AI-Enhanced AES Encryption for Kurdish Unicode Texts: A Neural Network–Based Key Generation Approach Using Linguistic Statistical Features

Ziyad Hazim Abduljabbar

doi:10.65542/djei.v2i2.39

Authors

Ziyad Hazim Abduljabbar Duhok Polytechnic University https://orcid.org/0009-0002-4493-2152

DOI:

https://doi.org/10.65542/djei.v2i2.39

Keywords:

Attack Model Evaluation, Central Kurdish Text, CKLTCD Dataset, FFNN, Feature Extraction, Key Generation

Abstract

This research presents an efficient and secure method for generating the AES master key, based on statistical features extracted from the linguistic structure of Middle Kurdish texts. These features include text length, word count, frequency of unique letters, bigram and trigram, and text entropy. The numerical feature vector is fed with a random salt value into a secure hashing algorithm (SHA256) to scale and encode it into a 32-bit intermediate key. This intermediate key is processed by a three-layer FFNN with random weights and bias values to output the AES master key. For optimal performance and security, the AES algorithm with a 256-bit key and the GCM operating mode were used. The encryption system was developed using Python. The initial test was performed on ten Kurdish texts. The measured entropy values for all generated master keys were high, approaching the maximum Central Kurdish alphabet entropy of 4.9542 bits/letter. To evaluate the system on a larger number of texts, a dataset named CKLTCD was created, consisting of 3000 Kurdish texts of varying lengths and domains. Keys were generated for all dataset texts. AES encryption and decryption were applied, yielding decrypted texts identical to the originals. The SHA function and FFNN significantly complicated and obscured the relationship between the original text and the generated key. The generated key became more independent and complex, making its analysis and prediction extremely difficult. The test results of cryptographic validation (NIST SP800-22, avalanche effect analysis, correlation analysis, and key sensitivity tests) and attack model evaluation (KPA, CPA, and brute-force attacks) reflected the success of the proposed encryption system's strength and security. Comparisons showed the method's similarity to standard functions (PBKDF2, Argon2, HKDF), validating this alternative method for generating dynamic keys based on Kurdish linguistic characteristics.

References

Mohammed N. Alenezi, Haneen Alabdulrazzaq, H.M.A. and F.A.A. On the Performance of AES Algorithm Variants. International Journal of Information and Computer Security 2024, Vol. 23, N, doi:https://doi.org/10.1504/IJICS.2024.138494. DOI: https://doi.org/10.1504/IJICS.2024.138494

Mu, C. Application of Optimizing Advanced Encryption Standard Encryption Algorithm in Secure Communication of Vehicle Controller Area Network Bus. 2024, 1–11, doi:10.3389/fmech.2024.1407665. DOI: https://doi.org/10.3389/fmech.2024.1407665

Chen, A.C.H. Performance Comparison of Various Modes of Advanced Encryption Standard. 2024, doi:10.1109/ICSSES62373.2024.10561385. DOI: https://doi.org/10.1109/ICSSES62373.2024.10561385

Ganesh, R.; Khan, B.U.I.; Khan, A.R.; Kamsin, A. Bin A Panoramic Survey of the Advanced Encryption Standard: From Architecture to Security Analysis, Key Management, Real-World Applications, and Post-Quantum Challenges. Int. J. Inf. Secur. 2025, 24, doi:10.1007/s10207-025-01116-x. DOI: https://doi.org/10.1007/s10207-025-01116-x

Soni, A.; Sahay, S.K.; Mehta, P. AESHA3: Efficient and Secure Sub-Key Generation for AES Using SHA-3. 2025, doi:10.1007/978-3-031-81168-5_5. DOI: https://doi.org/10.1007/978-3-031-81168-5_5

Barker, E.; Roginsky, A.; Davis, R. Recommendation for Cryptographic Key Generation; Gaithersburg, MD, 2020; DOI: https://doi.org/10.6028/NIST.SP.800-133r2-draft

Bonneau, J.; Herley, C.; Van Oorschot, P.C.; Stajano, F. The Quest to Replace Passwords: A Framework for Comparative Evaluation of Web Authentication Schemes. Proc. IEEE Symp. Secur. Priv. 2012, 553–567, doi:10.1109/SP.2012.44. DOI: https://doi.org/10.1109/SP.2012.44

Kim, J.; Song, M.; Seo, M.; Jin, Y.; Shin, S.; Kim, J. PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websites. 2025. DOI: https://doi.org/10.1016/j.eswa.2025.130111

Sandhya Venu, V.; Rithwik, D.; Prasoon, M.M.; Praneeth, D.S. A Bio-Cryptographic Approach to Aes Key Generation Using Randomized DNA Genes and Binary Encoding. 2025, 14, 3–6.

Setiawan, Y.; Maulidevi, N.U.; Surendro, K. The Optimization of N-Gram Feature Extraction Based on Term Occurrence for Cyberbullying Classification. Data Sci. J. 2024, 23, 1–21, doi:10.5334/dsj-2024-031. DOI: https://doi.org/10.5334/dsj-2024-031

Hassani, H.; Beneki, C.; Unger, S.; Mazinani, M.T.; Yeganegi, M.R. Text Mining in Big Data Analytics. Big Data and Cognitive Computing 2020, 4, 1–34, doi:10.3390/bdcc4010001. DOI: https://doi.org/10.3390/bdcc4010001

Kalimeri, M.; Constantoudis, V.; Papadimitriou, C.; Karamanos, K.; Diakonos, F.K.; Papageorgiou, H. Entropy Analysis of Word-Length Series of Natural Language Texts: Effects of Text Language and Genre. International Journal of Bifurcation and Chaos 2012, 22, doi:10.1142/S0218127412502239. DOI: https://doi.org/10.1142/S0218127412502239

Liu, K.; Ye, R.; Zhongzhu, L.; Ye, R. Entropy-Based Discrimination between Translated Chinese and Original Chinese Using Data Mining Techniques. PLoS One 2022, 17, doi:10.1371/journal.pone.0265633. DOI: https://doi.org/10.1371/journal.pone.0265633

Kodwani, G.; Arora, S.; Atrey, P.K. On Security of Key Derivation Functions in Password-Based Cryptography. Proceedings of the 2021 IEEE International Conference on Cyber Security and Resilience, CSR 2021 2021, 109–114, doi:10.1109/CSR51186.2021.9527961. DOI: https://doi.org/10.1109/CSR51186.2021.9527961

Dang, Q.H. Secure Hash Standard. FIBS 180-4 Publication 2015, 4, 36.

Barker, E.; Roginsky, A. Transitioning the Use of Cryptographic Algorithms and Key Lengths. NIST Special Publication 800-131A Revision 2 2019, 17–18. DOI: https://doi.org/10.6028/NIST.SP.800-131Ar2

Liu, Y.A.; Chen, L.; Li, X.W.; Liu, Y.L.; Hu, S.G.; Yu, Q.; Chen, T.P.; Liu, Y. A Dynamic AES Cryptosystem Based on Memristive Neural Network. Sci. Rep. 2022, 12, doi:10.1038/s41598-022-13286-y. DOI: https://doi.org/10.1038/s41598-022-13286-y

Zied, G.; Zrigui, M.; Guitouni, Z.; Zairi, A. Secure Transmission of Medical Images in IoMT Systems Using Feedforward Neural Networks. 2023.

Wu, X.; Han, Y.; Zhang, M.; Zhu, S.S.; Cui, S.; Wang, Y.; Peng, Y. Pseudorandom Number Generators Based on Neural Networks: A Review. Journal of King Saud University - Computer and Information Sciences 2025, 37, doi:10.1007/s44443-025-00007-4. DOI: https://doi.org/10.1007/s44443-025-00007-4

Guitouni, Z.; Zairi, A.; Zrigui, M. Implementation of Neural Key Generation Algorithm For IoT Devices. Journal of Computer Science Advancements 2024, 1, 276–290, doi:10.70177/jsca.v1i5.637. DOI: https://doi.org/10.70177/jsca.v1i5.637

Nitaj, A.; Rachidi, T. Applications of Neural Network-Based AI in Cryptography. Cryptography 2023, 7, 1–26, doi:10.3390/cryptography7030039. DOI: https://doi.org/10.3390/cryptography7030039

Wu, X.; Han, Y.; Zhang, M.; Li, Y.; Cui, S. GAN-Based Pseudo Random Number Generation Optimized through Genetic Algorithms. Complex and Intelligent Systems 2025, 11, doi:10.1007/s40747-024-01606-w. DOI: https://doi.org/10.1007/s40747-024-01606-w

Badawi, S. Deep Learning-Based Cyberbullying Detection in Kurdish Language. Comput. J. 2024, 67, 2548–2558, doi:10.1093/comjnl/bxae024. DOI: https://doi.org/10.1093/comjnl/bxae024

Abdulrazaq, N.N. A Novel Approach For Safeguarding Kurdish Text Files Via Modified AES-OTP And Enhanced RSA Cryptosystem On Unreliable Networks. Eurasian Journal of Science and Engineering 2024, 10, 102–119, doi:10.23918/eajse.v10i2p8. DOI: https://doi.org/10.23918/eajse.v10i2p8

Abid Al Jabbar, Z.H.; Ali, Z.A.; Taher, H.A. Design and Implementation of a Mathematical Encryption Model for the Central Kurdish Font Based on Unicode. Science Journal of University of Zakho 2023, 11, 273–279, doi:10.25271/sjuoz.2023.11.2.1126. DOI: https://doi.org/10.25271/sjuoz.2023.11.2.1126

Kathleen Moriarty Password-Based Cryptography Specification. 2017.

Understanding Optimizations and Measuring Performances of PBKDF2; Woungang, I., Dhurandher, S.K., Eds.; Lecture Notes on Data Engineering and Communications Technologies; Springer International Publishing: Cham, 2019; Vol. 27; ISBN 978-3-030-11436-7.

Biryukov, A.; Dinu, D.; Khovratovich, D.; Josefsson, S. RFC 9106: Argon2 Memory-Hard Function for Password Hashing and Proof-of-Work Applications. Internet Research Task Force (IRTF) 2021, 1–21. DOI: https://doi.org/10.17487/RFC9106

Aljuffri, A.; Huang, R.; Muntenaar, L.; Gaydadjiev, G.; Hamdioui, S.; Taouil, M. The Security Evaluation of an Efficient Lightweight. 2024, 1–20. DOI: https://doi.org/10.3390/cryptography8020024

Dworkin, M.J. NIST Special Publication 800-38D: Recommendation for Block Cipher Modes of Operation: Galois/Counter Mode (GCM) and GMAC. Computer Security, National Institute of Standards and Technology (NIST), published by NIST 2007. DOI: https://doi.org/10.6028/NIST.SP.800-38d

Medetov, B.; Serikov, T.; Tolegenova, A.; Dauren, Z. Comparative Analysis of the Performance of Generating Cryptographic Ciphers on the Cpu and Fpga. J. Theor. Appl. Inf. Technol. 2022, 100, 4813–4824.

Mouha, N.; Dworkin, M. NIST Internal Report NIST IR 8459 Ipd Report on the Block Cipher Modes of Operation in the NIST SP 800-38 Series Initial Public Draft; 2023; ISBN 0000000327459. DOI: https://doi.org/10.6028/NIST.IR.8459.ipd

Lee, J.S.; Kim, D.C.; Seo, S.C. Parallel Implementation of GCM on GPUs. ICT Express 2025, 11, 310–316, doi:10.1016/j.icte.2025.01.006. DOI: https://doi.org/10.1016/j.icte.2025.01.006

Kampanakis, P.; Campagna, M.; Crocket, E.; Petcher, A.; Gueron, S. Practical Challenges with AES-GCM and the Need for a New Cipher. Third NIST Workshop on Block Cipher Modes of Operation 2024, 3.

Abdulrahman, R.O.; Hassani, H.; Ahmadi, S. Developing a Fine-Grained Corpus for a Less-Resourced Language: The Case of Kurdish. arxiv.org 2019, 106–109.

Montemurro, M.A.; Zanette, D.H. Universal Entropy of Word Ordering across Linguistic Families. PLoS One 2011, 6, doi:10.1371/journal.pone.0019875. DOI: https://doi.org/10.1371/journal.pone.0019875

Abdulrahman, R.O.; Hassani, H. A Language Model for Spell Checking of Educational Texts in Kurdish (Sorani). 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages, SIGUL 2022 - held in conjunction with the International Conference on Language Resources and Evaluation, LREC 2022 - Proceedings 2022, 189–198.

Hamarashid, H.K.; Saeed, S.A.; Rashid, T.A. Next Word Prediction Based on the N-Gram Model for Kurdish Sorani and Kurmanji. Neural Comput. Appl. 2021, 33, 4547–4566, doi:10.1007/s00521-020-05245-3. DOI: https://doi.org/10.1007/s00521-020-05245-3

A. Rashid, T.; M. Mustafa, A.; Saeed, A.M. A Robust Categorization System for Kurdish Sorani Text Documents. Information Technology Journal 2016, 16, 27–34, doi:10.3923/itj.2017.27.34. DOI: https://doi.org/10.3923/itj.2017.27.34

Kathleen, M.; Burt, K.; Adam, R. PKCS #5: Password-Based Cryptography Specification Version 2.1; 2017;

Alex, B.; Daniel, D.; Dmitry, K.; Simon, J. Argon2 Memory-Hard Function for Password Hashing and Proof-of-Work Applications; 2021;

Hugo, K.; Pasi, E. HMAC-Based Extract-and-Expand Key Derivation Function (HKDF); 2010;

The Unicode Consortium Unicode 17.0 Character Code Charts Available online: https://unicode.org/charts/.

François Yergeau UTF-8, a Transformation Format of ISO 10646; 2003; DOI: https://doi.org/10.17487/rfc3629

Bassham, L.E.; Rukhin, A.L.; Soto, J.; Nechvatal, J.R.; Smid, M.E.; Barker, E.B.; Leigh, S.D.; Levenson, M.; Vangel, M.; Banks, D.L.; et al. A Statistical Test Suite for Random and Pseudorandom Number Generators for Cryptographic Applications; Gaithersburg, MD, 2010; DOI: https://doi.org/10.6028/NIST.SP.800-22r1a

Gáll, J.; Gürgez, P.; Horváth, G. Adding an Avalanche Effect to a Stream Cipher Suitable for IoT Devices. 2025, doi:10.3390/electronics. DOI: https://doi.org/10.3390/electronics14132546

Mohamed, K.; Pauzi, M.N.M.; Ali, F.H.H.M.; Ariffin, S. Analyse On Avalanche Effect In Cryptography Algorithm. In Proceedings of the Proceedings of the International Conference on Sustainable Practices, Development and Urbanisation (IConsPADU 2021), 16 November 2021, Universiti Selangor (UNISEL), Malaysia; European Publisher, October 31 2022; Vol. 3, pp. 610–618. DOI: https://doi.org/10.15405/epms.2022.10.57

Upadhyay, D.; Gaikwad, N.; Zaman, M.; Sampalli, S. Investigating the Avalanche Effect of Various Cryptographically Secure Hash Functions and Hash-Based Applications. IEEE Access 2022, 10, 112472–112486, doi:10.1109/ACCESS.2022.3215778. DOI: https://doi.org/10.1109/ACCESS.2022.3215778

Shamsa, K.; Saba, I.; Muqaddas, B.; Leila, J. An Efficient and Robust Image Encryption Model Using Hybrid Technique, SHA-224 Hashing, and Shift AES. 2026.

Koulouh, F.; Amine, S.; Es-Sabry, M.; AKKAD, N. EL; Shahin, A.I.; El-Shafai, W. Optimizing Color Image Security Using Hybrid Cryptographic Techniques Based on Sine and Logistic Maps. Sci. Rep. 2026, doi:10.1038/s41598-025-33319-6. DOI: https://doi.org/10.1038/s41598-025-33319-6

Zhang, X.; Chai, Y.; Xiang, S.; Li, S. Research on Image Encryption with Multi-Level Keys Based on a Six-Dimensional Memristive Chaotic System. Entropy 2025, 27, doi:10.3390/e27111152. DOI: https://doi.org/10.3390/e27111152

Zhiqiang, H.; Rauf, A.; Nazir, A.; Tchier, F.; Aslam, A.; Tola, K.A. Design and Analysis of a Secure Image Encryption Algorithm Using Proposed Non-Linear RN Chaotic System and ECC/HKDF Key Derivation with Authentication Support. Sci. Rep. 2025, 15, doi:10.1038/s41598-025-23592-w. DOI: https://doi.org/10.1038/s41598-025-23592-w

Wang, F.; Sang, J.; Liu, Q.; Huang, C.; Tan, J. A Deep Learning Based Known Plaintext Attack Method for Chaotic Cryptosystem. 2021.

Hazzazi, M.M.; Shah, D.; Alghamdi, M.; Alkhazi, I.S.; Riaz, N. Chosen-Plaintext Attacks on Image Ciphers Based on Nonlinear Dynamical Systems. Array 2026, 100642, doi:10.1016/j.array.2025.100642. DOI: https://doi.org/10.1016/j.array.2025.100642

Babu, P.A.; Thomas, J.J. Freestyle, a Randomized Version of ChaCha for Resisting Offline Brute-Force and Dictionary Attacks. 2018.

Ziyad, Hazim.A. Central Kurdish Linguistic Text Cryptography Dataset (CKLTCD); 2026.