SSGAN: Secure Steganography Based on Generative Adversarial Networks
This work addresses steganography security for data hiding applications, but it appears incremental as it builds on existing GAN methods with modifications.
The paper tackles the problem of generating secure and suitable cover images for steganography by proposing SSGAN, a method based on generative adversarial networks, which improves convergence speed, training stability, and image quality compared to existing approaches.
In this paper, a novel strategy of Secure Steganograpy based on Generative Adversarial Networks is proposed to generate suitable and secure covers for steganography. The proposed architecture has one generative network, and two discriminative networks. The generative network mainly evaluates the visual quality of the generated images for steganography, and the discriminative networks are utilized to assess their suitableness for information hiding. Different from the existing work which adopts Deep Convolutional Generative Adversarial Networks, we utilize another form of generative adversarial networks. By using this new form of generative adversarial networks, significant improvements are made on the convergence speed, the training stability and the image quality. Furthermore, a sophisticated steganalysis network is reconstructed for the discriminative network, and the network can better evaluate the performance of the generated images. Numerous experiments are conducted on the publicly available datasets to demonstrate the effectiveness and robustness of the proposed method.