Trust for AI Agents Offline
AI agents increasingly call tools, APIs and other agents on our behalf. Today’s identity and trust frameworks assume an agent can always reach a server to check credentials, an assumption that breaks in much of the world.
This project develops a lightweight attestation protocol that lets agents prove where a tool call came from and verify it locally, so trust holds even on intermittent networks. It targets the resource constrained deployments common across Africa and other emerging regions.
Full working title: Lightweight Attestation Based Provenance Verification for Autonomous AI Agent Tool Invocation: A Connectivity Resilient Trust Protocol for Resource Constrained AI Deployments.
Status: Ongoing research.
Darry Derrick is a Zambian researcher working on the security of AI systems and on putting trustworthy AI to work in agriculture and education across Southern Africa. His work starts from a practical question: how do we make intelligent systems safe and dependable when they run on limited compute, patchy connectivity and mobile money rails, rather than inside a well resourced data centre?
He leads Darry Lab for Secure and Applied AI, an independent research initiative. Current work includes ForgeryGuard, a guardrail that stops large language models from producing forged institutional documents; QSentry, an open source tool for securing the quantum software supply chain; LUDA, a ledger verified crop diagnostics platform for smallholder farmers; and YieldTrace, a causal approach to attributing crop losses at farm level.