FORMATION OF PARAMETERS OF INFORMATION SOURCES FOR NEURO-LINGUISTIC TEXT IDENTIFICATION
Abstract
This paper explores a method of neurolinguistic text identification aimed at analyzing and verifying information sources, including texts generated by artificial intelligence systems. Three versions of the information states of the text of Luo Guanzhong's Romance of the Three Kingdoms are analyzed: the original text and the text generated by the Gemini and GPT artificial intelligence systems. The study aims to formulate and substantiate parameters for use as identification factors in the generated text, as well as to create 3D images of neurolinguistic textual identification of information sources. The specialized software package "Neurolinguistic Text Identification Analyzer" is used, processing text data based on horizontal and vertical scanning of neurolinguistic information frames. As a result, information spectra, quantitative characteristics (information capacity, entropy, redundancy), and 3D neurolinguistic information images of neurolinguistic frames of textual information of the Chinese work are formed. A comparison of the identity levels of neurolinguistic 3D informational images of the textual information source and neurolinguistic information frames shows that the highest level of identity is observed when comparing the texts of neurolinguistic information frames with the original text, while the lowest level of identity is observed when comparing the original text with the text generated using neural networks. The obtained results demonstrate significant differences between the parameters of the neurolinguistic information frames of the original text and the parameters of the text generated by neural networks, both in terms of quantitative text characteristics and the characteristics of the neurolinguistic 3D informational images. It was found that the neurolinguistic 3D informational images of texts generated by neural networks have a smoother visual representation structure and an excellent color distribution compared to the neurolinguistic 3D images of the original text. The practical significance of this study lies in the application of an approach that allows for the identification of generated text and the verification of information sources. The obtained results open up prospects for further work and the possibility of creating programs capable of detecting the presence of text generation
References
1. Kotenko V.V. Tekhnologii informatsionnogo analiza pol'zovatel'skogo urovnya telekommunikatsionnykh sistem: ucheb. Posobie [Technologies of information analysis of the user level of telecommunication sys-tems: a textbook]. Rostov-on-Don – Taganrog: Izd-vo YuFU, 2019, 194 p.
2. Federal'nyy zakon №572 ot 29 dekabrya 2022 g. «Ob osushchestvlenii identifikatsii i (ili) autentifikatsii fizicheskikh lits s ispol'zovaniem biometricheskikh personal'nykh dannykh» [Federal Law No. 572 of December 29, 2022 "On the Identification and (or) Authentication of Individuals using Biometric per-sonal Data"].
3. Mitchell E., Lee Y., Khazatsky A., Manning C.D., and Finn C. Detectgpt: Zero-shot machine-generated text detection using probability curvature, In International Conference on Machine Learning, 2023, pp. 24950-24962. PMLR.
4. Kotenko V.V. Teoriya virtualizatsii i zashchita telekommunikatsiy: monografiya [Theory of virtualization and protection of telecommunications: a monograph]. Taganrog: Izd-vo TTI YuFU, 2011, 236 p.
5. Bao G., Zhao Y., Teng, Z., Yang L., and Zhang Y. Fast-DetectGPT: Efficient Zero-Shot Detection of MachineGenerated Text via Conditional Probability Curvature, In the Twelfth International Conference on Learning Representations, 2024.
6. Kornienko V.T., Giniyatullin L.P. Ispol'zovanie akusticheskoy golografii v sistemakh videonablyudeniya opticheski neprozrachnykh kontroliruemykh ob"emov [The use of acoustic holography in video surveil-lance systems of optically opaque controlled volumes], Informatsionnoe protivodeystvie ugrozam ter-rorizma [Information Counteraction to Terrorist Threats], 2010, No. 15, pp. 123-126.
7. Pron' E.V. Biometricheskaya sistema kontrolya dostupa na zakrytye ob"ekty putem raspoznavaniya lits lyudey v tolpe po signalam s kamer videonablyudeniya [Biometric access control system for closed facil-ities by recognizing people's faces in a crowd based on signals from surveillance cameras], Aktual'nye problemy aviatsii i kosmonavtiki [Actual Problems of Aviation and Cosmonautics], 2017, Vol. 2, pp. 218-220.
8. Glazkova A.V. Sravnenie neyrosetevykh modeley dlya klassifikatsii tekstovykh fragmentov, soderzhash-chikh biograficheskuyu informatsiyu [Comparison of neural network models for classifying text frag-ments containing biographical information], Programmnye produkty i sistemy [Software products and systems], 2019, Vol. 32, No. 2, pp. 65-69.
9. Tel'pov R.E., Lartsina S.V. Tipovye razlichiya estestvennykh i sgenerirovannykh neyronnoy set'yu tekstov v kvantitativnom aspekte [Typical differences between natural and neural network-generated texts in the quantitative aspect], Nauchnyy dialog [Scientific Dialogue], 2023, Vol. 12, No. 7, pp. 47-65.
10. Aydagulova A.R. Osobennosti tekstov, sgenerirovannykh iskusstvennym intellektom [Features of texts generated by artificial intelligence], Vestnik Bashkirskogo gosudarstvennogo pedagogicheskogo univer-siteta im. M. Akmully [Bulletin of the Bashkir State Pedagogical University named after M. Akmulla], 2023, No. 4 (72). Available at: https://cyberleninka.ru/article/n/osobennosti-tekstov-sgenerirovannyh-iskusstvennym-intellektom (accessed 13 September 2025).
11. Ukaz Prezidenta RF ot 10 oktyabrya 2019 g. № 490. «Natsional'naya strategiya razvitiya iskusstvennogo intellekta do 2030 goda v Rossiyskoy Federatsii» [Decree of the President of the Russian Federation No. 490 dated October 10, 2019. "National Strategy for the Development of Artificial Intelligence until 2030 in the Russian Federation"].
12. Kotenko V.V., Rumyantsev K.E., Khadzhieva L.K. Otsenka vozmozhnostey neyrolingvisticheskoy identi-fikatsii sistem iskusstvennogo intellekta [Assessment of the possibilities of neuro-linguistic identification of artificial intelligence systems], Vestnik UrFO. Bezopasnost' v informatsionnoy sfere [Bulletin of the Ural Federal District. Information Security], 2024, No. 2 (52), pp. 13-24.
13. Kurtukova A.V., Romanov A.S., Fedotova A.M., Shelupanov A.A. Arkhitektura intellektual'noy sistemy dlya identifikatsii avtora iskhodnogo koda [Architecture of an intelligent system for identifying the au-thor of the source code], Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radi-oelektroniki [Reports of Tomsk State University of Control Systems and Radio Electronics], 2022, Vol. 25, No. 3, pp. 39-44. DOI: 10.21293|1818-0442-2022-25-3-39-44.
14. Kotenko V.V., Rumyantsev K.E., Khadzhieva L.K. Parametry neyrolingvisticheskoy identifikatsii sistem iskusstvennogo intellekta [Parameters of neuro-linguistic identification of artificial intelligence sys-tems],Vestnik UrFO. Bezopasnost' v informatsionnoy sfere [Bulletin of the Ural Federal District. Infor-mation Security], 2024, No. 3 (53), pp. 32-43.
15. Siyuan Li, Xi Lin, Guangyan Li, Zehao Liu, Aodu Wulianghai, Li Ding, Jun Wu, Jianhua Li. Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection License: arXiv.org perpetual non-exclusive license arXiv:2508.06913v1 [cs.CL] 09 Aug 2025.
16. Rumyantsev K.E., Khadzhieva L.K. Analiz primeneniya neyrolingvisticheskoy identifikatsii sistem is-kusstvennogo intellekta [Analysis of the application of neuro-linguistic identification of artificial intelli-gence systems], Sovremennye metody, sredstva i tekhnologii zashchity informatsii – 2024: Sb. trudov XV Mezhdunarodnoy nauchno-prakticheskoy konferentsii imeni Olega Borisovicha Makarevicha [Mod-ern methods, means and technologies of information protection – 2024: Proceedings of the XV Interna-tional Scientific and Practical Conference named after Oleg Borisovich Makarevich]. Taganrog, 2024, pp. 188-192.
17. Chakraborty S., Bedi A., Zhu S., An B., Manocha D., and Huang F. Position: On the possibilities of AIgenerated text detection, In Forty-first International Conference on Machine Learning, 2024.
18. Bryukhomitskiy Yu.A. Model' sistemy biometricheskoy verifikatsii pol'zovateley informatsionnykh sistem [Model of the biometric verification system for information systems users], Izvestiya YuFU. Tekhniches-kie nauki [Izvestiya SFedU. Engineering Sciences], 2024, No. 2 (238), pp. 17-25.
19. Bryukhomitskiy Yu.A. Immunologicheskaya model' tekstonezavisimoy golosovoy identifikatsii lichnosti [Immunological model of text-independent voice identification], Izvestiya YUFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2022, No. 2 (226). – S. 6-13.
20. Khadzhieva L.K., Kotenko V.V., Rumyantsev K.E. Neyrolingvisticheskaya informatsionnaya identif-ikatsiya intellektual'nykh sistem [Neuro-linguistic information identification of intelligent systems], Izvestiya YUFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2024, No. 3 (239), pp. 33-44.
21. Chernigovskaya T.V. Estestvennyy i iskusstvennyy intellekt: smysly ili struktury [Natural and artificial intelligence: meanings or structures], Chelovek i sistemy iskusstvennogo intellekta [Man and artificial in-telligence systems]. St. Petersburg: Izd-vo «Yuridicheskiy tsentr», 2022, pp. 160-171.
22. Lektorskiy V.A., Vasil'ev S.N., Makarov V.L. [i dr.]. Chelovek i sistemy iskusstvennogo in-tellekta [Man and artificial intelligence systems]. St. Petersburg: Izd-vo «Yuridicheskiy tsentr», 2022. – 328 s. ISBN 978-5-94201-835-1. EDN XSBHKY.
23. Litvinova T. Authorship attribution of russian social media texts: does the volume of data favor idiolect identification?, Lecture Notes in Networks and Systems, 2022, Vol. 315, pp. 352-362.
24. Juan Liu, Min Hu, Ying Wang, Zhong Huang, Julang Jiang. Symmetric Multi-Scale Residual Network Ensemble with Weighted Evidence Fusion Strategy for Facial Expression Recognition, Symmetry, 2023, 15 (6), pp. 1228.
25. Gehrmann S., Strobelt H., & Rush A.M. GLTR: Statistical detection and visualization of generated text, In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2019, July, pp. 111-116.
26. Hans A., Schwarzschild A., Cherepanova V., Kazemi H., Saha A., Goldblum M., Geiping J., and Gold-stein T. Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text, In Interna-tional Conference on Machine Learning, 2024, pp. 17519-17537. PMLR.
27. Zhang S., Song Y., Yang J., Li Y., Han B., and Tan M. Detecting Machine-Generated Texts by Mul-tiPopulation Aware Optimization for Maximum Mean Discrepancy, In The Twelfth International Con-ference on Learning Representations, 2024.
