Image steganalysis using deep learning models

In the domain of digital steganography, the problem of efficient and accurate steganalysis is of utmost importance. Steganalysis seeks to detect the presence of hidden data within digital media, a task that is continually evolving due to advancements in steganographic techniques. This study undertakes a detailed exploration of the SRNet model, a prominent deep learning model for steganalysis. We aim to evaluate the impact of various factors, including choice of deep learning framework, model initialization and optimization parameters, and architectural modifications on the model's steganalysis performance. Three separate implementations of the SRNet model are examined in this study: our custom implementation, an implementation using TensorFlow, and another utilizing PyTorch. Each model is evaluated on its ability to detect different payloads, or bytes of hidden data per pixel, in digital images. This investigation includes a thorough comparative analysis of different performance metrics including accuracy, recall, precision, and F1-score. Our findings indicate that the choice of deep learning framework and the parameters utilized for model initialization and optimization play significant roles in influencing the model's steganalysis effectiveness. Notably, the TensorFlow implementation, enhanced with an additional dense layer, outperforms all other models. In contrast, our custom SRNet implementation, trained with fewer epochs, offers a balance between computational cost and steganalysis performance. This study thus provides valuable insights into the adaptability and potential of the SRNet model for steganalysis, illustrating the model's performance under different configurations and implementations. It underscores the importance of continued exploration and optimization in the field of steganalysis, offering guidance for future research in this evolving domain.