Examining the Application of Deep LSTM Neural Networks in Steganography of Textual Information in Digital Images

Abstract

Information security has emerged as a critical concern alongside the development of multimedia technology. Among the myriad security challenges, the secure transmission of sensitive information between parties has become a focal point of researchers. Encryption, involving mathematical techniques to ensure data security, is explored in this study. Specifically, the application of deep LSTM neural networks in concealing textual information within digital images is investigated. The approach involves embedding one image within another in a manner that prevents detection of the hidden image within the cover image, while textual content is covertly embedded within the image. The proposed method demonstrates superior performance based on three evaluation metrics—Peak Signal-to-Noise Ratio (PSNR) in decibels, Mean Squared Error (MSE), and accuracy rate in percentage—compared to three other benchmark images (lena.png, peppers.png, mandril.png, and monkey.png), achieving values of 93.665275 dB, 0.6945 MSE, and 97.23% accuracy, respectively.