Abstract
In the time when the communication mode is changing towards the digital aspect, such as; computing devices and the internet, it is natural that there is a need to safeguard the safety as well as the privacy of the data being shared, which can also compromise the integrity. Image steganography is a technique that conceals messages in pictures taken on a digital camera, and serves as a means of secure data trans-mission. In this study, we provide a novel method for image watermarks which is highly secure and robust through the application of Recur-rent Neural Systems and fuzzy logic. By merging fuzzy logic with the flexibility of Recurrent Neural networks, the proposed system enhances the protection and rate of hidden information even under noise, compression and other attacks. The model utilizes the learning capabilities of Recurrent Neural networks for optimization of the embedding process, while the Recurrent Neural model is useful for managing uncertainty and improving decision-making processes. Such two-layered systems ensure the inaudibility and invisibility of steganographic data while limiting the embedding of large amounts of visible data, which is highly effective. Robustness and security of the method is tested by using various images types within different environments. To enhance the efficiency and robustness of steganography of images, this work proposes an innovative two-layer method that combines fuzzy logic with Recurrent Neural Networks (RNNs). By enhancing embedding, strengthening attack resistance, and offering an adaptable, intelligent framework for safe data concealing, it advances the field. It was observed that compared to other techniques used in steganography approaches, it is pleasing to note that the whole embedding efficiency and resistance to attacks are far and above enhancement candidates. The results demonstrate that the seamless integration of fuzzy logic and Recurrent Neural Systems provides an efficient and scalable framework for secure image steganography.