Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/129851
Título: Physical Biometric Spoofing of 3D Dynamic On-Air Signature
Autores/as: Quintana Hernández, José Juan 
Ferrer, Miguel A. 
Diaz, Moises 
Carmona-Duarte, Cristina 
Clasificación UNESCO: 33 Ciencias tecnológicas
Palabras clave: 3D Automatic Gesture Recognition
3D Biometric Authentication
3D Synthesis Of Human Movements
Kinematic Theory Of Rapid Movements
Sigma-Lognormal Model
Fecha de publicación: 2023
Conferencia: 56th International Carnahan Conference on Security Technology, ICCST 2023 
Resumen: 3D on-air signatures represent a novel behavioral biometric that is highly challenging to imitate, even from a distance. However, the emergence of robotic arms capable of mimicking human movements poses a potential security vulnerability. This paper examines the possibility of generating 3D fingertip movements with a robotic arm that accurately mimic a 3D on-air signature to circumvent a biometric system. The robotic arm controls trajectory and velocity to generate a human-like movement. Robotic-made signatures are then used to spoof a 3D on-air dynamic signature biometric system, which relies on a DTW verifier. Experiments demonstrate that robotic signatures can effectively bypass a verifier exclusively trained with real signatures, underscoring the importance of incorporating an additional security layer, such as a liveness detector, into these biometric schemes.
URI: http://hdl.handle.net/10553/129851
ISBN: 9798350315875
ISSN: 1071-6572
DOI: 10.1109/ICCST59048.2023.10474253
Fuente: Proceedings - International Carnahan Conference on Security Technology[ISSN 1071-6572], (Enero 2023)
Colección:Actas de congresos
Vista completa

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.