ARCHITECTURE AND IMPLEMENTATION OF BASIC COMPONENTS OF NEURAL NETWORK PROTECTION SYSTEM AND DATA TRANSMISSION CODING

2022;
: 53-62
https://doi.org/10.23939/ujit2022.01.053
Received: May 06, 2022
Accepted: May 19, 2022

Ци­ту­вання за ДСТУ: Цмоць І. Г., Опо­тяк Ю. В., Різник О. Я., Бе­резь­кий О. М., Лу­ка­щук Ю. А. Архі­текту­ра та ре­алі­за­ція ба­зо­вих компо­нентів систе­ми нейро­ме­ре­же­во­го за­хисту і ко­ду­вання пе­ре­да­чі да­них. Укра­їнсь­кий журнал інформа­ційних техно­ло­гій. 2022, т. 4, № 1. С. 53–62.

Ci­ta­ti­on APA: Tsmots, I. G., Opo­ti­ak, Yu. V., Riznyk, O. Ya., Be­rezsky, O. M., & Lu­kashchuk, Yu. A. (2022). Archi­tectu­re and imple­menta­ti­on of ba­sic compo­nents of ne­ural network pro­tecti­on system and da­ta transmissi­on co­ding. Ukra­ini­an Jo­urnal of Informa­ti­on Techno­logy, 4(1), 53–62. https://doi.org/10.23939/ujit2022.01.053

1
Lviv Polytechnic National University, Lviv, Ukraine
2
Lviv Polytechnic National University, Department of Automated Control Systemst
3
Lviv Polytechnic National University, Lviv, Ukraine
4
Ternopil National University, Ternopil, Ukraine; Lviv Polytechnic National University, Lviv, Ukraine
5
Lviv Polytechnic National University, Lviv, Ukraine

The development of basic components of the neural network protection system, data transmission coding based on an integrated approach, which includes an improved method of neural network encryption (decryption) and the method of adaptive barker-like coding (decoding) of data, which focuses on modern element base. The principles of specialization and adaptation of hardware and software to the structure of algorithms for neuro-like encryption (decryption) of data, neural network architecture, and barker-like code are used to develop the system. The architecture of the system is proposed, which takes into account the variable composition of the equipment and modularity. The method of neural network encryption (decryption) of data has been improved. The time of neural network encryption and decryption of data depends on the size of the tables of macroparticle products. The size of the tables of pre-calculated macroparticle products is based on the provision of encryption and decryption of data in real-time. A method of adaptive barker-like encoding (decoding) has been developed, which, due to the signal-to-noise ratio, provides high noise immunity and reduces data transmission time. The hardware of the system, which was created using the developed basic components of neural network protection and barker-like data encoding, is described. When creating hardware, ready-made components and modules of industrial production are used as much as possible, and the availability of appropriate means of software code development is taken into account. Means of neural network cryptographic encryption (decryption) of data of the mobile part of the system are implemented using a microcomputer-based on SoC. Not the most powerful microcomputer of the NanoPi Duo type from FriendlyElec has been especially used to test the means of neural network cryptographic encryption (decryption) of data. Using the created system, it is determined that the performance of neural network cryptographic encryption (decryption) of data blocks based on a microcomputer is carried out in close to real-time. The time of formation and training of the neural network is about 200 ms, and the implementation of encryption and decryption procedures is about 35 ms and 30 ms, respectively, and does not depend significantly on the chosen configuration of the neural network.

[1]     Ar­van­di, M., Wu, S., Sa­deg­hi­an, A., Me­lek, W. W., & Wo­un­gang, I. (2006). Symmet­ric cip­her de­sign using re­cur­rent neu­ral net­works. Pro­ce­edings of the IEEE In­ter­na­ti­onal Jo­int Con­fe­ren­ce on Neu­ral Net­works, 2039–2046.

[2]     Chang, A. X. M., Mar­ti­ni, B., & Cu­lur­ci­el­lo, E. (2015). Re­cur­rent neu­ral net­works hardwa­re imple­men­ta­ti­on on FPGA: ar­Xiv prep­rint ar­Xiv:1511.05552.

[3]     Chi, Zhang, Wei, Zou, Li­ping, Ma, & Zhi­qing, Wang. (2020). Bi­olo­gi­cally inspi­red jum­ping ro­bots: A compre­hen­si­ve re­vi­ew, Ro­bo­tics and Au­to­no­mo­us Systems, vol. 124.
https://doi.org/10.1016/j.robot.2019.103362

[4]     Co­ro­na-Bermúdez, E., Chi­mal-Eguía, J. C., & Téllez-Cas­til­lo, G. (2022). Cryptog­rap­hic Ser­vi­ces Ba­sed on Ele­men­tary and Cha­otic Cel­lu­lar Au­to­ma­ta. Electro­nics, 11(4), 613.
https://doi.org/10.3390/electronics11040613

[5]     Di­aman­ta­ras, K. I., & Kung, S. Y. (1996). Prin­ci­pal Com­po­nent Neu­ral Net­works. The­ory and Appli­ca­ti­ons (Wi­ley, 1996), 270 p.

[6]     Ha­ikin, S. (2016). Neu­ral net­works: full co­ur­se ( 2nd ed . add. and re­vi­sed). (Trans. from English). Mos­cow: Wil­li­ams.

[7]     Khan, S., Han, L., Lu, H., Butt, K., Bac­hi­ra, G., & Khan, N. (2019). A New Hybrid Ima­ge Encrypti­on Al­go­rithm Ba­sed on 2D-CA, FSM-DNA Ru­le Ge­ne­ra­tor, and FSBI. IEEE Ac­cess 2019, 7, 81333–81350.
https://doi.org/10.1109/ACCESS.2019.2920383

[8]     Korchen­ko, O., Te­rey­kovsky, I., & Bi­loshchytsky, A. (2016). Met­ho­do­logy of de­ve­lop­ment of neu­ral net­work me­ans of in­for­ma­ti­on se­cu­rity of In­ter­net-ori­en­ted in­for­ma­ti­on systems. "Nash For­mat".

[9]     Os­ta­pov, S. (2013). In­for­ma­ti­on se­cu­rity techno­lo­gi­es. Khar­kiv: KhNEU.

[10]  Riz­nik, O. Ia., Tkac­hen­ko, R. O., & Ki­nash, Iu. Ye. (2019). Ne­iro­me­rez­he­va tekhno­lo­giia zak­his­tu ta pe­re­dac­hi da­nikh u re­al­no­mu cha­si z vi­ko­ris­tan­ni­am shu­mo­po­dib­nikh ko­div. In­no­vat­ci­ini tekhno­lo­gii u roz­vit­ku suc­has­no­go sus­pilstva: zbir­nik tez do­po­vi­dei mizhna­rod­noi nau­ko­vo-prak­tichnoi kon­fe­rentcii (Lviv, 18–19 kvit­nia 2019 r.), 19–23. [In Uk­ra­ini­an].
https://doi.org/10.1007/s00092-019-2378-8

[11]  Ru­den­ko, O., & Bod­yansky, E. (2006). Ar­ti­fi­ci­al neu­ral net­works. Khar­kiv: SMIT Com­pany Ltd.

[12]  Sa­gar, V., & Ku­mar, K. (2014). A Symmet­ric Key Cryptog­rap­hic Al­go­rithm Using Co­un­ter Pro­pa­ga­ti­on Net­work (CPN). Pro­ce­edings of the 2014 ACM In­ter­na­ti­onal Con­fe­ren­ce on In­for­ma­ti­on and Com­mu­ni­ca­ti­on Techno­logy for Com­pe­ti­ti­ve Stra­te­gi­es. https://doi.org/10.1145/2677855.2677906

[13]  Shi­hab, K. A. (2006). Backpro­pa­ga­ti­on neu­ral net­work for com­pu­ter net­work se­cu­rity. Jo­ur­nal of Com­pu­ter Sci­en­ce, vol. 2, no. 9, 710–715.

[14]  Śledź, S., Ewer­towski, M. W., & Pi­ekarczyk, J. (2021). Appli­ca­ti­ons of un­man­ned aeri­al ve­hic­le (UAV) sur­veys and Struc­tu­re from Mo­ti­on pho­tog­ram­metry in gla­ci­al and pe­rig­la­ci­al ge­omorpho­logy. Ge­omorpho­logy 2021, 378 p.
https://doi.org/10.1016/j.geomorph.2021.107620

[15]  Tcim­bal, Iu. V. (2018). Ne­iro­me­rez­he­vii me­tod si­met­richno­go shif­ru­van­nia da­nikh. Vis­nik Nat­ci­onal­no­go uni­ver­si­te­tu "Lvivska po­li­tekhni­ka". Se­riia: In­for­mat­ci­ini sis­te­mi ta me­rez­hi, 901, 118–122. [In Uk­ra­ini­an].

[16]  Te­rey­kovsky, I. (2007). Neu­ral net­works in the me­ans of pro­tec­ti­on of com­pu­ter in­for­ma­ti­on. Polygraph Con­sul­ting.

[17]  Tkac­hen­ko, R., Tkac­hen­ko, P., Izo­nin, I., & Tsymbal, Y. (2018). Le­ar­ning-ba­sed ima­ge sca­ling using neu­ral-li­ke struc­tu­re of ge­omet­ric transfor­ma­ti­on pa­ra­digm. Ad­van­ces in Soft Com­pu­ting and Mac­hi­ne Le­ar­ning in Ima­ge Pro­ces­sing, Sp­rin­­ger, 537–565. https://doi.org/10.1007/978-3-319-63754-9_25

[18]  Tsmots, I. G., Ra­bik, V. G., & Lu­kashhuk, Iu. A. (2021). Roz­rob­len­nia mo­bil­nikh za­so­biv ne­iro­po­dib­no­go krip­tog­ra­fichno­go shif­ru­van­nia ta des­hif­ru­van­nia da­nikh u re­al­no­mu cha­si. Vis­nik Nat­ci­onal­no­go uni­ver­si­te­tu "Lvivska po­li­tekhni­ka". Se­riia: In­for­mat­ci­ini sis­te­mi ta me­rez­hi, 9, 84–95. [In Uk­ra­ini­an].
https://doi.org/10.23939/sisn2021.09.084

[19]  Tsmots, I., Rabyk, V., Riznyk, O., & Kynash, Y. (2019). Met­hod of Synthe­sis and Prac­ti­cal Re­ali­za­ti­on of Qua­si-Bar­ker Co­des. 2019 IEEE 14th In­ter­na­ti­onal Con­fe­ren­ce on Com­pu­ter Sci­en­ces and In­for­ma­ti­on Techno­lo­gi­es (CSIT), Lviv, Uk­ra­ine, 76–79. https://doi.org/10.1109/STC-CSIT.2019.8929882

[20]  Tsmots, I., Teslyuk, V., Teslyuk, T., Lu­kashchuk, Y. (2021). The met­hod and si­mu­la­ti­on mo­del of ele­ment ba­se se­lec­ti­on for pro­tec­ti­on system synthe­sis and da­ta transmis­si­on. In­ter­na­ti­onal Jo­ur­nal of Sen­sors, Wi­re­less Com­mu­ni­ca­ti­ons and Control, 11(5), 518–530. https://doi.org/10.2174/2210327910999201022194630

[21]  Tsmots, I., Tsymbal, Y., Kha­val­ko, V., Sko­rok­ho­da, O., & Tes­luyk, T. (2018). Neu­ral-Li­ke Me­ans for Da­ta Stre­ams Encrypti­on and Decrypti­on in Re­al Ti­me. Pro­ces­sing of the 2018 IEEE 2nd In­ter­na­ti­onal Con­fe­ren­ce on Da­ta Stre­am Mi­ning and Pro­ces­sing, DSMP 2018, 438–443.
https://doi.org/10.1109/DSMP.2018.8478513

[22]  Tsmots, I., Tsymbal, Yu., Sko­rok­ho­da, O., & Tkac­hen­ko, R. (2019). Neu­ral-li­ke Met­hods and Hardwa­re Struc­tu­res for Re­al-ti­me Da­ta Encrypti­on and Decrypti­on. Pro­ce­edings of 14th In­ter­na­ti­onal Sci­en­ti­fic and Techni­cal Con­fe­ren­ce (CSIT), Lviv, Uk­ra­ine, 3. 248–253.
https://doi.org/10.1109/STC-CSIT.2019.8929809

[23]  Tsymbal, Yu. (2018). Neu­ral net­work met­hod of symmet­ric da­ta encrypti­on. Bul­le­tin of the Lviv Polytechnic Na­ti­onal Uni­ver­sity. In­for­ma­ti­on systems and net­works, 901, 118–122.

[24]  Ver­ma, A., & Ran­ga, V. (2020). Se­cu­rity of RPL ba­sed 6LoW­PAN Net­works in the In­ter­net of Things: A Re­vi­ew. IEEE Sens. J., 20, 5666–5690.
https://doi.org/10.1109/JSEN.2020.2973677

[25]  Vol­na, E., Kotyrba, M., Ko­ci­an, V., & Ja­no­sek, M. (2012). Cryptog­raphy Ba­sed On Neu­ral Net­work. Pro­ce­edings of the 26th Eu­ro­pe­an Con­fe­ren­ce on Mo­de­ling and Si­mu­la­ti­on, 386–391.
https://doi.org/10.7148/2012-0386-0391

[26]  Wang, M., Cong, S., & Zhang, S. (2018). Pseu­do Chirp-Bar­ker-Go­lay co­ded ex­ci­ta­ti­on in ultra­so­und ima­ging, 2018 Chi­ne­se Control And De­ci­si­on Con­fe­ren­ce (CCDC), Shen­yang, 4035–4039.
https://doi.org/10.1109/CCDC.2018.8407824

[27]  Wang, S., & He, P. (2018). Re­se­arch on Low In­ter­cep­ting Ra­dar Wa­ve­form Ba­sed on LFM and Bar­ker Co­de Com­po­si­te Mo­du­la­ti­on, 2018 In­ter­na­ti­onal Con­fe­ren­ce on Sen­sor Net­works and Sig­nal Pro­ces­sing (SNSP), Xi­an, Chi­na, 297–301. https://doi.org/10.1109/SNSP.2018.00064

[28] Zhou, K., Kang, Y., Hu­ang, Y., & Feng, E. (2007). Encrypting Al­go­rithm Ba­sed on RBF Neu­ral Net­work. Pro­ce­edings of the IEEE Third In­ter­na­ti­onal Con­fe­ren­ce on Na­tu­ral Com­pu­ta­ti­on, 1, 765–768.
https://doi.org/10.1109/ICNC.2007.353