Detailseite
Projekt
Design and Evaluation skalierbarer verhaltensbiometrischer Systeme in Pervasive Computing Umgebungen
Antragsteller
Professor Dr. Florian Alt; Professor Dr. Stefan Schneegass
Fachliche Zuordnung
Bild- und Sprachverarbeitung, Computergraphik und Visualisierung, Human Computer Interaction, Ubiquitous und Wearable Computing
Förderung
Förderung seit 2020
Projektkennung
Deutsche Forschungsgemeinschaft (DFG) - Projektnummer 425869382
Knowledge-based authentication mechanisms that require users to remember login and password are still among the most popular means for authentication. The average user is expected to access sensitive information through about 200 different, password-protected accounts in 2020. The caveat of such mechanisms is that they require people to use more passwords than they can remember and that entering passwords requires a significant amount of time. The number of authentications will further increase as more and more pervasive computing devices are being used in smart public spaces. These devices will not be recognized as computing devices anymore and may use predominantly interaction techniques most likely not suitable for entering knowledge-based passwords (e.g., gestures, speech). Examples include personal devices (e.g., smart glasses, smart phones, HMDs, smart clothes, wearables) as well as devices in the environment (interactive displays, pressure-sensitive floors, etc.) and will jointly create a pervasive computing environment. In past years, behavioral biometrics, that is the ability to identify users implicitly from their behavior, received considerable attention in the research community. This approach does not require users to remember a secret but authentication can seamlessly slide into the background. In particular, researchers showed that numerous behavior traits (gait, typing behavior, touch targeting, gaze) can be used for identification. At the same time, behavioral biometrics so far was mainly investigated in the lab for single users, since assessing different features’ biometric value requires precise measurements. Thus, it remains unclear how these approaches scale to novel challenges of pervasive computing environments.In this project, we examine how pervasive computing environments can leverage behavioral biometrics for identifying and authenticating users. The main challenge this project is addressing is the question how behavioral biometric approaches scale to different pervasive computing environments, containing multiple users with changing behavior, different physicalities, and changing sensing and interaction capabilities. From this objective, many questions emerge: (1) How is users’ behavior influenced both by other people in the vicinity, characteristics of a space, as well as by novel interaction techniques emerging as more and more computers become part of our everyday life; (2) how does this influence the way in which we design and develop behavioral biometrics; and (3) what does this mean for behavioral biometrics-based authentication concepts.We envision this project to enable a significant leap forward towards behavioral biometrics becoming a powerful means for identifying and authenticating users in future pervasive computing environments that combines high usability with strong security. The project outcomes are valuable beyond security, enabling novel UIs to be built that adapt to users’ behavior.
DFG-Verfahren
Schwerpunktprogramme
