DEMO MODE — Pre-computed ResNet-50 inference results. No live backend.
You are offline. Symptom screening works fully offline. New diagnoses will queue and sync when reconnected.
5 nodes · live training

Diagnose with Confidence.
Protect with Certainty.

A secure, federated AI medical diagnosis platform built for Nigerian healthcare. Five hospital nodes train together. Zero patient data shared.

Final Year Project · CSC 492 · Caritas University, Enugu · August 2026
Supervisor: Dr. Ugo Nwankwo
0
Hospital Nodes
< 0.00
ε Privacy
0.000
AUC-ROC
Loading topology…
Federated Pentagon · FedAvg + DP-SGD
How it works

How Federated Learning Works

Three steps. The model visits the data — the data never leaves the hospital.

01

Train Locally

Each institution trains the ResNet-50 model on their own chest X-rays. No image leaves the hospital.

02

Share Only Learning

Only model weight updates — protected by DP-SGD with gradient clipping (C=1.0) and Gaussian noise — are transmitted via mutually authenticated gRPC connections.

03

Improve Together

FedAvg aggregates updates weighted by dataset size. All five hospitals benefit from the improved model, which now reflects combined learning from 4,430 training images.

Privacy guarantee

Mathematical, not just policy.

Three layered defences, each providing a verifiable guarantee.

Federated Learning

Patient data stays at source. The ResNet-50 model visits the data, not the other way around.

Differential Privacy

DP-SGD adds Gaussian noise N(0,σ²C²I) calibrated so the system satisfies (ε=5.13, δ=1e-5)-DP after 50 rounds. An adversary intercepting all model updates cannot determine any individual's participation to more than e^5.13 ≈ 169× baseline certainty.

Mutual TLS

All gRPC communications use mTLS 1.3 with X.509 certificates signed by the system's private CA. Certificate revocation via CRL.

Figure 3.14

Privacy-Utility Trade-off

AUC-ROC over 50 training rounds for each privacy configuration. Higher epsilon = weaker privacy guarantee. Moderate Privacy is the production default — 0.947 AUC-ROC for ε=5.13.

High Privacy
ε=1.02 · AUC 0.921
Moderate Privacy
ε=5.13 · AUC 0.947
Low Privacy
ε=10.07 · AUC 0.958
Non-Private
Centralised · AUC 0.963

Ready to put privacy first?

Sign up as a patient for a symptom screening, or as a clinician to diagnose against the federated ResNet-50 model.