🧩 Research (and Engineering) Outputs

This page highlights software systems, tools, benchmarks, and prototypes developed by us, including students and collaborators. These outputs reflect hands-on research, engineering effort, and real deliverables.

Federated Learning Attack Benchmark Suite

🧑‍🎓 Team: Names

🛠 Output: Research Software / Benchmarking Framework

📌 Description: Benchmarking data poisoning, model poisoning, and inference attacks against federated learning systems.

This software provides a unified framework to evaluate robust aggregation rules, privacy defenses, and attack strategies under realistic non-IID settings. The framework is designed to support reproducibility and extensibility.

🔧 Technologies: Python · PyTorch · NumPy · Federated Learning

View Software →

Privacy-Preserving Name Matching using FHE

🧑‍🎓 Team: Names

🛠 Output: Secure Algorithm & Prototype

📌 Description: Secure fuzzy name matching across organizations using Fully Homomorphic Encryption.

The system enables two parties to compute approximate string similarity without revealing raw identifiers, supporting cross-border data sharing under strict privacy constraints.

🔧 Technologies: Fully Homomorphic Encryption · C++ · Secure Computation

View Prototype →