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
"Living" Document app
A program that continuously identifies the user while working with an electronic document. The content of the document and the functionality of the program change in real time depending on who is working with the document at the moment.
the essence of the concept of a “living” document
In the process of working with a document, biometric data is continuously collected for more reliable verification of the user’s identity: keyboard handwriting, facial parameters, and data on the movement of the mouse. The accumulated biometric information is used to generate an encryption key using wide neural networks, which are converters capable of transforming a vector of fuzzy, ambiguous biometric parameters “Genuine” into a clear, unambiguous key code.
As identification information about the user accumulates, document data blocks containing confidential information are decrypted, resulting in the document changing display and editing parameters "on the fly", hiding or replacing certain fragments, and blocking and providing certain functions. The actions to hide or replace content are determined by the creator of the document
Biometric "mouse"
for application management
Not all computers are equipped with a web camera, and when working with documents, the user does not always actively use the keyboard (for example, in viewing mode). In order to obtain informative data about the user while working with documents, we equipped the mouse manipulator with two special sensors: a gyroscope and an accelerometer. With the help of these sensors, fairly informative signals about the movement of the manipulator are generated; analysis of these signals in real time makes it possible to identify the user.
Key publications
"Generation of encryption keys based on biometric features recorded by standard computer equipment"
Generation of a biometrically activated digital signature based on hybrid neural network algorithms
biometric signature, electronic signature, dynamic biometric image, neural network biometric-code converter, image recognition, integrity and authenticity protection
https://iopscience.iop.org/article/10.1088/1742-6596/1050/1/012047/pdf

Lozhnikov P.S., Sulavko A.E. Generation of a biometrically activated digital signature based on hybrid neural network algorithms // IOP Conf. Series: Journal of Physics: Conf. Series. II International scientific conference "Mechanical Science and Technology Update", 27-28 February 2018. Omsk, Russia. doi:10.1088/1742-6596/1050/1/012047

This paper suggests a model of a hybrid wide neural network based on perceptrons, quadratic form networks and multidimensional difference and hyperbolic Bayes functionals. It is experimentally proved that this model is highly efficient when used for biometric authentication and generation of a digital signature activated biometrically. The paper suggests methods of generating keys of a digital signature and personal authentication by handwritten patterns, a key stroke manner and facial parameters. Comparatively high rates of reliability for taken solutions were achieved that were estimated taking into account the variability of dynamic biometric patterns over time.
Authentication of computer users in real-time
by generating bit sequences based on keyboard
handwriting and face features
keyboard handwriting, facial features, authentication of computer users, recognition of subjects, biometric feature
https://www.elibrary.ru/item.asp?id=29457219

Lozhnikov P.S., Sulavko A.E., Buraya E.V., Pisarenko V.Yu. Authentication of computer users in real-time by generating bit sequences based on keyboard handwriting and face features // Issues of cybersecurity. - 2017. - No. 3. - pp. 24-34. DOI: 10.21681/2311-3456-2017-3-24-34

We consider the problem of user’s recognition in the process of working on a computer in the space of features of keyboard handwriting and face. Several approaches to the formation of solutions is proposed: network of perceptrons and Pearson-Hamming, Bayes-Pearson-Hamming, Bayes-Hamming networks. It was confirmed that the multi-dimensional Bayes functional works better with higher correlated features and when its dimension is higher. It is shown that for a variety features can be found some functional that best work with them. It was found that an increase in user monitoring time can be substantially reduced erroneous decisions due to more accurate calculation of the characteristic values. A method of generating keys (which can be used for encryption, authentication, digital signature algorithm) with probability of erroneous decisions, depending of user monitoring time when he works on a computer was proposed: 30 seconds - FRR = 0,002, FAR = 0,0036; 60 seconds - FRR = 0,002, FAR = 0,0009; 150 seconds - FRR <0,0005, FAR <0,0005.
Alternative scenarios of authorization at identification of users by dynamics of subconscious movements
biometric identification, methods of integration, image recognition, authorization, deception systems.
https://www.elibrary.ru/item.asp?id=19047630
Epifantsev B.N., Lozhnikov P.S., Sulavko A.E. Alternative scenarios of authorization at identification of users by dynamics of subconscious movements // Issues of information security / FSUE "VIMI". - Moscow: 2013, No. 2. pp. 28-35.
Proposed the concept of alternative scenarios of authorization for access control systems. Proposed
the algorithm of identification of users on the dynamics of unconscious movements with alternative scenarios
authorization. Conducted the experiment to evaluate the effectiveness of the algorithm.
The assesment of the identification capabilities of features of the user interacts аith a computer mouth
PATTERN RECOGNITION, BIOMETRIC SYSTEMS, IDENTIFICATION, AUTHENTICATION, ATTACKER, IDENTIFYING FEATURES, FEATURES OF WORKING WITH THE MOUSE
https://elibrary.ru/item.asp?id=24716609
Borisov R.V., Zverev D.N., Sulavko A.E., Pisarenko V.Yu. Assessing the identification capabilities of the user’s work with a computer mouse // Bulletin of the Siberian State Automobile and Road Academy / SibADI. - Omsk: SibADI, 2015, No. 5(45), pp. 106-113.
This article discusses the problem of Identity Theft Protection from unauthorized access in computer system. The method of user identification by features of user interacts with computer mouse based on a monitoring of subject activities and using Bayesian networks for identification decision making.
Made on
Tilda