A Deep Learning Assisted Cryptographic Scheme Integrating Graph Neural Networks and Convolutional Autoencoders for Secure Data Transmission
Received: 6 February 2026 | Revised: 26 February 2026 and 15 March 2026 | Accepted: 26 March 2026 | Online: 6 April 2026
Corresponding author: A. V. Gahan
Abstract
Advanced Encryption Standard (AES-256) is a cryptographic algorithm that offers high confidentiality under standard security assumptions. However, structured data inherently possess correlations before encryption. This study proposes a structural and statistical pre-processing framework that uses Graph Neural Networks (GNNs) and Convolutional Autoencoders (CAEs) to transform the structured plaintext data before performing AES-256 encryption. The plaintext data are first converted into a graph structure to represent their inter-block relationships. The GNN learns the relational embeddings, which are further compressed by a CAE into low-dimensional latent spaces. These new spaces are subsequently encrypted using AES-256 without changing their internal architecture. The cryptographic security of the system is entirely inherited from AES-256, while the proposed learning-based module functions as a deterministic pre-processing transformation applied before encryption. The experimental results on computational complexity and statistical diffusion properties demonstrated consistency with statistical diffusion properties and computational efficiency, without compromising the security guarantees of AES-256.
Keywords:
secured cryptography, graph neural networks, convolutional autoencoders, deep learning–based security, intelligent encryptionDownloads
References
M. A. Qasem et al., "Cryptography Algorithms for Improving the Security of Cloud‐Based Internet of Things," SECURITY AND PRIVACY, vol. 7, no. 4, Jul. 2024, Art. no. e378.
R. Kaur and C. Sahu, "Cryptography in Industry," in Next Generation Mechanisms for Data Encryption, 1st ed., Boca Raton, FL, USA: CRC Press, 2024, pp. 146–163.
R. A. Jowarder and S. Jahan, "Quantum Computing in Cyber Security: Emerging Threats, Mitigation Strategies, and Future Implications for Data Protection," World Journal of Advanced Engineering Technology and Sciences, vol. 13, no. 1, pp. 330–339, Sep. 2024.
P. Singh et al., "Understanding RSA Algorithm in Cryptography," Undergraduate Thesis, University of Jammu, Jammu, India, 2024.
P. Singh, P. Pranav, and S. Dutta, "Optimizing Cryptographic Protocols Against Side Channel Attacks Using WGAN-GP and Genetic Algorithms," Scientific Reports, vol. 15, no. 1, Jan. 2025, Art. no. 2130.
A. I. Saiyed, "Hybrid Quantum-Classical Cryptographic Protocols: Enhancing Security in the Era of Quantum Supremacy," Spectrum of Research, vol. 5, no. 1, pp. 1–7, 2025.
S. Fu, H. Xu, A. Ali, and S. Sajid, "PriFed-IDS: A Privacy-Preserving Federated Reinforcement Learning Framework for Secure and Intelligent Intrusion Detection in Digital Health Systems," Electronics, vol. 14, no. 23, Nov. 2025, Art. no. 4590.
N. Fazrina, "Securing Distributed Sensor Systems Through Adaptive Encryption Algorithms in 5G-Based Smart Energy Networks," Open Journal of Robotics, Autonomous Decision-Making, and Human-Machine Interaction, vol. 9, no. 11, pp. 18–27, 2024.
M. Khule, D. Motwani, and D. Chauhan, "A Layered and Integrative Framework for Advance Persistent Threat Detection and Mitigation: Combining AI, Zero-Trust, and Advanced Threat Intelligence," Cluster Computing, vol. 28, no. 11, Oct. 2025, Art. no. 740.
K. Mansoor, M. Afzal, W. Iqbal, and Y. Abbas, "Securing the Future: Exploring Post-Quantum Cryptography for Authentication and User Privacy in IoT Devices," Cluster Computing, vol. 28, no. 2, Apr. 2025, Art. no. 93.
Y. Ding, F. Tan, Z. Qin, M. Cao, K.-K. R. Choo, and Z. Qin, "DeepKeyGen: A Deep Learning-Based Stream Cipher Generator for Medical Image Encryption and Decryption." arXiv, 2020.
G. S. Mamatha, N. Dimri, and R. Sinha, "Post-Quantum Cryptography: Securing Digital Communication in the Quantum Era." arXiv, 2024.
C. Benitez, "Mapping Quantum Threats: An Engineering Inventory of Cryptographic Dependencies." arXiv, Mar. 03, 2026.
H. E. Mozo, "Quantum-Classical Hybrid Encryption Framework Based on Simulated BB84 and AES-256: Design and Experimental Evaluation." Jun. 27, 2025.
A. Badr, "Instant-Hybrid Neural-Cryptography (IHNC) Based on Fast Machine Learning," Neural Computing and Applications, vol. 34, no. 22, pp. 19953–19972, Nov. 2022.
R. Devendiran and A. V. Turukmane, "A Secured Cryptographic Approach with Extreme Gradient Boosting Model for Data Aggregation and Routing in WSN," Journal of Information Security and Applications, vol. 98, May 2026, Art. no. 104372.
M. A. Khan et al., "An Improvised Certificate-Based Proxy Signature Using Hyperelliptic Curve Cryptography for Secure UAV Communications," IEEE Transactions on Intelligent Transportation Systems, vol. 26, no. 4, pp. 5264–5275, Apr. 2025.
M. Abu-Faraj, A. Al-Hyari, K. Aldebei, Z. A. Alqadi, and B. Al-Ahmad, "Rotation Left Digits to Enhance the Security Level of Message Blocks Cryptography," IEEE Access, vol. 10, pp. 69388–69397, 2022.
Y. Ma, J. Qiu, X. Sun, and Y. Tao, "A Novel Cryptography-Based Architecture to Achieve Secure Energy Trading in Microgrid," IEEE Transactions on Smart Grid, vol. 15, no. 2, pp. 2056–2072, Mar. 2024.
P. Radanliev, "Artificial Intelligence and Quantum Cryptography," Journal of Analytical Science and Technology, vol. 15, no. 1, Feb. 2024, Art. no. 4.
D. Ghosh, K. Ghosh, C. Chakraborty, A. Datta, and S. Gupta, "Securing the Future: Emerging Threats and Countermeasures in Cryptography," in Securing the Digital Frontier, 1st ed., K. Sharma, V. Sharma, P. Nand, A. K. Sagar, and G. Shrivastava, Eds. Hoboken, NJ, USA: Wiley, 2025, pp. 91–107.
A. S. Ahanger, F. S. Masoodi, A. Khanam, and W. Ashraf, "Managing and Securing Information Storage in the Internet of Things," in Internet of Things Vulnerabilities and Recovery Strategies, 1st ed., New York City, NY, USA: Auerbach Publications, 2024, pp. 102–151.
Y. M. Dalal, S. Supreeth, K. Amuthabala, T. Y. Satheesha, PN. Asha, and S. Somanath, "Optimizing Security: A Comparative Analysis of RSA, ECC, and DH Algorithms," in IEEE North Karnataka Subsection Flagship International Conference, Bagalkote, India, Sep. 2024, pp. 1–6.
N. Naveen and J. Nirmaladevi, "Secure Bio-Inspired Optimization with Intrusion Aware on-Demand Routing in MANETs," Scientific Reports, vol. 15, no. 1, Jul. 2025, Art. no. 25335.
M. Abudalou, "Enhancing Data Security through Advanced Cryptographic Techniques," International Journal of Computer Science and Mobile Computing, vol. 13, no. 1, pp. 88–92, Jan. 2024.
A. O. Ezeogu, "Post-Quantum Cryptography for Healthcare: Future-Proofing Population Health Databases Against Quantum Computing Threats," Research Corridor Journal of Engineering Science, vol. 2, no. 1, pp. 29–56, Feb. 2025.
Z. Yu, "Research on Cryptography Based on Quantum-Resistant Algorithms," in International Conference on Electronics and Devices, Computational Science (ICEDCS), Sep. 2024, pp. 149–154.
S. N. Yusof, M. R. K. Ariffin, and W. N. Aqlili, "A Cryptanalysis on the Bivariate Cryptosystem in a Multivariate Setting," in Cryptology and Information Security Conference, Sep. 2024, Art. no. 75.
A. Aydeger, E. Zeydan, A. K. Yadav, K. T. Hemachandra, and M. Liyanage, "Towards a Quantum-Resilient Future: Strategies for Transitioning to Post-Quantum Cryptography," in 15th International Conference on Network of the Future, Oct. 2024, pp. 195–203.
H. Y. Naser, A. K. Mattar, M. A. Saare, M. A. Almaiah, and R. Shehab, "A Comparison of Lightweight Cryptographic Protocols for Energy-Efficient and Sustainable IoMT Authentication," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25746–25756, Aug. 2025.
"BOSS Base v1.0.1 Dataset." Binghamton, 2023, [Online]. Available: https://dde.binghamton.edu/download/.
Downloads
How to Cite
License
Copyright (c) 2026 A. V. Gahan, Geetha D. Devanagavi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
