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.
Protection of hybrid document flow using digital signature with biometric activation

Is it possible to convert a handwritten signature to an digital signature and apply it to a paper document?

The developed technology allows this to be done to protect legally significant documents on electronic and paper media from threats to integrity and authenticity.

Information security threats in mixed document flow
The most significant shortcomings of document management systems are due to the problem of “alienation” of digital signature (ES) keys from the owner, which can lead to the falsification of legally significant decisions and the implementation of other related threats. Another important problem is the impossibility of automated verification of integrity and authenticity, as well as the use of digital signatures and other cryptographic mechanisms in relation to “paper” implementations of a document, which leads to lower security of the document when distributed “on paper”.
A solution to these problems has been proposed by creating hybrid neural network biometric-code converters (BCCs) and procedures for converting “paper” document implementations into electronic form.
A handwritten signature is converted into a digital signature key
using a hybrid biometric-to-code converter
The handwritten image is converted into a feature vector, after which it is fed to the input of a hybrid network consisting of quadratic, Bayesian, and classical neurons. At the network output, a digital signature key appears. The pre-hybrid BBC “learns” to convert a handwritten image into a cryptographic key. After the introduction of a digital signature with biometric activation, the route of the hybrid document changes.
Hybrid Document Lifecycle
BEFORE and AFTER the implementation of digital signature with biometric activation

Key publications
on the topic "Biometric protection of hybrid document flow"
Biometric protection of hybrid document flow
The monograph outlines a range of current problems for mixed document flow protection systems. It is proposed to move to the concept of hybrid document flow. The key difference is the use of biometric characteristics in the formation of a private (secret) digital signature (ES) key. A model and technology for protecting hybrid document flow based on biometric data of handwritten images, keyboard handwriting and face has been developed. The indicated features were analyzed, and their informativeness was assessed. Modern algorithms for forming decisions in recognizing subjects and generating key sequences based on biometric data (fuzzy extractors, neural network biometric-code converters based on perceptrons and a learning algorithm according to GOST R 52633.5-2011, networks of quadratic forms, multidimensional Bayesian functionals and other functionals) are considered. Optimal algorithms for solving the assigned problems have been determined. A number of important theses have been identified and experimentally confirmed.

authentication, digital signature with biometric activation, handwritten signature, biometric image, biometric-code converters, correlation between features, mixed document flow, information security, neural networks, Bayes formula
P.S. Lozhnikov. Biometric protection of hybrid document flow: monograph / Novosibirsk: Publishing House SB RAS, 2017. - 130 p.
Evaluation of signature verification reliability based on artificial neural networks, Bayesian multivariate functional and quadratic forms
neural networks, network of quadratic forms, multi-dimensional Bayes functional, signature reproduction peculiarities, biometric features

Ivanov AI, Lozhnikov PS, Sulavko AE. Evaluation of signature verification reliability based on artificial neural networks, Bayesian multivariate functional and quadratic forms. Computer Optics 2017; 41(5): 765-774. DOI: 10.18287/2412-6179-2017-41-5-765-774.

An experimental comparison of various functional neural networks for signature verification is performed. A signature database for the realization of the computing experiment is built. It is confirmed that up to a certain point, the increase of the decision rule dimension reduces the probability of signature verification error, with an increase in the number of neurons in the network reducing the number of errors. A higher-dimension multi-dimensional Bayes functional with stronger inter-feature correlation is found to perform better. The best result for the signature verification is obtained using networks of Bayesian multidimensional functional, with false acceptance rate of FRR= 0.0288 and false rejection rate of FAR = 0.0232.
Methods of Generating Key Sequences Based on Parameters of Handwritten Passwords and Signatures
signature reproduction peculiarities; fuzzy extractors; a handwritten password; an encryption key; biometrics
Lozhnikov P.S., Sulavko A.E., Eremenko A.V., Volkov D.A. Methods of Generating Key Sequences based on Parameters of Handwritten Passwords and Signatures. Information. MDPI. - 2016, №7(4), 59; doi:10.3390/info7040059.
The modern encryption methods are reliable if strong keys (passwords) are used, but the human factor issue cannot be solved by cryptographic methods. The best variant is binding all authenticators (passwords, encryption keys, and others) to the identities. When a user is authenticated by biometrical characteristics, the problem of protecting a biometrical template stored on a remote server becomes a concern. The paper proposes several methods of generating keys (passwords) by means of the fuzzy extractors method based on signature parameters without storing templates in an open way.
Experimental Evaluation of Reliability of Signature Verification by Quadratic Form Networks, Fuzzy Extractors and Perceptrons
Signature Reproduction Features, Biometrics, Fuzzy Extractors, Artificial Neural Networks, Authentication.
view the work on

Lozhnikov P.S., Sulavko A.E., Eremenko A.V., Volkov D.A. Experimental assessment of the reliability of signature verification using networks of quadratic forms, fuzzy extractors and perceptrons // Information and control systems. - 2016. - №. 5. - P. 73-85.

Purpose: The problems of information security become more and more pressing, therefore the demands to biometric systems become tougher. Our objective is to compare fuzzy extractors, neural network biometry-code converters and networks of quadratic forms by their authentication reliability, on the base of signature features. Results: We have analyzed the literature and conducted a series of numerical experiments based on real biometric data. The main result of the experiments is that fuzzy extractors are significantly inferior to the other system by their authentication reliability and the key length. The best performance was provided by Bayesian– Pearson networks. Practical relevance: The results will be of interest to researchers and developers of biometric systems
Identification Potential of Online Handwritten Signature Verification
information security, subconscious movements, identification of signers, artificial intelligence, natural intelligence, comparison of intelligence capabilities, identification of subject states
view the work on

Epifantsev B.N., Lozhnikov P.S., Sulavko A.E., Zhumazhanova S.S. Identification potential of handwritten passwords in the process of their reproduction // Autometry. 2016. No. 3, pp. 28-36.

Epifantsev B.N., Lozhnikov P.S., Sulavko A.E., Zhumazhanova S.S. Identification Potential of Online Handwritten Signature Verification // Optoelectronics, Instrumentation and Data Processing. 2016, №3(52), p. 238-244. doi:10.3103/S8756699016030043

This paper presents a comparison of natural and artificial intelligences in identifying operators of information-processing systems and their functional state based on handwriting. The cause of the large scatter in the person identification error probability is determined. It is concluded that at the present level of knowledge, the best result achieved in solving the problem by artificial intelligence systems is close to that potentially possible. It is substantiated that online handwritten signature verification is suitable for identifying the functional state of operators of human-machine systems in professional activities.
A model of protection of hybrid documents on the basis of handwritten signatures with an assessment of psychophysiological state of signers

Lozhnikov P.S., Sulavko A.E., Samotuga A.E. Model for the protection of hybrid documents based on the handwritten signatures of their owners, taking into account the psychophysiological state of the signatories // Issues of information protection / FSUE "STC of the defense complex "Compass". - Moscow: 2016. - No. 4. - pp. 47-59.

At the present time the most prevalent document flow is a mixed document flow. Authors suggest move to hybrid document flow which is the further development of mixed document flow. It is proposed to combine a secret key of electronic digital signature with features of signature images reproduction of electronic digital signature owner. The model of hybrid document security on the basis of handwritten signatures of subjects with a psychophysiological state assessment of signers was designed. The computational experiment of assessing the reliability of obtaining the secret keys on the basis of biometric data of a signature was carried out.
Usage of fuzzy extractors in a handwritten-signature based technology of protecting a hybrid document management system
hybrid document, authentication, encryption key generation, subject signature, biometrics
view the work on

Lozhnikov P.S., Sulavko, A.E., Volkov D.A. Usage of fuzzy extractors in a handwritten-signature based technology of protecting a hybrid document management system / 2016 10th International Conference on Application of Information and Communication Technologies (AICT), 12-14 October 2016, Baku, Azerbaijan – p.395-400.

The paper covers the issue of protecting private keys of a digital signature in a hybrid document management system. It proposes a method of generating private keys based on a handwritten signature using a method of building a reference signature description. The method demonstrates the following indicators of reliability: FRR=0.148, FAR=0.05 when the length of the key is 304 bits.
On the possibility of introducing distributed registry technologies into mixed document flow systems

electronic document management systems, hybrid document, distributed registry systems, blockchain technologies, biometrics, electronic digital signature
Lozhnikov P.S., Sulavko A.E., Zhumazhanova S.S. On the possibility of introducing distributed registry technologies into mixed document flow systems // Information Technology Security. 2019. No. 1 (26). pp. 15–24.

The paper presents a study of the possibility of using distributed registry technologies to manage various business processes based on electronic document management systems. In the field of finance and trade, a type of distributed registry technology called blockchain has already been presented as a real alternative to the existing infrastructure, but there is currently insufficient experience in creating and implementing such solutions in electronic document management systems. The hybrid document flow model previously proposed by the authors has a number of advantages over the usual information exchange scheme since it combines equal protection of documents in analog and digital form with the use of cryptographic and biometric methods. The hybrid document flow scheme based on distributed registry technologies ensures decentralized storage of information, a fixed volume of data blocks stored and transmitted by users, the generation of cryptographic keys using biometric images of authorized users, and the identification of subjects who performed various actions with the document, regardless of the type of its media. The work examines possible problems of information interaction that society may encounter when developing and implementing a hybrid document flow scheme.

Made on