Title: Cátedra ENIA UAM-VERIDAS en IA Responsable

Type: NextGenerationEU Plan de Recuperación, Transformación y Resiliencia

Code: TSI-100927-2023-2

Funding: ca. 800 Keuros

Participants: Univ. Autonoma de Madrid

Period: January 2023 - December 2026

Principal investigator(s): Julian Fierrez and Ruben Tolosana

Objectives:

- Improve the robustness and security performance of biometric systems against attacks such as DeepFakes, posisoning and backdoor attacks, etc.

- Analysis and proposal of novel methods to reduce the bias in AI models.

- Proposal of novel methods to improve the explainability of the AI models.

- Analysis and proposal of novel methods to detect and mitigate the extraction/use of sensitive information in AI models.

Title: Empowering AI Technologies through Large Language/Vision Models and Generative AI with Applications to Security, Health and Human Behavior

Type: Comunidad de Madrid R&D Program

Code: SI4/PJI/2024-00062

Funding: ca. 54 Keuros

Participants: Univ. Autonoma de Madrid

Period: January 2025 - December 2026

Principal investigator(s): Ruben Tolosana

Objectives:

- Exploration and proposal of novel Generative AI methods for the synthesis of data in the scenarios considered.

- Exploration of novel Foundational Models to overcome traditional limitations in Machine Learning and in real-life scenarios.

- Application of the insights in scenarios such as Security, Health, and Human Behavior.

Title: Human Interaction with Smart Devices in Security and Digital Health Domains

Type: Spanish National R&D Program

Code: PID2021-126521OB-I00

Funding: ca. 220 Keuros

Participants: Univ. Autonoma de Madrid

Period: January 2022 - December 2024

Principal investigator(s): Javier Ortega-Garcia and Ruben Vera-Rodriguez

Objectives:

- Acquire, generate synthetic data, and analyze human-machine interaction data as a ground basis of research.

- Improve the robustness and security performance of biometrics from human-machine interaction data.

- Propose new schemes for human-machine interaction data over time in the digital health and wellness domains.

- Proposal and development of new schemes in the privacy preserving domain to quantify and remove the sensitive attributes contained in human-machine interaction data.

Title: Inteligencia Artificial para la Prevención de Enfermedades Crónicas a través de una Nutrición Personalizada

Type: Comunidad de Madrid Synergy Program

Code: Y2020/TCS6654

Funding: ca. 310 Keuros UAM (620 Keuros in total)

Participants: Univ. Autonoma de Madrid and IMDEA-Food Institute

Period: July 2021 - June 2024

Principal investigator(s): Javier Ortega-García (UAM technical lead: Aythami Morales)

Objectives:

- AI4Food will develop a series of enabling technologies to process, analyze and exploit a large number of biometric signals indicative of individual habits, phenotypic and molecular data.

- AI4Food will integrate all this information and develop new machine learning algorithms to generate a paradigm shift in the field of nutritional counselling.

- AI4Food technology will allow a more objective and effective assessment of the individual nutritional status, helping experts to propose changes towards healthier eating habits from general solutions to personalized solutions that are more effective and sustained over time for the prevention of chronic diseases.

- AI4Food will also advance knowledge on three questions using these new technologies: 1) WHICH are the sensor dependent and sensor independent biomarkers that work best for nutritional modelling of human behavior and habits? 2) WHEN, that is, under what circumstances (e.g., user habits, signal quality, context, phenotypic and molecular data), and 3) HOW can we best leverage those signals and context information to improve nutritional recommendations.

Title: Training in Secure and Privacy-preserving Biometrics

Type: H2020 Marie Curie Initial Training Network

Code: H2020-MSCA-ITN-2019-860813

Funding: ca. 502 Keuros

Participants: UAM, Univ. Applied Sciences H-DA (Germany), Univ. Groningen (Netherlands), IDIAP (Switzerland), Chalmers Univ. (Sweden), Katholieke Univ. Leuven (Belgium)

Period: January 2020 – December 2023

Principal investigator(s): Massimiliano Todisco (Julian Fierrez and Aythami Morales for UAM)

Objectives:

- To combat rising security challenges, the global market for biometric technologies is growing at a fast pace. It includes all processes used to recognise, authenticate and identify persons based on biological and/or behavioural characteristics.

- The EU-funded TReSPAsS-ETN project will deliver a new type of security protection (through generalised presentation attack detection (PAD) technologies) and privacy preservation (through computationally feasible encryption solutions).

- The TReSPAsS-ETN Marie Sklodowska-Curie early training network will couple specific technical and transferable skills training including entrepreneurship, innovation, creativity, management and communications with secondments to industry.

Title: Privacy Matters

Type: H2020 Marie Curie Initial Training Network

Code: H2020-MSCA-ITN-2019-860315

Funding: ca. 485 Keuros

Participants: UAM, Univ. of Kent (UK), NTNU (Norway), NR (Norway), Julius-Max Univ. (Germany), Katholieke Univ. Leuven (Belgium)

Period: January 2020 – December 2023

Principal investigator(s): Raymond Veldhuis (Ruben Vera-Rodriguez and Julian Fierrez for UAM)

Objectives:

- To train 14 creative, entrepreneurial, and innovative researchers as privacy protection experts.

- To contribute to a full understanding of the multidisciplinary nature of privacy protection in a digitalised society.

- To contribute to the development of solutions that address this important societal challenge.

Title: Identifying Digital Endpoints to Assess Fatigue, Sleep and Activities in Daily Living in Neurodegenerative Disorders and Immune-mediated Inflammatory Diseases

Type: H2020 Innovative Medicines Initiative 2 (IMI2) - Research and Innovation Action (RIA)

Code: H2020-JTI-IMI2-2018-15-two-stage-853981

Funding: ca. 40 Meuros in total (ca. 200 Keuros for UAM)

Participants: UAM + 44 more: Janssen, Takeda, Lilly, Pfizer, Sanofi, ECRIN, Cambridge Cognition, Asociación de Parkinson Madrid, Imperial College London, etc.

Period: November 2019 - April 2025

Principal investigator(s): Fai Ng from Newcastle Univ., UK (Julian Fierrez for UAM)

Objectives:

- Fatigue and sleep disturbances are two common and disabling symptoms that affect patients with neurodegenerative disorders (NDD) and immune-mediated inflammatory diseases (IMID). These symptoms are major predictors of poor quality of life and increased healthcare cost. Current questionnaire-based approaches to measure these symptoms have key limitations preventing them from being used as reliable endpoints in clinical trials to evaluate the effect of therapies.

- IDEA-FAST aims to address these issues by identifying novel digital endpoints for fatigue and sleep disturbances that will provide more objective, sensitive and reliable measures of the severity and impact of these symptoms in ecological settings. Such digital endpoints will not only help to gain insight into the underpinning mechanisms of fatigue and sleep disturbances, but will also vastly improve the efficiency of clinical trials, ultimately reducing the time and cost to bring new therapies to patients.

- To identify these digital endpoints, we will follow the recommendations of the Clinical Trials Transformation Initiative (CTTI). We will identify the characteristics that fatigue and sleep disturbances will have impact, then select the digital measures (endpoints) to quantify them, followed by choosing the appropriate digital device/technology accordingly. We will then perform a pilot study to prioritise a few of these candidate digital endpoints for validation. We will test the performance of these digital endpoints in two NDD and four IMID in a large longitudinal study during which extensive relevant clinical data will be collected. If these digital endpoints were validated, we will seek support from EMA/FDA for their qualification. Patient users’ perspective, ethical, data privacy, legal and other regulatory issues will be taken into consideration in all aspects of our proposal.

- The resultant digital biobank from the longitudinal study will become an invaluable resource for future exploitation.

Title: Spanish Network of Machine Learning and Computer Vision for Human Analysis and Robotic Perception

Type: Spanish National R&D Program, Research Network

Code: RED2018-102511-T

Funding: ca. 10 Keuros (Full Project)

Participants: 8 Spanish universities, including Univ. Autonoma de Madrid

Period: January 2020 - December 2021

Principal investigator(s): Filiberto Pla (Julian Fierrez for UAM)

Objectives:

- To foster collaboration between Spanish research groups working in Computer Vision and Pattern Recognition.

Title: Biometrics and Behavior for Context-Aware and Secure Human-Computer Interaction

Type: Spanish National R&D Program

Code: RTI2018-101248-B-I00

Funding: ca. 243 Keuros

Participants: Univ. Autonoma de Madrid

Period: January 2019 - December 2021

Principal investigator(s): Julian Fierrez and Aythami Morales

Objectives:

- Generating a better understanding about the nature of biometrics in terms of distinctiveness, permanence, and relation to stress levels and emotions. New methods for analyzing and modelling complex yet structured relations on heterogeneous data will be developed in BIBECA.

- Design of robust algorithms in terms of biometric representation and matching from uncooperative users in unconstrained and varying scenarios. BIBECA will contribute in this topic to: innovative adaptive fusion schemes, and public databases with heterogeneous continuous biometrics, in realistic mobile and desktop setups.

- Experimental exploration and technology development towards new biometrics applications: mobile authentication and ubiquitous biometrics.

- Understand and improve the usability of biometric systems.

- Understand and improve the security in biometric systems. BIBECA will track the advances in security against attacks and privacy preservation in biometric systems, and will adapt and investigate those advances for the kind of human interaction signals to be explored during the project implementation.

Title: Cognitive Biometric Authentication: Human Interaction for Identification

Type: Spanish National R&D Program

Code: TEC2015-70627-R

Funding: ca. 280 Keuros

Participants: Univ. Autonoma de Madrid

Period: January 2016 - December 2018

Principal investigator(s): Julian Fierrez and Javier Ortega-Garcia

Objectives:

- Proposal and development of novel cognitive authentication schemes based on behavioral biometrics from heterogeneous data sets originating from human-machine interaction.

- Improving the state of the art in continuous authentication systems making use of biometrics.

- Proposal and development of novel user-dependent information fusion schemes, adaptive over time, and making use of context information.

Title: Evaluation of Performance and Countermeasures against Attacks and Threats on Biometrics Systems

Type: Spanish National R&D Program

Code: TEC2012-34881

Participants: Univ. Autonoma de Madrid

Period: January 2013 - December 2015

Principal investigator(s): Javier Ortega-Garcia

Title: Biometrics Evaluation and Testing

Type: FP7-SECURITY, CP-FP: Small or Medium-scale Focused Research Project

Code: SEC-2011.5.1-1-284989

Funding: ca. 3.5 Meuros (ca. 530 Keuros for UAM)

Participants: 10 EU Institutions, including Univ. Autonoma de Madrid

Period: March 2012 - February 2016

Principal investigator(s): Sebastien Marcel (Julian Fierrez for UAM)

Objectives:

- Identity management using Biometrics is deployed in a growing number of applications ranging from identification platforms (e.g. biometric passports) to access control systems for border checks or banking transactions. Unfortunately, the reliability of these technologies remains difficult to compare. There are no european-wide standards for evaluating their accuracy, their robustness to attacks or their privacy preservation strength.

- BEAT will fill this gap by building an online and open platform to transparently evaluate biometric systems, designing protocols and tools for vulnerability analysis and developing standardization documents for Common Criteria evaluations. The planned impact is three-fold: the reliability of biometric systems becomes standardized and comparable, potentially leading to a meaningful increase in their performance; technology transfer from research to companies becomes easier with the use of an interoperable framework; authorities and decision-makers become more informed about the progress made in biometrics as results impact standards.