SavedAdd your journal

Journals / El-Cezeri / 2026 / Cilt: 13 Sayı: 3

Performance Evaluation of Autoencoder and JPEGBased Image Compression Schemes Integrated with AES and RSA Encryption

AES ve RSA Şifrelemesiyle Entegre Edilmiş Otomatik Kodlayıcı ve JPEG Tabanlı Görüntü Sıkıştırma Şemalarının Performans Değerlendirmesi

Zekeriya Katılmış(Kütahya Sağlık Bilimleri Üniversitesi)0000-0002-2095-5483
Şevval Koç(Kütahya Sağlık Bilimleri Üniversitesi)0009-0009-6169-0053
Journal
El-Cezeri
Pages
477–496
Publication Date
2026-09-07
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results showed that the deep learning-based compression combined with classical encryption provides a robust and flexible architecture for secure image transmission over different hardware platforms.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:With the rapid growth of digital data production and transmission, the need to protect sensitive content and avoid unauthorized access has emerged.
📊
Key Findings & Data:In this paper, the complete framework for the evaluation of deep learning-based Autoencoder (AE) and traditional JPEG compression with symmetric (AES-128) and asymmetric (RSA-2048) cryptographic standards are proposed.
💡
Conclusion & Impact:The results showed that the deep learning-based compression combined with classical encryption provides a robust and flexible architecture for secure image transmission over different hardware platforms.
🔬Design:Araştırma Makalesi
📍Scope:2048 Verileri
⚙️Variables:Görüntü şifreleme · sıkıştırma · derin öğrenme

Abstract

With the rapid growth of digital data production and transmission, the need to protect sensitive content and avoid unauthorized access has emerged. Data security is achieved through encryption, but the increasing volume of data requires efficient compression techniques to reduce bandwidth and storage expenses. In this paper, the complete framework for the evaluation of deep learning-based Autoencoder (AE) and traditional JPEG compression with symmetric (AES-128) and asymmetric (RSA-2048) cryptographic standards are proposed. A multi-faceted approach is utilized to analyze the performance of four different configurations: AE+AES, AE+RSA, JPEG+AES and JPEG+RSA. This approach includes visual quality (PSNR, SSIM), cryptographic security (NPCR, UACI, Entropy) and statistical randomness and hardware resource utilization. The experimental results on 52,000 high-resolution images from the FFHQ dataset show a large tradeoff between reconstruction fidelity and computational efficiency. JPEG based configurations have better visual reconstruction (PSNR ≈ 44.64 dB) and faster processing speed, but they are highly memory dependent (up to 3.9 GB RAM). In contrast, the proposed AE-based latent encryption method is very lightweight with a small memory footprint (0.01 GB RAM) which makes it an ideal solution for resource-constrained edge devices and IoT applications. The results showed that the deep learning-based compression combined with classical encryption provides a robust and flexible architecture for secure image transmission over different hardware platforms.

Özet

Dijital verinin üretim ve iletim hızındaki artış, hassas içeriklerin korunması ve yetkisiz erişimlerin önlenmesini kritik hâle getirmiştir. Bu nedenle, veri güvenliğini sağlamak için şifreleme yöntemleri zorunlu bir unsur olarak öne çıkmaktadır. Bununla birlikte, artan veri hacmi, bant genişliği ve depolama maliyetlerini minimize etmek amacıyla etkili sıkıştırma tekniklerinin kullanımını gerekli kılmaktadır. Dolayısıyla, güvenli ve verimli veri iletimi için görüntü sıkıştırma ve şifreleme yöntemlerinin bir arada kullanımı kaçınılmaz hâle gelmiştir. Bu çalışma, görüntü verilerinin hem boyutunu azaltmak hem de güvenliğini sağlamak amacıyla hibrit bir sıkıştırma ve şifreleme yaklaşımı önerilmiştir. Sıkıştırma işlemi için otomatik kodlayıcı (Autoencoder, AE) modeli kullanılmıştır. Sıkıştırılmış veriler üzerinde AES ve RSA algoritmaları ile şifreleme gerçekleştirilmiştir. Geliştirilen üç farklı yapı (tekli AE, AE+AES, AE+RSA), görsel kalite, güvenlik, istatistiksel rastgelelik, işlem süresi ve kaynak kullanımı olmak üzere çeşitli metriklerle değerlendirilmiştir. Deneysel çalışmalar, Flickr Yüksek Kaliteli Yüzler veri seti kullanılarak gerçekleştirilmiştir. Deneysel sonuçlar, AE+AES modelinin şifreleme güvenliği ve işlem verimliliği açışından en dengeli yapıyı sunduğunu; AE+RSA modelinin ise daha yüksek güvenlik sağlamakla birlikte daha fazla kaynak tükettiğini ortaya koymuştur. Elde edilen bulgular, derin öğrenme temelli sıkıştırma modellerinin klasik şifreleme algoritmalarıyla entegre edilerek güvenli ve verimli veri iletimi için etkili bir çözüm sunduğunu göstermektedir.

🔖

Cite This Article

Katılmış, Z., Koç, Ş. (2026). Performance Evaluation of Autoencoder and JPEGBased Image Compression Schemes Integrated with AES and RSA Encryption. El-Cezeri, Cilt: 13 Sayı: 3, 477–496. https://doi.org/10.31202/ecjse.1796961

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (42)

  1. Álvarez, G. and Li, S., Some basic cryptographic requirements for chaos‑based cryptosystems, International Journal of Bifurcation and Chaos, 2006, 16(8), 2129–2151. https://doi.org/10.1142/S0218127406015970
  2. Huang, Q. X., Yap, W. L., Chiu, M. Y. and Sun, H. M., Privacy-preserving deep learning with learnable image encryption on medical images. IEEE Access, 2022, 10, 66345-66355. 10.1109/ACCESS.2022.3185206
  3. Zhang, B., Classification of encrypted text based on artificial intelligence. In IOP Conference Series: Materials Science and Engineering 2020, January, Vol. 740, No. 1, p. 012133, IOP Publishing. https://doi.org/10.1088/1757‑899X/740/1/01213
  4. Sang, Y., Sang, J. and Alam, M. S., Image encryption based on logistic chaotic systems and deep autoencoder, Pattern Recognition Letters, 2022, 153, 59–66. https://doi.org/10.1016/j.patrec.2021.11.025
  5. Maung Maung, A. and Kiya, H., Generative model‑based attack on learnable image encryption for privacy‑preserving deep learning, 2023, arXiv:2303.05036. https://doi.org/10.48550/arXiv.2303.05036
  6. Ahmed, F., Rehman, M. U., Ahmad, J., Khan, M. S., Boulila, W., Srivastava, G. and Buchanan, W. J. A., DNA based colour image encryption scheme using a convolutional autoencoder. ACM Transactions on Multimedia Computing, Communications and Applications, 2023, 19(3s), 1–21. https://doi.org/10.1145/3570165
  7. Al‑Maadeed, T. A., Hussain, I., Anees, A. and Mustafa, M. T., An image encryption algorithm based on chaotic Lorenz system and novel primitive polynomial S‑boxes. Multimedia Tools and Applications, 2021, 80, 24801–24822. https://doi.org/10.1007/s11042‑020‑08821‑w
  8. Sayood, K., Introduction to data compression. Morgan Kaufmann, 2017.
  9. Naveen, A. K., Thunga, S., Murki, A., Kalale, M. and Anil, S., Autoencoded Image Compression for Secure and Fast Transmission. In 2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI), 2024, October, (pp. 1–6). IEEE. DOI: 10.1109/CVMI61877.2024.10781629
  10. Hinton, G. E. and Salakhutdinov, R. R., Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786), 504–507. https://doi.org/10.1126/science.1127647
  11. Oswald, E., Daemen, J., & Rijmen, V., The Design of Rijndael: AES - The Advanced Encryption Standard, 2002, Springer Science & Business Media.
  12. Rivest, R. L., Shamir, A., & Adleman, L., A method for obtaining digital signatures and public‑key cryptosystems. Communications of the ACM, 1978, 21(2), 120–126. https://doi.org/10.1145/358980.358990
  13. Karras, T., Laine, S., & Aila, T., A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (FFHQ Dataset), 2019, https://www.kaggle.com/datasets/arnaud58/flickrfaceshq-dataset-ffhq
  14. Alslman, Y., Alnagi, E., Ahmad, A., AbuHour, Y., Younisse, R., & Abu Al-haija, Q. (2022). Hybrid encryption scheme for medical imaging using autoencoder and advanced encryption standard. Electronics, 11(23), 3967.
  15. Sabha, I., Parah, S. A., Sarosh, P., & Islam, M. O. U. (2024). CESCAL: A joint compression-encryption scheme based on convolutional autoencoder and logistic map. Multimedia Tools and Applications, 83(11), 32069-32098.
  16. Sharma, V., Shrivastava, L., & Shrivastava, N., Multi-Layer Image Security Framework Using Autoencoder Compression and Chaotic-AES Hybrid Security. In 2025 International Conference on Electrical, Communication, and Computing Technologies (iCONECCT), 2025, (pp. 1-5). IEEE.
  17. Shariatzadeh, M., Eftekhari, M., & Rostami, M. J., A New Scheme for Image Compression and Encryption Using ECIES, Henon Map, and AEGAN, 2022, arXiv preprint arXiv:2208.07635.
  18. Gupta, N., & Vijay, R., Hybrid image compression-encryption scheme based on multilayer stacked autoencoder and logistic map, China Communications, 2022, 19(1), 238-252.
  19. Wang, B., & Lo, K. T., Autoencoder-based joint image compression and encryption, Journal of Information Security and Applications, 2024, 80, 103680.
  20. Ahmed, A. M., Bouallegue, B., & Youness, H. A., Image Encryption and Compression Based on Auto Encoder for Real Time Using IoT Technique, International Journal of Computer Science & Network Security, 2025, 63-68.
  21. Wei, J., Zhang, M., & Tong, X. (2022). Multi-image compression–encryption algorithm based on compressed sensing and optical encryption, Entropy, 24(6), 784.
  22. Almola, S. A., Younis, H. A., & Khudeyer, R. S. A Robust Image Encryption Framework Using Deep Feature Extraction and AES Key Optimization, Cryptography, 2026, 10(2), 16.
  23. Lata, K., Gupta, C., & Cenkeramaddi, L. R., A cryptographic framework for secure medical imaging in smart healthcare environments, Results in Engineering, 2025, 106780.
  24. Xiao, W., Wan, N., Hong, A., & Chen, X., A fast JPEG image compression algorithm based on DCT. In 2020 IEEE International Conference on Smart Cloud (SmartCloud), 2020, (pp. 106-110). IEEE.
  25. Chen, H., He, X., Yang, H., Qing, L., & Teng, Q., A feature-enriched deep convolutional neural network for JPEG image compression artifacts reduction and its applications. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(1), 430-444.
  26. Berahmand, K., Daneshfar, F., Salehi, E. S., Li, Y., & Xu, Y., Autoencoders and their applications in machine learning: a survey. Artificial Intelligence Review, 2024, 57(2), 28. https://doi.org/10.1007/s10462-023-10400-0
  27. Ozturk, E., & Mesut, A., Comparison of learned image compression methods and JPEG. In 2024 Innovations in Intelligent Systems and Applications Conference (ASYU), 2024, (pp. 1-6). IEEE.
  28. Fraihat, S., & Al-Betar, M. A., A novel lossy image compression algorithm using multi-models stacked Auto Encoders, Array, 2023, 19, 100314.
  29. Zhang, W., Zheng, X., Xing, M., Yang, J., Yu, H., & Zhu, Z., Chaos-Based Color Image Encryption with JPEG Compression: Balancing Security and Compression Efficiency, Entropy, 2025, 27(8), 838.
  30. Salamah, A. H. A. M. (2026). JPEG-Inspired Encoding for Deep Learning.
  31. Abdmouleh, M. K., Khalfallah, A., & Bouhlel, M. S., A novel selective encryption scheme for medical images transmission based-on JPEG compression algorithm, Procedia computer science, 2017, 112, 369-376.
  32. Kurihara, K., Shiota, S., & Kiya, H. (2015). An encryption-then-compression system for jpeg standard. In 2015 Picture Coding Symposium (PCS) (pp. 119-123). IEEE.
  33. Lian, S., Sun, J., & Wang, Z., A novel image encryption scheme based-on JPEG encoding. In Proceedings. Eighth International Conference on Information Visualisation, 2004. IV 2004, 2004, (pp. 217-220). IEEE.
  34. Elkabbany, G. F., Aslan, H. K., & Rasslan, M. N. (2015). A design of a fast parallel‑pipelined implementation of AES: Advanced Encryption Standard. arXiv:1501.01427. https://doi.org/10.48550/arXiv.1501.01427
  35. Smid, M. E., Development of the advanced encryption standard. Journal of Research of the National Institute of Standards and Technology, 2021, 126, 126024. https://doi.org/10.6028/jres.126.024
  36. Kaliski, B., The mathematics of the RSA public‑key cryptosystem. RSA Laboratories, 2006.
  37. Nitaj, A., The mathematical cryptography of the RSA cryptosystem. In Cryptography: Protocols, Design and Applications, 2012, (pp. 159–186).
  38. Renieblas, G. P., Nogués, A. T., González, A. M., Gómez‑León, N., & Del Castillo, E. G., Structural similarity index family for image quality assessment in radiological images. Journal of Medical Imaging, 2017, 4(3), 035501. https://doi.org/10.1117/1.JMI.4.3.035501
  39. Alsaraireh, S., Ahmad, A., & AbuHour, Y., New step in lightweight medical image encryption and authenticity. Mathematics, 2025, 13(11), 1799. https://doi.org/10.3390/math13111799
  40. Susanto, A., Rachmawanto, E. H., Mulyono, I. U. W., Sari, C. A., Sarker, M. K., & Sazal, M. R., Triple layer image security using bit‑shift, chaos, and stream encryption. Bulletin of Electrical Engineering and Informatics, 2020, 9(3), 980–998. https://doi.org/10.11591/eei.v9i3.2492
  41. Hussein, M. K., Hassan, K. R., & Al‑Mashhadi, H. M., The quality of image encryption techniques by reasoned logic. TELKOMNIKA,2020, 18(6), 2992–2998. https://doi.org/10.12928/TELKOMNIKA.v18i6.14114
  42. Shakhmetova, G., Barlybayev, A., Saukhanova, Z., Sharipbay, A., Raykul, S., & Khassenov, A., Enhancing visual data security: A novel FSM‑based image encryption and decryption methodology. Applied Sciences,2024, 14(11), 4341. https://doi.org/10.3390/app14114341