Rail 02

Biometric Systems

Redefining identity for the decentralised era — privacy-first recognition systems that never expose biometric templates to a central server.

Biometric Systems

Biometric Systems

Our biometric research develops advanced multimodal recognition systems using facial, fingerprint, iris, and behavioural biometrics. We prioritise security, privacy preservation, and ethical implementation — using zero-knowledge proofs and federated architectures to ensure biometric data never leaves the device.

Homomorphic Encryption Zero-Knowledge Proofs GANs CNNs Cryptography Federated Learning

Key Research Topics

Multimodal Recognition

Fusing fingerprint, facial, and iris modalities for robust recognition under degraded conditions and partial occlusion.

Iris & Retinal Analysis

Deep learning pipelines for high-resolution iris and retinal biometrics, including analysis under low-light and off-angle conditions.

Privacy-First Architectures

Zero-knowledge proof protocols and homomorphic encryption schemes that verify identity without ever exposing raw templates.

Spoofing & Liveness Detection

Adversarial presentation-attack detection models trained on synthetic and real spoofing datasets to harden recognition pipelines.

Current Projects

Security · Active · 2024–2026

ZKBio: Zero-Knowledge Biometric Authentication

Privacy-preserving biometric authentication using zero-knowledge proofs — securing identity without exposing raw biometric data.

ZK-SNARKs circom Rust WebAssembly PostgreSQL

Related Publications

Interested in Collaborating?

We welcome partnerships with institutions, NGOs, and researchers working at the frontier of AI and this domain.