Dopamine: Differentially Private Federated Learning on Medical Data (AAAI - PPAI)

Easy-to-use utilities to build privacy-preserving AI.

Securing Collaborative Medical AI by Using Differential Privacy

Code for the paper "PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning" by L. Corbucci, M. A. Heikkilä, D.S. Noguero, A. Monreale, N. Kourtellis.

Hands-on part of the Federated Learning and Privacy-Preserving ML tutorial given at VISUM 2022

Building an AI model for chest X-ray under patient privacy guarantees

A Comparative Study of Gradient Clipping Techniques in Differentially Private Stochastic Gradient Descent (DP-SGD)

Imagenet-scale DP-SGD training using Pytorch Opacus

SecureMed-LLM: A privacy-preserving framework for clinical report generation from chest X-rays, integrating Med-Guard anonymization, DP-SGD (ε=3.0), adversarial training, IDS-LLM validation, and ECIES/Curve25519 encryption. PeerJ Computer Science 2025.

Federated learning system for image classification with gradient privacy protection and gradient inversion attack simulation.

Empirical study of the Privacy–Robustness–Performance trilemma in Federated Learning: combining DP-SGD, FLTrust Byzantine-robust aggregation, and Top-k compression across 8 configurations on MNIST, simulated with Flower.

DP-SGD accuracy vs. privacy budget (ε) experiments on MNIST using Opacus — quantifies the accuracy/privacy/compute trade-off with RDP accounting.

🔐 IEEE SAFL framework re-implementation: Federated recommendation with DP-SGD (ε=2.58), FedProx & Sentence-BERT — 54.6% MAE reduction

Implementation of Opacus DP in Flower.

Implementation of my research on automating the optimal privacy budget (ε) in DP-FL using epsilon-aware strategy.

Reproducible benchmark comparing centralized, federated, and differentially private federated learning for cardiovascular disease prediction.

Federated learning with differential privacy for mental health text classification. MSc Data Science thesis, University of Glasgow

Privacy-preserving credit-risk prediction using DP-SGD, local differential privacy, membership-inference auditing, and fairness analysis.