There are several proposals:
(2002) The University of Southampton (UK) and the University of Twente (Netherlands) have studied the idea of tapping recognition, starting from the idea that you are able to recognize who is knocking on your door, or that telegraphy operators were able to identify each other by recognizing the way in which they tapped out messages.
They concentrated on the waveform properties of the pulses which result from tapping
the sensor on a smart card. The use of rhythm features may be also used, but it's closer to a secret password than biometrics.
Waveform captured with a piezoelectric sensor
Sample of sensors / Exemple de capteurs, Position on the smart card / Position sur la carte à puce:
Published papers / papiers publiés:
Human-generated Random time-intervals (RTIs)
(2009) Recent studies in cognitive neuroscience and psychiatry have reported that the generation of random rhythms or numbers is a demanding cognitive task and carries enough information to discriminate between different clinical populations. When someone is asked to generate random numbers, there is a cognitive load implied, since there is a close interaction between short-term memory and internalized decision making mechanisms. A closely related task is the generation of random tapping rhythms. Finger tapping, in particular, requires sensorimotor interaction and specific cortical networks responsible for this have been identified and modeled. It has also been demonstrated that different individuals are characterized by unique eigen-rhythms which regulate spontaneous finger tapping.
In this work, we present SilentSense, a framework to authenticate users silently and transparently by exploiting dynamics mined from the user touch behavior biometrics and the micro-movement of the device caused by user’s screen-touch actions. We build a “touch-based biometrics” model of the owner by extracting some principle features, and then verify whether the current user is the owner or guest/attacker. When using the smartphone, the unique operating dynamics of the user is detected and learnt by collecting the sensor data and touch events silently. When users are mobile, the micromovement of mobile devices caused by touch is suppressed by that due to the large scale user-movement which will render the touch-based biometrics ineffective. To address this, we integrate a movement-based biometrics for each user with previous touch-based biometrics. We conduct extensive evaluations of our approaches on the Android smartphone, we show that the user identification accuracy is over 99%.