new study shows it’s possible for machines.
Secret Messages Can Hide in AI-Generated Media
New Breakthrough enables Perfectly Secure Digital Communications
A team led by University of Oxford researchers has achieved a breakthrough in secure communications by developing an algorithm that conceals sensitive information so effectively that it is impossible to detect that anything has been hidden.
New Breakthrough enables Perfectly Secure Digital Communications
“Perfectly secure” algorithm could aid spread of free speech
A new algorithm has solid implications for information security, data compression and storage, but the real benefits could be seen among vulnerable groups
“Perfectly secure” algorithm could aid spread of free speech
Steganography algorithms enable ‘perfectly secure’ information
An algorithm has been developed that conceals sensitive information so effectively that it is impossible detect that anything has been hidden.
Steganography algorithms enable ‘perfectly secure’ information
Climate Change: the Case for Artificial Intelligence
A recent Intergovernmental Panel on Climate Change (IPCC) report has made it very clear that drastic, immediate cuts to greenhouse gas emissions are needed to limit global warming to 1.5° C. With the absence of a technological silver bullet, this requires rapid changes at unprecedented scale across all sectors of the global economy. Just as the climate clock is ticking, technological breakthroughs in machine learning algorithms (ML) and robotic control have turned artificial intelligence (AI) into a powerful new agent of change.
Climate Change: the Case for Artificial Intelligence

Blog

*
The Sweeping Powers of Model-Free Opponent Shaping
Opponent shaping is a powerful technique that can be used to induce cooperation, but also to extort others. New, model-free techniques exemplify this approach and provide lessons for the development of Cooperative AI.
The Sweeping Powers of Model-Free Opponent Shaping

Consulting

Contact me here for 1:1 consulting on topics related to my past industry research experiences and/or my current research in academia.

    Industry Collaboration

    Contact me here if you would like me to complete an end-to-end industry research project. For reference, projects I take on typically lead to patents and/or papers.

      Speaker/Moderator Request

      Contact me here if you would like me to speak at or moderate an event such as a panel discussion, podcast episode, or interview.

        Other

        Contact me by email for a purpose other than the ones listed above.