Projects |

ForgeryGuard

Tue, 01 Sep 2026 00:00:00 +0000

Large language models will readily draft letters, certificates and official notices on request. That is useful, but it also makes forging institutional documents easier than it has ever been.

ForgeryGuard sits in front of the model and screens each request before it is answered. The aim is to block prompts that impersonate institutions or ask for fraudulent artifacts, while still allowing the legitimate document drafting that schools, offices and businesses depend on every day. The approach combines neural classification with symbolic reasoning, so that each decision can be explained rather than simply asserted.

Status: Research complete. Publication details will be added here once the paper is published.

QSentry

Sat, 17 Oct 2026 00:00:00 +0000

Quantum programs depend on a fast growing ecosystem of open source compilers, SDKs and libraries. The security practices that now protect classical software supply chains have barely reached it.

QSentry is an open source tool for detecting supply chain risks in quantum software projects, so that researchers and developers can trust the dependencies their circuits are built on. It is designed to fit into the workflows quantum developers already use.

Status: In active development.

LUDA

Sat, 01 Aug 2026 00:00:00 +0000

LUDA (Ledger verified Unified Diagnostics for Agriculture) is an Android platform that helps smallholder farmers diagnose crop disease, see the reasoning behind each diagnosis, and buy the inputs they need.

A team of specialised AI agents follows a verify before commit pattern: no diagnosis, explanation or transaction is recorded until it has been checked, and verified records are anchored on the Internet Computer blockchain. Farmers can pay for inputs through MTN MoMo, Airtel Money and Zamtel. Climate context comes from CHIRPS, ERA5 and NASA POWER, and the models improve through federated learning with differential privacy, so farm data stays on the farmer’s device.

Status: In development.

YieldTrace

Thu, 01 Oct 2026 00:00:00 +0000

When a harvest fails, farmers, insurers and governments all need to know why. YieldTrace estimates what each farm would have produced under normal conditions and attributes the shortfall to its causes.

The project applies the potential outcomes framework of causal inference at the scale of an individual farm, drawing on CHIRPS and ERA5 climate data. The first study will focus on maize, cassava and tomato in Chinsali District, Muchinga Province, Zambia. The goal is to produce the kind of farm level evidence that agricultural policy commitments under the CAADP Kampala Declaration call for.

Status: Concept stage.

Trust for AI Agents Offline

Tue, 01 Sep 2026 00:00:00 +0000

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.