Metadata (cookie, IP address, location) may be collected for the functioning of the site. If you do not want this data processed, then you should leave the site.
OK
Smart biometric keyboard
Each computer user has a unique keyboard signature. However, it is not possible to “measure” it quite accurately on any keyboard.
LONG PASSWORDS ARE DIFFICULT TO REMEMBER
AND EASILY COMPROMISED
but
THE PASSWORD CAN BE STRENGTHENED
if you associate data with it about how it was entered
Using a regular keyboard, it is almost impossible to obtain truly informative typing dynamics features suitable for user identification. Keyboard handwriting is very variable (depending on the person’s condition, time of day, etc.). However, using additional features, such as the force of pressing the keys, the speed of hand movement, and their position over the keyboard, you can greatly increase the accuracy of person identification, even if his keyboard handwriting is unstable.
The device consists of the following components
  • a standard keyboard that uses mechanical switches to press keys to close sections of an electronic circuit in which sensors are built into the body;
  • five resistive pressure sensors for measuring the force of pressing the keys, which are force-measuring resistors made in the form of flat thin passive elements, the resistance of which is proportional to the force acting on their surface;
  • piezoelectric sensor for converting mechanical vibrations of the keyboard into an electrical signal that can detect even minor vibrations;
  • two time-of-flight laser rangefinders that record the dynamic characteristics of the right and left hands; USB Host Shield module for connecting a USB keyboard to the microcontroller;
  • Arduino microcontroller to which the USB Host Shield and sensors are connected.
Device capabilities
The developed prototype (device + software) allows you to identify or verify the keyboard user, as well as determine the presence of deviations in his psychophysiological state from the “norm” (alcohol intoxication, fatigue, drowsiness, agitation).
The keyboard allows you to obtain comprehensive information about the individual typing characteristics of each user
Key publications
on the topic "Biometric keyboard"
Biometric authentication by keyboard handwriting with force of pressing the keys, parameters of vibration and movements of the operator's hands
dynamics of hand movements over the keyboard, pressure on the keys, key holding time, pauses between keystrokes, “wide” neural networks, wavelet analysis, amplitude spectrum, fast Fourier transform
view the work on researchgate.net

Sulavko, A. E. Biometric authentication by keyboard handwriting with force of pressing the keys, parameters of vibration and movements of the operator's hands / A. E. Sulavko, A. R. Khamzin, A. A. Lyzhin, M. D. Novikov, N V. Sednev, S. V. Khabarov // Issues of information protection. - 2018. - №. 2. - pp. 41-50

The paper deals with the problem of biometric authentication using the keyboard handwriting. Traditional signs of the keyboard handwriting are of little informative and do not allow creating reliable authentication means. In this paper it is suggested to use additional features: the force of pressing the keys, the trajectory of the movement of hands over the keyboard and the parameters of its vibration when typing a passphrase. To register new features, a special keyboard has been developed. An estimation of the information content of these characteristics was carried out. It is proposed to use flexible hybrid neural networks, capable of rapid learning, for recognizing keyboard users. The reliability of network decisions is estimated. The achieved result exceeds those obtained earlier.
Users' identification through keystroke dynamics based on vibration parameters and keyboard pressure
key pressure, keyboard vibration, wide artificial neural networks, correlation between biometric features, probability density
view the work on researchgate.net

Sulavko A.E., Fedotov A.A., Eremenko A.V. Users' identification through keystroke dynamics based on vibration parameters and keyboard pressure // 2017 Dynamics of Systems, Mechanisms and Machines, Dynamics 2017, 14-16 November, 2017, Omsk, Russia. - pp. 1-7. doi:10.1109/Dynamics.2017.8239514

The problem of protecting data from unauthorized access by authenticating subjects using keyboard handwriting is considered. It is proposed to use the parameters of pressure on the keys and vibration of the keyboard, together with the temporal features of the keystrokes, to recognize the typing subject. A keyboard has been developed using special sensors that allow you to register additional parameters. An assessment was made of the information content of new features as well as the probabilities of errors in recognizing subjects based on perceptrons, the Bayes formula, and networks of quadratic forms. The best result was that the number of identification errors for 20 people was 0.6%.
The influence of the operator’s functional state on the parameters of his keyboard handwriting in biometric authentication systems
measurement of keyboard handwriting parameters, artificial neural networks, operator functional state, subject recognition, biometrics
view the work on researchgate.net

Sulavko A.E. The influence of the operator’s functional state on the parameters of his keyboard handwriting in biometric authentication systems // Sensors and systems. - 2017. - №. 11. - pp. 19-30

The problem of protecting data from unauthorized access by authenticating subjects using keyboard handwriting is considered. The influence of alcohol intake, sedatives, caffeine, and intense physical activity on the operator's keyboard handwriting parameters was assessed. A series of experiments were carried out on the influence of the operator’s functional state on the results of his keyboard handwriting recognition using the Pearson measure, chi-modulus, multidimensional Bayesian hypothesis formula, weighted Euclidean measure, as well as their networks and perceptrons configured according to GOST R 52633.5.
Made on
Tilda