Secure Image Steganography Using AES-CBC Encryption and Dynamic Key Derivation from Image Features

Authors

  • Mohammed Fadhil Kamil Information Technology Centre, Mustansiriyah University, Iraq
  • Ali Qasim Mohammed Information Technology Centre, Mustansiriyah University, Iraq

DOI:

https://doi.org/10.31695/IJASRE.2025.10.7

Keywords:

AES-CBC Encryption, Cryptography, Digital Image Processing, Feature-Based Key Derivation , Dynamic Key Generation, LSB Embedding, Image Security, Image Steganography

Abstract

This research presents a technique for concealing messages within images by combining AES encryption in Cipher Block Chaining (CBC) mode with Least Significant Bit (LSB) embedding. A key feature of this method is the dynamic generation of the encryption key based on intrinsic statistical properties of the image—specifically, the standard deviation of the RGB channels— This eliminates the necessity for external key exchange, making the encryption process inherently dependent on the image itself. The secret message is first encrypted using AES-CBC, and the resulting ciphertext is embedded into the image using LSB manipulation. The proposed approach was evaluated using standard image quality metrics. Experimental results reveal excellent preservation of visual quality, with a Mean Squared Error (MSE) of 0.000091, Mean Absolute Error (MAE) of 0.000091, Peak Signal-to-Noise Ratio (PSNR) of 88.53 dB, Structural Similarity Index Measure (SSIM) of 1.000000, and a coefficient of determination (R²) of 1.000000. A total of 336 pixel-level changes were detected, all strictly confined to the LSBs, resulting in a 100% LSB-only modification ratio. These outcomes confirm that the proposed method ensures both strong security and  the imperceptibility of the hidden data.

Downloads

How to Cite

Fadhil Kamil, M., & Qasim Mohammed, A. (2025). Secure Image Steganography Using AES-CBC Encryption and Dynamic Key Derivation from Image Features. International Journal of Advances in Scientific Research and Engineering (IJASRE), ISSN:2454-8006, DOI: 10.31695/IJASRE, 11(10), 79–91. https://doi.org/10.31695/IJASRE.2025.10.7