QSentry
An open source tool for finding supply chain risks in quantum software projects.
Darry Derrick
Founder and Principal Investigator, Darry Lab for Secure and Applied AI
Professional Summary
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.
Education
Master of Computer Applications (Data Science and Artificial Intelligence)
Datta Meghe Institute of Higher Education and Research, India
Bachelor of Mobile Communications
Information and Communications University, Lusaka
Certificate, AI and Digital Pedagogy for Educators
Indian Technical and Economic Cooperation (ITEC)
Interests
AI Security and Safety
LLM Guardrails
Software Supply Chain Security
Trustworthy AI for Agriculture
AI in Education
Research
Darry Lab studies a gap that most AI security work leaves open: what happens when intelligent systems are deployed where connectivity is intermittent, compute is scarce, and the people relying on them cannot afford a failure. The lab works across three connected threads.
Securing AI systems. Guardrails, provenance and attestation for large language models and autonomous agents, designed to keep working offline and on modest hardware.
Securing the software they depend on. Supply chain protection for emerging software stacks, starting with quantum computing.
Putting trustworthy AI to work. Crop diagnostics, loss attribution and digital teaching tools built with and for communities in Zambia and the wider SADC region.
The lab welcomes collaboration with researchers, funders and practitioners who share these concerns.
Projects
YieldTrace
Counterfactual crop loss attribution at the scale of a single farm.
ForgeryGuard
A guardrail that screens requests before they reach a large language model, so it cannot be used to forge institutional documents.
Trust for AI Agents Offline
Lightweight attestation that lets autonomous AI agents verify tool calls even when connectivity drops.
LUDA
Ledger verified crop diagnostics for smallholder farmers, with explainable AI and mobile money built in.
Publications