Dr. Lázaro Janier Gonzalez-Soler

- Project lead for the EU-funded Einstein Project, focused on advanced computer vision solutions for combating identity fraud. - Efficient finetuning using LoRA of foundation models (i.e., CLIP and DINO) for identity fraud detection. - Development of conditional mechanism for latent diffusion models to generate high-fidelity synthetic hand biometrics for data augmentation and gesture recognition research. - Contributed to the integration of CV pipelines in embedded identity verification systems.

- Developed and optimised deep learning pipelines for multimodal anomaly detection and biometric PAD. - Investigated model generalisation, robustness, and cross-domain adaptation on large-scale datasets. - Applied deep PAD methods across face, fingerprint, and voice data, addressing cross-modal robustness and spoofing resilience. - Awarded Best Paper at IEEE WIFS 2021 for contributions to anomaly detection in morphing attacks.

Development of data collection pipelines using web scraping technologies to process more than 500,000 data points per week.

Development of algorithms based on abstract syntax trees to automatically interpret ASTM, Kermit and HL7 message protocols from different laboratory instrument vendors.

- Implemented GPU-accelerated algorithms in CUDA C++ for large-scale data analysis and pattern recognition. - Collaborated on embedded AI solutions for secure, real-time recognition systems.