Neural Cryptography Based on Tree Parity Machine to Generate OTP

Authors

  • Vera Wati
  • Nur Fitrianingsih Hasan

Keywords:

Cryptography, Neural Cryptography, One Time Pad, Neural Network, Tree Parity Machine

Abstract

The rapid development of cloud computing increases cybersecurity risks, including hacktivism, phishing, fraud, and OTP theft. In addition to user education, further security technologies are required, such as one-time authentication at the main gateway or as an extra layer within the application system. OTP, generated through cryptographic techniques, is an effective security method because it can only be used once and does not require additional device installation. If implemented correctly, OTP provides a high level of confidentiality. Artificial Neural Networks (ANNs) are an innovation in neural cryptography. TPM ANNs, which apply synchronized learning to parity machines, can learn independently based on input, hidden, and output parameters. This study proposes the implementation of OTP ANN with TPM to improve system security. The integration of OTP with TPM on the login menu using a web server aims to generate more random keys with ideal parameters K ≥ 4, N ≥ 5, and L ≥ 5. As a result, real-time OTPs can be sent via Telegram and Email, offering a more secure and efficient encryption solution in real-world applications. Compared to deterministic OTP approaches that rely on hashes of fixed time values and parameters, TPM-based stochastic approaches offer advantages in terms of entropy and cryptographic uncertainty. Deterministic OTPs are time-efficient, but are vulnerable to prediction if the seed is not accompanied by an additional secret. In contrast, TPM-based stochastic OTPs are more resistant to predictive attacks due to their complex synchronization properties and independence from system time, making them more suitable for high-risk authentication scenarios.

References

N. Sanchiga Nandhini and P. Arumugam, “Digital currency banking using block chain technology,” World J. Adv. Eng. Technol. Sci., vol. 8, no. 1, pp. 053–061, 2023, https://doi.org/10.30574/wjaets.2023.8.1.0011.

M. Hammed and A.B. Adesi, “Authentication scheme using tree parity artificial neural networks for fraud detection in an on-line banking system,” Proceedings of the 4th National Development Conference of the School of Pure and Applied Science, 2019, pp. 257–265.

S. Matelski, “Universal key to authentication authority with human-computable OTP generator,” Proceedings of the 2022 17th Conference on Computer Science and Intelligence Systems (FedCSIS), 2022, pp. 663–671. https://doi.org/10.15439/2022F71.

R. A. Grimes, One‐Time Password Attacks, Wiley, 2021.

K. Brindhashree and S. J. Prakash, “Data security based on cryptography, steganography combined with OTP algorithm and Huffman coding in the cloud environment,” Int. Res. J. Mod. Eng. Technol. Sci., vol. 2, no. 10, pp. 441–447, 2020.

F. Ramadhani, U. Ramadhani, and L. Basit, “Combination of hybrid cryptography in one time pad (OTP) algorithm and keyed-hash message authentication code (HMAC) in securing the WhatsApp communication application,” J. Comput. Sci. Inf. Technol. Telecommun. Eng., vol. 1, no. 1, pp. 31–36, 2020, https://doi.org/10.30596/jcositte.v1i1.4359.

M. Ziaurrahman, E. Utami, and F. W. Wibowo, “Modifikasi Kriptografi Klasik Vigenere Cipher Menggunakan One Time Pad Dengan Enkripsi Berlanjut,” J. Inform. dan Teknol. Inf., vol. 4, no. 1, p. (halaman 2), 2019. (in Indonesian).

M. Ashiqul Islam, A. A. Kobita, M. Sagar Hossen, L. S. Rumi, R. Karim, and T. Tabassum, “Data security system for a bank based on two different asymmetric algorithms cryptography,” Lect. Notes Data Eng. Commun. Technol., vol. 53, no. January, pp. 837–844, 2021, https://doi.org/10.1007/978-981-15-5258-8_77.

M. Volkmer and S. Wallner, “Tree parity machine rekeying architectures,” IEEE Trans. Comput., vol. 54, no. 4, pp. 421–427, 2005. https://doi.org/10.1109/TC.2005.70.

A. P. Veera Manindra and B. Karthikeyan, “OTP camouflaging using LSB steganography and public key cryptography,” Proceedings of the 2022 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), 2022, pp. 109–115. https://doi.org/10.1109/ICESC54411.2022.9885542.

B. T. Hammad, A. M. Sagheer, I. T. Ahmed, and N. Jamil, “A comparative review on symmetric and asymmetric DNA-based cryptography,” Bull. Electr. Eng. Informatics, vol. 9, no. 6, pp. 2484–2491, 2020, https://doi.org/10.11591/eei.v9i6.2470.

N. G. N. Amma and F. R. Dhanaseelan, “Optimal privacy preserving scheme based on modified ANN and PSO in cloud,” Res. Anthol. Priv. Secur. Data, pp. 773–793, 2021, https://doi.org/10.4018/978-1-7998-8954-0.ch035.

S. Jeong, C. Park, D. Hong, C. Seo, and N. Jho, “Neural cryptography based on generalized tree parity machine for real-life systems,” Secur. Commun. Networks, vol. 2021, 2021, https://doi.org/10.1155/2021/6680782.

S. Y. Yan, Computational Number Theory and Modern Cryptography, Google Books, [Online]. Available at: https://books.google.co.id/books?hl=id&lr=&id=74oBi4ys0UUC&oi=fnd&pg=PR9&dq=Typically,+in+many+modern+cryptography+methods,+algebraic+number+theory+is+involved+&ots=fR44FTmYIO&sig=2DazU2MVXoRT-kb7vI6G65tFt_c&redir_esc=y#v=onepage&q=Typically%2C in many modern cryptography methods%2C algebraic number theory is involved&f=false.

Z. Zheng, Modern Cryptography Volume 1, Springer, 2022, 359. https://doi.org/10.1007/978-981-19-0920-7.

S. Chourasia, C. H. Bharadwaj, Q. Das, K. Agarwal, and K. Lavanya, “Vectorized neural key exchange using tree parity machine,” Compusoft, vol. 8, no. 5, pp. 3140–3145, 2019.

M. Dolecki and R. Kozera, “Distribution of the tree parity machine synchronization time,” Adv. Sci. Technol. – Res. J., vol. 7, no. 18, pp. 20–27, 2013, https://doi.org/10.5604/20804075.1049490.

A. J. Menezes, P. C. van Oorschot, and S. A. Vanstone, Handbook of Applied Cryptography (1st ed.). CRC Press, 2022. https://doi.org/10.1201/9780429466335.

C. Biswas, M. M. Haque, and U. Das Gupta, “A modified key sifting scheme with artificial neural network based key reconciliation analysis in quantum cryptography,” IEEE Access, vol. 10, no. July, pp. 72743–72757, 2022, https://doi.org/10.1109/ACCESS.2022.3188798.

Y. R. Mislovaty, I. Perchenok, W. Kanter, and Kinzel, “Secure key-exchange protocol with an absence of injective functions,” Phys. Rev., vol. 66, no. 6, 2002. https://doi.org/10.1103/PhysRevE.66.066102.

I. Kanter, W. Kinzel, and E. Kanter, “Secure exchange of information by synchronization of neural networks,” Euro-physics Lett., vol. 57, no. 1, p. 141, 2002. https://doi.org/10.1209/epl/i2002-00552-9.

M. Rosen-Zvi, E. Klein, I. Kanter, and W. Kinzel, “Mutual learning in a tree parity machine and its application to cryptography,” Phys. Rev. E, vol. 66, no. 6, p. 66135, 2002, https://doi.org/10.1103/PhysRevE.66.066135.

E. Shishniashvili, L. Mamisashvili, and L. Mirtskhulava, “Enhancing IoT security using multi-layer feedforward neural network with tree parity machine elements,” Int. J. Simul. Syst. Sci. Technol., pp. 6–10, 2020, https://doi.org/10.5013/IJSSST.a.21.02.37.

E. M. M. Manucom, B. D. Gerardo, and R. P. Medina, “Analysis of key randomness in improved one-time pad cryptography,” Proceedings of the 2019 IEEE 13th International Conference on Anti-Counterfeiting, Security, and Identification (ASID), 2019, pp. 11–16. https://doi.org/10.1109/ICASID.2019.8925173.

R. Manjupargavi, M. V. Srinath, “Efficient OTP generation with encryption and decryption for secure file access in cloud environment,” J. Commun. Technol., vol. 13, no. 2, pp. 2683–2688, 2022, https://doi.org/10.21917/ijct.2022.0397.

L. C. B. C. Ferreira, P. R. Chaves, R. M. Assumpção, O. C. Branquinho, F. Fruett, and P. Cardieri, “The three-phase methodology for IoT project development,” Internet of Things, vol. 20, p. 100624, 2022, https://doi.org/10.1016/j.iot.2022.100624.

É. Salguero Dorokhin, W. Fuertes, and E. Lascano, “On the development of an optimal structure of tree parity machine for the establishment of a cryptographic key,” Secur. Commun. Networks, vol. 2019, 2019, https://doi.org/10.1155/2019/8214681.

S. Matelski, “Human-computable OTP generator as an alternative of the two-factor authentication,” pp. 64–71, 2022, https://doi.org/10.1145/3528580.3532842.

X. Lei, X. Liao, F. Chen, and T. Huang, “Two-layer tree-connected feed-forward neural network model for neural cryptography,” Phys. Rev. E - Stat. Nonlinear, Soft Matter Phys., vol. 87, no. 3, p. 032811, 2013, https://doi.org/10.1103/PhysRevE.87.032811.

A. Ruttor, “Neural synchronization and cryptography,” 2007, [Online]. Available: http://arxiv.org/abs/0711.2411.

A. Ruttor, W. Kinzel, and I. Kanter, “Dynamics of neural cryptography,” Phys. Rev. E - Stat. Nonlinear, Soft Matter Phys., vol. 75, no. 5, p. 056104, 2007, https://doi.org/10.1103/PhysRevE.75.056104.

M. A. Budiman, Handrizal, and William, “A neural cryptography approach for digital image security using Vigenère cipher and tree parity machine,” J. Phys. Conf. Ser., vol. 1898, no. 1, p. 012039, 2021, https://doi.org/10.1088/1742-6596/1898/1/012039.

I. Meraouche, S. Dutta, H. Tan, and K. Sakurai, “Learning asymmetric encryption using adversarial neural networks,” Eng. Appl. Artif. Intell., vol. 123, p. 106220, 2023, https://doi.org/10.1016/j.engappai.2023.106220.

Downloads

Published

2025-10-02

How to Cite

Wati, V., & Hasan, N. F. (2025). Neural Cryptography Based on Tree Parity Machine to Generate OTP. International Journal of Computing, 24(3), 559-569. Retrieved from https://computingonline.net/computing/article/view/4193

Issue

Section

Articles