Digital Life
Resources
To support the development of the project, we will have the following resources:
- Access to virtual development environments, experimental servers and, if necessary, physical devices for testing and simulations.
- Tutorials and guides on training AI models on edge devices and federated learning.
- Links to recommended articles, books, and academic resources for further study of biometrics and cybersecurity.
- Information on best practices and ethical considerations in the design and use of biometric systems.
Are you interested?
If you are a professor or university student and you are interested in participating in the TUTORING program, register your information so that we can start the program.
Context
Challenge aimed at students with a solid foundation in artificial intelligence and machine learning, capable of understanding and working with AI models, neural networks, and biometric systems.
It is advisable to have programming experience (preferably in Python), basic knowledge of generative or deep learning models, and curiosity about the development of responsible and ethical solutions for authentication and data protection.
We particularly value an interest in experimentation, the practical application of AI, and multidisciplinary work on technological innovation projects.
Intro
Biometric authentication has become one of the most important technologies for ensuring security and protecting digital identity in modern environments.
This challenge proposes going beyond traditional methods and designing an innovative system capable of operating directly on edge computing devices, where the processing and protection of personal data are essential.
The challenge invites participants to imagine and propose solutions based on artificial intelligence that use biometric data, promoting trust, efficiency and privacy in new interfaces and use cases that require robust and responsible authentication.
Challenge Description
At Telefónica Digital Innovation's Scientific Research team, we are seeking to develop an innovative authentication system based on biometric data, such as voice, fingerprint and/or periocular images, that works efficiently and securely on edge computing devices.
This system will be powered by advanced artificial intelligence, including foundational models and distributed learning techniques, such as federated learning and on-device training, with the aim of minimising privacy risks by processing and storing data locally.
The challenge will focus on developing solutions based on biometric data, such as voice, fingerprint or periocular images, using responsible, reliable and scalable AI models for real-world authentication and access control applications.
