The International Journal of Engineering Sciences

Images are essential digital assets in the application of IOT, such as medicine, transportation, farming, the armed forces, and smart city planning. However, ensuring secure transmission of images over IoT networks remains a challenge due to key generation vulnerabilities and reliance on mathematically complex cryptographic systems. This paper proposes a new encryption scheme combining Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) for random key generation, used with the AES encryption algorithm.
The randomness of the generated keys was verified using NIST and Diehard tests, demonstrating good statistical quality. Experimental results confirm the efficacy of the scheme: the encrypted images showed entropy values approaching 8.0 indicating a very high degree of randomness; PSNR values were around 6.12 dB and MSE values were above 105 indicating very strong encryption data distortion; histogram analyses showed the outputs had uniform distributions; and correlation coefficients were shown to be close to zero, thereby demonstrating the scheme was resistant to statistical attacks and spatial attacks. Decryption led to lossless reconstruction characterized by infinite PSNR and MSE of zero.
Overall, the results presented in this study demonstrate the scheme's robustness, efficiency in the encryption and decryption process, and applicability for protecting sensitive image data in IoT networks..

References

References
[1]   K. G. Salim, S. M. K. Al-alak, and M. J. Jawad, “Improved image security in internet of thing (IoT) using multiple key AES,” Baghdad Sci. J., vol. 18, no. 2, pp. 0417–0417, 2021.
[2]       M. N. Halgamuge and D. Niyato, “Adaptive edge security framework for dynamic IoT security policies in diverse environments,” Comput. Secur., vol. 148, p. 104128, Jan. 2025, doi: 10.1016/j.cose.2024.104128.
[3]       Gunjan, S. Agarwal, D. Rai, and S. Talreja, “Applications of IoT in Smart Homes and Cities,” in IoT Based Smart Applications, N. Sindhwani, R. Anand, M. Niranjanamurthy, D. Chander Verma, and E. B. Valentina, Eds., in EAI/Springer Innovations in Communication and Computing. , Cham: Springer International Publishing, 2023, pp. 55–70. doi: 10.1007/978-3-031-04524-0_4.
[4]       V. Gugueoth, S. Safavat, S. Shetty, and D. Rawat, “A review of IoT security and privacy using decentralized blockchain techniques,” Comput. Sci. Rev., vol. 50, p. 100585, Nov. 2023, doi: 10.1016/j.cosrev.2023.100585.
[5]       G.-C. Lee, J.-H. Li, and Z.-Y. Li, “A Wasserstein Generative Adversarial Network–Gradient Penalty-Based Model with Imbalanced Data Enhancement for Network Intrusion Detection,” Appl. Sci., vol. 13, no. 14, p. 8132, Jul. 2023, doi: 10.3390/app13148132.
[6]       M. Kaur et al., “EGCrypto: A Low-Complexity Elliptic Galois Cryptography Model for Secure Data Transmission in IoT,” IEEE Access, vol. 11, pp. 90739–90748, 2023, doi: 10.1109/ACCESS.2023.3305271.
[7]       M. G. Samaila, M. Neto, D. A. B. Fernandes, M. M. Freire, and P. R. M. Inácio, “Challenges of securing Internet of Things devices: A survey,” Secur. Priv., vol. 1, no. 2, p. e20, Mar. 2018, doi: 10.1002/spy2.20.
[8]       “Fractal resonator based frequency Reconfigurable Antenna with varying capacitive effect for wireless applications,” Inf. MIDEM - J. Microelectron. Electron. Compon. Mater., vol. 51, no. 3, Dec. 2024, doi: 10.33180/InfMIDEM2025.104.
[9]       G. Lackner, “A Comparison of Security in Wireless Network Standards with a Focus on Bluetooth, WiFi and WiMAX”.
[10]       H. El-Sofany, S. A. El-Seoud, O. H. Karam, and B. Bouallegue, “Using machine learning algorithms to enhance IoT system security,” Sci. Rep., vol. 14, no. 1, p. 12077, May 2024, doi: 10.1038/s41598-024-62861-y.
[11]       A. Shafique, A. Mehmood, M. Alawida, M. Elhadef, and M. U. Rehman, “A fusion of machine learning and cryptography for fast data encryption through the encoding of high and moderate plaintext information blocks,” Multimed. Tools Appl., vol. 84, no. 8, pp. 5349–5375, Apr. 2024, doi: 10.1007/s11042-024-18959-6.
[12]       S. S. Chaeikar, M. Alizadeh, M. H. Tadayon, and A. Jolfaei, “An intelligent cryptographic key management model for secure communications in distributed industrial intelligent systems,” Int. J. Intell. Syst., vol. 37, no. 12, pp. 10158–10171, Dec. 2022, doi: 10.1002/int.22435.
[13]       A. Arab, M. J. Rostami, and B. Ghavami, “An image encryption method based on chaos system and AES algorithm,” J. Supercomput., vol. 75, no. 10, pp. 6663–6682, Oct. 2019, doi: 10.1007/s11227-019-02878-7.
[14]   A. BashirAbugharsa, A. Samad Bin Hasan Basari, and H. Almangush, “A New Image Encryption Approach using the Integration of a Shifting Technique and the AES Algorithm,” Int. J. Comput. Appl., vol. 42, no. 9, pp. 36–45, Mar. 2012, doi: 10.5120/5723-7785.
[15]   Y. Jha, K. Kaur, and C. Pradhan, “Improving image encryption using two-dimensional logistic map and AES,” in 2016 International Conference on Communication and Signal Processing (ICCSP), Melmaruvathur, Tamilnadu, India: IEEE, Apr. 2016, pp. 0177–0180. doi: 10.1109/ICCSP.2016.7754116.
[16]   M. S. Q. Khizrai and S. T. Bodkhe, “Image Encryption using Different Techniques for High Security Transmission over a Network,” vol. 2, no. 4, 2014.
[17]   A. H. Mohsen and S. H. Shaker, “Images encryption using symmetric encryption algorithm based on random keys generator,” vol. 01, no. 08, 2016.
[18]       S. Mohammed, S. M. K. Al-Alak, and H. A. Lafta, “ECC and AES Based Hybrid Security Protocol for Wireless Sensor Networks”.
[19]       S. N. Hussein and S. M. Al-Alak, “Secret Keys Extraction Using Light Weight Schemes for Data Ciphering,” J. Phys. Conf. Ser., vol. 1999, no. 1, p. 012114, Sep. 2021, doi: 10.1088/1742-6596/1999/1/012114.
[20]       P. Ji, H. Ma, Q. Ma, and X. Chen, “A Novel Method to Generate Pseudo-Random Sequence based on GAN”.
[21]   S. Park, K. Kim, K. Kim, and C. Nam, “Dynamical Pseudo-Random Number Generator Using Reinforcement Learning,” Appl. Sci., vol. 12, no. 7, p. 3377, Mar. 2022, doi: 10.3390/app12073377.
[22]   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,” Dec. 21, 2020, arXiv: arXiv:2012.11097. doi: 10.48550/arXiv.2012.11097.
[23]   V. Desai, R. Patil, and D. Rao, “Using Layer Recurrent Neural Network to Generate Pseudo Random Number Sequences,” vol. 9, no. 2, 2012.
[24]   V. Pachghare, Cryptography and information security. PHI Learning Pvt. Lt

Article history_en

Received : Jun 02, 2025

Revised : Jun 04, 2025

Accepted : Jul 21, 2025

Authors Affiliations_en

Ethics declarations_en

Acknowledgment	None
Author Contribution	All authors contributed equally to the main contributor to this paper. All authors read and approved the final paper.
Conflicts of Interest	“The authors declare no conflict of interest.”
Funding	“This research received no external funding”