Logo des Repositoriums

Auflistung nach Autor:in "Joosen, Wouter"

1 - 3 von 3
  • Zeitschriftenartikel
    DPMF: A Modeling Framework for Data Protection by Design
    (Enterprise Modelling and Information Systems Architectures (EMISAJ) – International Journal of Conceptual Modeling: Vol. 15, Nr. 10, 2020) Sion, Laurens; Dewitte, Pierre; Van Landuyt, Dimitri; Wuyts, Kim; Valcke, Peggy; Joosen, Wouter
    Building software-intensive systems that respect the fundamental rights to privacy and data protection requires explicitly addressing data protection issues at the early development stages. Data Protection by Design (DPbD)—as coined by Article 25(1) of the General Data Protection Regulation (GDPR)—therefore calls for an iterative approach based on (i) the notion of risk to data subjects, (ii) a close collaboration between the involved stakeholders and (iii) accountable decision-making. In practice, however, the legal reasoning behind DPbD is often conducted on the basis of informal system descriptions that lack systematicity and reproducibility. This affects the quality of Data Protection Impact Assessments (DPIA)—i.e. the concrete manifestation of DPbD at the organizational level. This is a major stumbling block when it comes to conducting a comprehensive and durable assessment of the risks that takes both the legal and technical complexities into account. In this article, we present DPMF, a data protection modeling framework that allows for a comprehensive and accurate description of the data processing operations in terms of the key concepts used in the GDPR. The proposed modeling approach supports the automation of a number of legal reasonings and compliance assessments (e.g., purpose compatibility) that are commonly addressed in a DPIA exercise and this support is strongly rooted upon the system description models. The DPMF is supported in a prototype modeling tool and its practical applicability is validated in the context of a realistic e-health system for a number of complementary development scenarios.
  • Konferenzbeitrag
    Gait Authentication based on Spiking Neural Networks
    (BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Rúa, Enrique Argones; van Hamme, Tim; Preuveneers, Davy; Joosen, Wouter
    In this paper we address gait authentication using a novel approach based on spiking neural networks (SNNs). This technology has proven advantages regarding energy consumption and it is a perfect match with some proposed neuromorphic hardware chips, which can lead to a broader adoption of user device applications of artificial intelligence technologies. One of the challenges when using this technology is the training of the network itself, since it is not straightforward to apply well-known error backpropagation, massively used in traditional artificial neural networks (ANNs). In this paper we propose a new derivation of error backpropagation for the spiking neural networks that integrates lateral inhibition and provides competitive results when compared to state of the art ANNs in the context of IMU-based gait authentication.
  • Konferenzbeitrag
    Gait template protection using HMM-UBM
    (BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Van hamme, Tim; Argones Rúa, Enrique; Preuveneers, Davy; Joosen, Wouter
    This paper presents a hidden Markov model-Universal background model gait authentication system, which is also incorporated into a template protection based on a fuzzy commitment scheme.We show that with limited enrollment data the HMM-UBM system achieves a very competitive equal error rate of 1% using one sensor. The proposed template protection scheme benefits from eigenfeatures coming from multiple Universal background model systems fused with a novel technique that minimizes the bit error rate for genuine attempts. This allows the protected system to achieve a false rejection rate below 5% with an effective key length of 64 bits.