Past Events

Mobile devices such as smartphones and smartwatches are part of our everyday lives, acquiring large amounts of personal information which needs to be properly secured. Among the different authentication techniques, behavioural biometrics has become a very popular method as it allows authentication in a non-intrusive and continuous way. We propose M-GaitFormer, a novel mobile biometric gait verification system based on Transformer architectures. The proposed system outperforms other state-of-the-art approaches based on popular Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This biometric system only considers the accelerometer and gyroscope data acquired by the mobile device.

Curriculum vitæ

Paula Delgado de Santos has a bachelor's degree in Telecommunications Engineering from the Universidad Autonoma de Madrid. She later acquired a master’s degree in Telecommunications Engineering while she was pursuing a scholarship of IBM together with her home university. The previous year she was working at a Swiss University, HEIG-VD, as a Data Scientist. In 2020 she began her PhD studies with a Marie Curie Fellowship within the PriMa (Privacy Matters) EU project, supervised by Professor Richard Guest (University of Kent) and Doctor Ruben Tolosana (Universidad Autonoma de Madrid). She will study the richness of background sensor data elements obtained from mobile devices in a continuous authentication scenario.

We thank our media partner:

Workshop of the Biometrics Working Group of TeleTrusT, the IT Security Association in Germany

Back in spring 2011 our Norwegian Biometrics Laboratory (NBL) was established and for the opening we organized a workshop. Since then we have celebrated the NBL Annual Workshops (NBLAW). All the workshops are listed on the NBL homepage.

European laws and international standards categorize biometric data as sensitive personal data that require adequate protection. Where biometric data is stored, transferred, or processed, this protection must be assured. NBLAW 2023 therefore aims to shine a light on the recent progress and challenges in biometric template protection from a cryptographic standpoint. In particular, the need for post-quantum protection of biometric templates will be a focus. Furthermore, it is the goal of the workshop to connect research and real-life applications through addressing questions such as current quantum security levels for homomorphic encryption schemes and efficient ways of computing on encrypted biometric data. The workshop will be held as a hybrid event and can be attended remotely as well.

Cognisant of the privacy risks for data subjects interacting with biometric systems, researchers in academia and industry have devised a variety of biometric template protection schemes based on one-way functions. Unlike traditional asymmetric encryption, one-way functions allow biometric recognition to happen in the encrypted domain. Thus, they protect the confidentiality and integrity of biometric templates end to end, that is, during transmission, processing, and storage.

To discuss the concerns about the legal implications of the protection schemes under the General Data Protection Regulation (GDPR), the European Association for Biometrics (EAB) is hosting a workshop on March 1st, 2023. The main themes covered will include GDPR safety standards, cryptography, and GDPR in relation to biometric data. The workshop will feature three keynote speakers, a roundtable discussion, and an online networking session.

The aim of the event is to inform about the topic, and to provide a comprehensive understanding of current trends, as well as to discuss current and future challenges related to biometric data protection under GDPR requirements.

State of the art face detection and recognition algorithms are increasingly focusing on attention, but how do they compare with human attention on faces? Do they “fixate” the same areas as humans do? Can we use human fixations to improve recognition models? We try to answer these questions using a human fixations dataset on face images, comparing them to Visual Transformers and using them to build a bottom-up, part-based model for face detection and recognition.

Curriculum vitæ

Marinella Cadoni received her PhD on Mathematics at the University of Warwick (UK) in 2004. From 2004 to 2008 she worked as a postdoc at the IEIIT-CNR research institute located in Turin, where she carried out research in the field of Computer Vision. She then won a three year research grant on Biometrics at the University of Sassari. From 2011 to 2017 she carried out research activities at the University of Sassari and for private companies. From 2017 she is an Assistant Professor in Computer Science at the University of Sassari. Her research interests focus on Biometrics, 3D object reconstruction and retrieval and human visual attention.

We thank our media partner:

In June 2021, the European Parliament (EP) asked for a permanent ban on the automated recognition of individuals in public spaces. Parliament calls for the use of private facial recognition databases and predictive policing based on behavioural data to be forbidden. Dr Emilio Mordini argues that EP's reasons for concern are partly misplaced and stem from an overemphasis on the technological potential of AI for recognition technology and an underestimation of its inherent limitations. His argument is based on what has been called 'the most beautiful 10 minutes in the history of cinema': the final sequence of Sergio Leone's movie ‘The Good, the Bad and the Ugly'.

Curriculum vitæ

Emilio Mordini is an M.D. and M.Phil.; he has some 40 years of practice as a psychiatrist and psychoanalyst.  During his professional life, he has been awarded with several research grants within the scope of the 3rd, 4th, 5th, 6th, 7th RTD FPs, and H2020, and by the NATO Science for Peace and Security Programme. Emilio pioneered international research on ethics of biometrics, launching in 2003 the FP6 project BITE (Biometric Technology Ethics) and initiating 4 major international conferences on ethics of biometrics, held in Europe (15-16 Dec 2005, Brussels, jointly convened by the European Commission), in the US (28 – 29 Nov 2006, jointly convened by the US Dept. of Homeland Security), in India (24-25 Sept 2009, New Delhi, jointly convened by the Data Security Council of India), and in the People's Republic of China (4-5 Jan 2010, Hong Kong, and 11-12 Oct 2011, Beijing, jointly convened by the HK Polytechnic University and the Chinese Academy of Science). Currently, he serves as a member of the CERIS Expert Group at DG Home and chairs the ethical committee of the European Association of Biometrics (EAB). He has extensively published in international journals and edited several books.