Open Access

ARTICLE

Cylinder XOR-Cascade: Lightweight Image Encryption Using Autoencoder-Based Representation

Rania Al-Ali¹, Mustafa Al-Fayoumi^1,2, Saleem Alsaraireh^3,*

1 Department of Cybersecurity, King Hussein School of Computing Sciences, Princess Sumaya University for Technology (PSUT), Amman, Jordan
2 Department of Computer Science, Faculty of Information Technology, Middle East University (MEU), Amman, Jordan
3 Department of Computer Science, King Hussein School of Computing Sciences, Princess Sumaya University for Technology (PSUT), Amman, Jordan

* Corresponding Author: Saleem Alsaraireh. Email:

(This article belongs to the Special Issue: Applied Cryptography and Privacy-Enhancing Technologies for Secure Digital Infrastructures)

Computers, Materials & Continua 2026, 89(2), 78 https://doi.org/10.32604/cmc.2026.085806

Received 19 May 2026; Accepted 25 June 2026; Issue published 15 September 2026

Abstract

The rapid growth of the Internet of Things (IoT) and edge computing has increased the demand for secure and lightweight image encryption suitable for resource-constrained environments. This paper proposes a hybrid framework combining a residual-based pretrained autoencoder with a novel Cylinder XOR-Cascade (CXC) encryption scheme. The autoencoder compresses images into a compact latent representation while a residual branch preserves fine spatial details for accurate reconstruction. Both representations are encrypted using CXC, a two-pass column-wise stream cipher that enhances confusion and diffusion through sequential SHA3-256-based chaining and a cylinder-like feedback mechanism. Experiments on the USC-SIPI dataset demonstrate strong statistical security: Number of Pixels Change Rate (NPCR) $\approx$99.5%, Unified Average Changing Intensity (UACI) $\approx$33.5%, and entropy $\approx$7.5. The full pipeline processes images in 280 ms on GPU and 928 ms on CPU, with the cryptographic stage requiring only 25 ms. For noisy channels, integrating Reed–Solomon forward error correction restores Structural Similarity Index Measure (SSIM) $>$0.85 under Gaussian noise ($\sigma =20$), making the framework suitable for edge-assisted IoT and real-time visual transmission across both reliable and noisy channel conditions.

---

Keywords

---