CW
Christian Schroeder de Witt
cs.AIcs.LGcs.CRcs.MAcs.CLstat.MLcs.CYcs.GTphysics.ao-phecon.GN
On Valency
published · living versionsW_b4fwehf7·v1 · currentpublished
Conflux: Preventing Privilege Escalation with Principal Contexts and System-Level Evaluation
with Raya Buckley
1 version
W_kscrjsq8·v1published
Preprints & journals
53 papers in the corpus · 2018–2026Inside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks2610.24135v1 · Magnus Sesodia, Juil Sock, Philip Torr et al.2026 · 0 citationsarXiv
AI Models Can Provably Hide Arbitrary Capabilities2610.13928v2 · Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas et al.2026 · 0 citationsarXiv
Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks2610.05640v1 · James Peters-Gill, Avi Semler, Henning Bartsch et al.2026 · 0 citationsarXiv
Weight Oracles: Reading Neural Network Weights with Language Models2610.07334v1 · Krishna Kabra, Constantin Venhoff, Christian Schroeder de Witt2026 · 0 citationsarXiv
Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks2610.05346v1 · Emanuele La Malfa, Saar Cohen, Gabriele La Malfa et al.2026 · 0 citationsarXiv
ORBIT: A Framework for Multi-Agent Safety and Security Evaluations2609.33102v1 · Ben Hagag, William L. Anderson, Srija Chakraborty et al.2026 · 0 citationsarXiv
MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning2609.33563v2 · Brandon Gary Kaplowitz, Osaze James Obahor, Christian Schroeder de Witt2026 · 0 citationsarXiv
Epsilon-Nash Equilibria in History-Dependent SA-MDPs2609.18829v2 · Brandon Gary Kaplowitz, Dominik Bohnet Zurcher, Akash Agrawal et al.2026 · 0 citationsarXiv
Spatial Generalization Tests for Machine Learning-based Weather Models to Assess Physical Consistency2607.20716v1 · Maren Hover, Milan Klower, Christian Schroeder de Witt et al.2026 · 0 citationsarXiv
Exploring the Cryptographic Limits of Transformer Networks2606.29389v1 · Stefan Domunco, Andis Draguns, Philip Torr et al.2026 · 0 citationsarXiv
Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems2606.28425v1 · Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa et al.2026 · 0 citationsarXiv
A Note on the Strategic Confinement Problem2606.09931v1 · Christian Schroeder de Witt2026 · 0 citationsarXiv
Architecture Matters for Multi-Agent Security2604.23459v1 · Ben Hagag, William L. Anderson, Christian Schroeder de Witt et al.2026 · 0 citationsarXiv
OpenSanctions Pairs: Large-Scale Entity Matching with LLMs2603.11051v2 · Chandler Smith, Magnus Sesodia, Friedrich Lindenberg et al.2026 · 0 citationsarXiv
Sensitivity Analysis for Climate Science with Generative Flow Models2511.00663v3 · Alex Dobra, Jakiw Pidstrigach, Tim Reichelt et al.2025 · 0 citationsarXiv
DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection2510.21638v1 · Tala Aljaafari, Varun Kanade, Philip Torr et al.2025 · 0 citationsarXiv
Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations2509.08646v1 · Ron F. Del Rosario, Klaudia Krawiecka, Christian Schroeder de Witt2025 · 1 citationarXiv
Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security Research2508.09815v1 · Klaudia Krawiecka, Christian Schroeder de Witt2025 · 0 citationsarXiv
Mitigating Goal Misgeneralization via Minimax Regret2507.03068v2 · Karim Abdel Sadek, Matthew Farrugia-Roberts, Usman Anwar et al.2025 · 0 citationsarXiv
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents2505.02077v2 · Christian Schroeder de Witt, Klaudia Krawiecka, Igor Krawczuk et al.2025 · 2 citationsarXiv
REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites2504.11543v2 · Divyansh Garg, Shaun VanWeelden, Diego Caples et al.2025 · 3 citationsarXiv
Mixture of Experts Made Intrinsically Interpretable2503.07639v1 · Xingyi Yang, Constantin Venhoff, Ashkan Khakzar et al.2025 · 0 citationsarXiv
AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence2503.00128v2 · Rilton Franzone, Magnus Sesodia, Alina Petrova et al.2025 · 0 citationsarXiv
Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems2502.19145v2 · Pierre Peigne-Lefebvre, Mikolaj Kniejski, Filip Sondej et al.2025 · 9 citationsarXiv
Multi-Agent Risks from Advanced AI2502.14143v1 · Lewis Hammond, Alan Chan, Jesse Clifton et al.2025 · 12 citationsarXiv
Humanity's Last Exam2501.14249v12 · Long Phan, Alice Gatti, Ziwen Han et al.2025 · 61 citationsarXiv
MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection2410.20140v3 · Kumud Lakara, Georgia Channing, Christian Rupprecht et al.2024 · 2 citationsarXiv
Efficient Dictionary Learning with Switch Sparse Autoencoders2410.08201v2 · Anish Mudide, Joshua Engels, Eric J. Michaud et al.2024 · 0 citationsarXiv
SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders2410.07456v1 · Constantin Venhoff, Anisoara Calinescu, Philip Torr et al.2024 · 0 citationsarXiv
Comparative Global AI Regulation: Policy Perspectives from the EU, China, and the US2410.21279v1 · Jon Chun, Christian Schroeder de Witt, Katherine Elkins2024 · 44 citationsarXiv
IDs for AI Systems2406.12137v3 · Alan Chan, Noam Kolt, Peter Wills et al.2024 · 0 citationsarXiv
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits2406.02619v2 · Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani et al.2024 · 1 citation38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Computing Low-Entropy Couplings for Large-Support Distributions2405.19540v1 · Samuel Sokota, Dylan Sam, Christian Schroeder de Witt et al.2024 · 0 citationsarXiv
Near to Mid-term Risks and Opportunities of Open-Source Generative AI2404.17047v2 · Francisco Eiras, Aleksandar Petrov, Bertie Vidgen et al.2024 · 2 citationsarXiv
The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games2402.01088v2 · Jake Levi, Chris Lu, Timon Willi et al.2024 · 0 citationsarXiv
Bayesian Exploration Networks2308.13049v4 · Mattie Fellows, Brandon Kaplowitz, Christian Schroeder de Witt et al.2023 · 1 citationarXiv
Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning2303.10733v1 · Yat Long Lo, Christian Schroeder de Witt, Samuel Sokota et al.2023 · 1 citationarXiv
Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learning2211.11043v1 · Dylan Radovic, Lucas Kruitwagen, Christian Schroeder de Witt et al.2022 · 5 citationsarXiv
Perfectly Secure Steganography Using Minimum Entropy Coupling2210.14889v4 · Christian Schroeder de Witt, Samuel Sokota, J. Zico Kolter et al.2022 · 12 citationsarXiv
Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks2207.10170v5 · Tim Franzmeyer, Stephen McAleer, Joao F. Henriques et al.2022 · 0 citationsarXiv
Generalized Beliefs for Cooperative AI2206.12765v1 · Darius Muglich, Luisa Zintgraf, Christian Schroeder de Witt et al.2022 · 1 citationarXiv
Biological Evolution and Genetic Algorithms: Exploring the Space of Abstract Tile Self-Assembly2205.15311v1 · Christian Schroeder de Witt2022 · 0 citationsarXiv
Model-Free Opponent Shaping2205.01447v2 · Chris Lu, Timon Willi, Christian Schroeder de Witt et al.2022 · 6 citationsarXiv
(Private)-Retroactive Carbon Pricing [(P)ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment2205.00666v1 · Yoshua Bengio, Prateek Gupta, Dylan Radovic et al.2022 · 1 citationarXiv
Mirror Learning: A Unifying Framework of Policy Optimisation2201.02373v11 · Jakub Grudzien Kuba, Christian Schroeder de Witt, Jakob Foerster2022 · 6 citationsarXiv
Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS2111.12197v1 · Christian Schroeder de Witt, Yongchao Huang, Philip H.S. Torr et al.2021 · 3 citationsarXiv
Communicating via Markov Decision Processes2107.08295v2 · Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl et al.2021 · 0 citationsarXiv
RainBench: Towards Global Precipitation Forecasting from Satellite Imagery2012.09670v1 · Christian Schroeder de Witt, Catherine Tong, Valentina Zantedeschi et al.2020 · 8 citationsarXiv
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?2011.09533v1 · Christian Schroeder de Witt, Tarun Gupta, Denys Makoviichuk et al.2020 · 183 citationsarXiv
Simulation-Based Inference for Global Health Decisions2005.07062v1 · Christian Schroeder de Witt, Bradley Gram-Hansen, Nantas Nardelli et al.2020 · 1 citationICML Workshop on Machine Learning for Global Health, Thirty-Seventh International Conference on Machine Learning (ICML 2020)
Career total: 65 works. 53 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.