collaborators

7 papers

cs.CR2026

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa +1

Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defence to these collusion attempts…

cs.GT2026

A Note on the Strategic Confinement Problem

Christian Schroeder de Witt

Lampson's confinement problem asks how to prevent a program that processes confidential information from leaking it to a third party. We introduce the strategic confinement problem…

cs.AI2026

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

Aaron Rose, Carissa Cullen, Sahar Abdelnabi +3

As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on…

cs.AI2026

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

Usman Anwar, Julianna Piskorz, David D. Baek +6

Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to de…

cs.MA2026

Architecture Matters for Multi-Agent Security

Ben Hagag, William L. Anderson, Christian Schroeder de Witt +1

Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that d…

cs.CR2025

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations

Ron F. Del Rosario, Klaudia Krawiecka, Christian Schroeder de Witt

As Large Language Model (LLM) agents become increasingly capable of automating complex, multi-step tasks, the need for robust, secure, and predictable architectural patterns is par…