Implementation of an adaptive authentication system using an EEG interface

The work offers methodological support for critical information infrastructure objects, which provides for the systematization of the basic steps for the formation of adaptive authentication algorithms, including using a biometric factor, which consists in checking the electroencephalogram of the access subject. The proposed approach eliminates the drawbacks of existing traditional authentication methods based on the use of explicit verification methods related to the fact that authentication characteristics are used to authenticate the user, which can be compromised by attackers. During the research, an authentication subsystem was implemented using the brain-computer interface. Despite the resistance to errors of the second kind, the insufficient results of the false access denial coefficient obtained at the stage of the experiment do not allow for the “seamless” implementation of such biometric authentication mechanisms in existing objects of critical information infrastructure. At the same time, the effectiveness of the adaptive mechanisms for checking the user profile formed on the basis of the approach proposed in the work indicates the possibility of their use on real objects using diverse factors and authentication criteria. Thus, in the framework of this article, one of the aspects of an integrated approach to ensure the security of the functioning of technological processes, as well as combating fraud and theft of information through the formation of adaptive authentication algorithms, was considered.

1. Dvojnishnikov N.E. Technological features of the problems of ensuring the information security of automated control systems that are objects of critical information infrastructure. International Journal of Applied Sciences and Technologies “Integral”. 2019;1:127-132.

2. Arakelyan E.K., Andryushin A.V., Minzov A.P. Features of information security systems for process control systems of thermal and nuclear power plants. Doklady BGUIR. 2015;2:213-214. (In Russ.)

3. Goncharov S.M., Vishnyakov M.S. User identification based on electroencephalography data using «Brain Computer Interface» technology. Proceedings of Tomsk State University of Control Systems and Radioelectronics. 2012:1-2(25):166-170. (In Russ.)

4. Damasevicius R., Maskeliunas R., Kazanavicius E., Wozniak M. Combining Cryptography with EEG Biometrics. Computational Intelligence and Neuroscience. 2018:1867548.

5. Kuzmin O.V., Druzhinin V.I. Bose – Chaudhuri – Hocquenghem codes in systems of detection and correction of errors when transferring data. Modern technologies. System analysis. Modeling. 2013;3(39):23-29. (In Russ.)

6. Goncharov S., Borshevnikov A. Neural network transformer “Biometry – access code” based on the electroencephalogram in modern cryptographic applications. Vestnik SibGUTI. 2016;1:17-22. (In Russ.)

7. Hu B., Liu Q., Zhao Q., Qi Y., Peng H. A real-time electroencephalogram (EEG) based individual identification interface for mobile security in ubiquitous environment. 2011 IEEE Asia-Pacific Services Computing Conference. 2011:436-441.

8. Marcel S., Millan J. del R. Person authentication using brainwaves (EEG) and maximum a posteriori model adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2007;29;4:743–748.

9. Yang S., Deravi F. On the Usability of Electroencephalographic Signals for Biometric Recognition: A Survey. IEEE Transactions on Human-Machine Systems. 2017;47;6:958– 969.

10. Rahman M.W., Gavrilova M. Overt mental stimuli of brain signal for person identification. 2016 International Conference on Cyberworlds. 2016:197–203.

11. Chan H.-L., Kuo P.-C., Cheng C.-Y., Chen, Y.-S. Challenges and Future Perspectives on Electroencephalogram-Based Biometrics in Person Recognition. Frontiers in Neuroinformatics. 2018;12:1–15.

12. Iskhakov A.Y., Meshcheryakov R.V. Patterns user authentication in the ACS using QR codes and data technology NFC. Information counteraction to threats of terrorism. 2014;22:11-15. (In Russ.)

13. Bogdanov D.S., Klyuev S.G. Сlassification and comparative analysis of technologies of multifactor authentication in Web applications. Modeling, optimization and information technology. 2020;8(1). (In Russ.)

14. Iskhakov, A. Y., Iskhakova, A. O., Meshcheryakov, R. V., Bendraou, R., Melekhova, O. Application of User Behavior Thermal Maps for Identification of Information Security Incident. SPIIRAS Proceedings. 2018;6(61):147-171.

15. Haikin S. Neural Networks: a complete course, 2nd ed.– M.: Williams Publishing House. 2006. (In Russ.)

16. Lebedeva N.N., Karimova E.D. Stability of human EEG patterns in different tasks: the personality authentication problem. Neuroscience and Behavioral Physiology, 2020;70(1):40-49. (In Russ.)

17. Sulavko A.E., Samotuga A.E., Stadnikov D.G., Pasenchuk V.A, Zhumazhanova S.S. Biometric authentication based on electroencephalogram parameters. Materials of the III International Scientific and Technical Conference Problems of Engineering. 2019;2:375- 384. (In Russ.)

18. Evsutin O.O., Meshcheryakov R.V., Shumskaya O.O. Steganalysis of digital images with use of the naive Bayes classifier. Materials of the 10th All-Russian Multi-Conference MKPU-2017. 2017:56-58. (In Russ.)

19. Usmonov B., Evsutin O., Iskhakov A., Shelupanov A., Iskhakova A., Meshcheryakov R. The cybersecurity in development of IoT embedded technologies. 2017 International Conference on Information Science and Communications Technologies (ICISCT). 2017:1- 4.

20. Iskhakov S.Yu., Shelupanov A.A., Iskhakov A.Y. Engineering of imitation model of a complex network of security systems. Proceedings of Tomsk State University of Control Systems and Radioelectronics. 2014;2(32):82–86.