Specify trust before testing it
Each project states what a system must protect, who can challenge it, and which failures count.
About the lab
Trusted Agentic Systems Lab
How can autonomous systems be trusted when they act across code, markets, and physical infrastructure?
Trust Lab studies how autonomous and multi-agent systems can be secured, audited, and kept resilient when they act through software services, smart contracts, digital markets, and physical infrastructure.
The research connects agent assurance with blockchain security, cyber-physical systems, and requirements engineering. It treats trust as a property that must be specified, tested, and revised when systems fail.
Trust Lab is a member-led virtual research group within REQS Labs. It is not a separately incorporated institute or an employer; members retain their independent institutional affiliations.
Operating principles
What the structure protects
Study systems under pressure
Security claims matter only after adversarial conditions, partial failure, and conflicting incentives enter the model.
Connect methods across fields
Agent assurance draws on security, requirements engineering, distributed systems, and empirical measurement.
Keep the evidence public
Papers, code, data, protocols, and negative results should remain inspectable whenever publication rules allow it.