scaling trustcommunity

Before finalising the Scaling Trust programme, we ran a pre-programme discovery call : a round of short, fully open-source research projects — three months, up to £20,000 each — to sharpen the programme’s direction and start building its community.

Teams worked across four tracks: systematising knowledge (from “nature cryptography” to multi-agent security for embodied agents), prototyping agentic coordination challenges, analysing the ethics and risks of multi-agent systems, and growing the community in the UK and beyond.

PactMulti-agent

A choreographic language bringing game theory to agent protocol design.

Kiran Gopinathan, Jack Feser, Michelangelo Naim, Zenna Tavares, Eli Bingham · Basis AI PaperBlogTalk

Profit is the Red TeamMulti-agent

A profit-driven adversary that red-teams agents through economic interaction.

Davide Crapis, Shouqiao Wang, Marcello Politi, Samuele Marro PaperTalk

Mechanism Design Is Not EnoughMulti-agent

Incentives aren't enough — agents need intrinsic prosocial preferences to cooperate.

Samuele Marro, Angelo Huang, Emanuele La Malfa · Institute of Decentralised AI PaperARIA insightTalk

AgentMatrixMulti-agent

Automated benchmarking and securing of AI-agent interaction protocols.

Marios Kogias · Imperial College London CodeTalk

NDAI ZoneFoundations

Can LLMs assess security evidence inside trusted execution environments?

Enrico Bottazzi, Pia Park PaperTalk

Diagrammatic foundations for trustFoundations

Category-theoretic, substrate-independent foundations for cryptographic trust.

Martti Karvonen, Robin Piedeleu, Fabio Zanasi · UCL Report (PDF)Talk

Living ProofFoundations

Mechanobiological cryptography: grounding trust in the physical organisation of living cells, where security rests on the non-invertibility of biological state transitions rather than computational hardness.

Kimia Witte · University of Strathclyde PaperTalk

Verifiable supply-chain dataFoundations

Cryptographic methods for supply-chain data integrity.

Martin Kleppmann · University of Cambridge Talk

Physical-Layer TrustCyber-physical

Measuring embodied interaction and trust in robot swarms.

Suet Lee, Aron Kisdi · Autodiscovery Write-upTalk

LabTrust-GymCyber-physical

A benchmarking environment for trustworthy AI-agent interactions in the lab.

Matéo Petel · Stanford University CodeTalk

Trusted Molecular MemoryCyber-physical

Trust in hybrid biological–computational systems.

Larissa Pschetz, Raphael Kim, Thomas Heinis · University of Edinburgh Talk

Untrustworthy Things EverywhereCyber-physical

Securing cyber-physical industrial infrastructure.

Awais Rashid, Joseph Gardiner, Louise Evans · Hacktonics Talk

Who am I?Cyber-physical

Identity and authentication for physically-embodied AI agents.

Mary Maller, Oded Goffer, Charlotte Léonard, Aurélien Nicolas · Inversed Tech Talk

SoTA communityCommunity

Building a UK community around cyber-physical security.

Jamie Croucher, Matvey Boguslavskiy · Society of Technological Advancement TalkEventUnlocking cyber-physical potentialMineTrust