Sterilization of image steganography using self-supervised convolutional neural network

Abstract

Background: With the development of steganography technology, lawbreakers can implement covert communication in social networks more easily, exacerbating network security risks. Sterilization of image steganography methods can eliminate secret messages to block the transmission of illegal covert communication. However, existing methods overly rely on cover-stego image pairs and are unable to sanitize unknown image, which reduces stego image blocking rate in social networks.

Methods: To address the above problems, this paper proposes an effective sterilization of image steganography method using self-supervised convolutional neural network (SS-Net), which does not require any prior knowledge of image steganography schemes. SS-Net includes a purification module and a refinement module. Firstly, the pixel-shuffle down-sampling in purification module is adopted to reduce the spatial correlation of pixels in the stgeo image, and improve the learning mode from supervised learning to self-supervised learning. Secondly, centrally masked convolutions and dilated convolution residual blocks are merged to eliminate secret messages and avoid image quality degradation. Finally, a refinement module is employed to improve image texture details and boundaries.

Results: A series of experiments show that SS-Net from BOSSbase test sets is able to balance the destruction of secret messages with image quality, achieving 100% blocking rate of stego image. Meanwhile, our method outperforms the state-of-the-art methods in secret messages elimination ability and image quality preserving ability.

Keywords: Image steganalysis; Self-supervised learning; Steganography; Steganography sterilization.

Figure 1. The overall process of SS-Net.

SS-Net includes a purification module and a refinement module.

Figure 2. Comparison between self-supervised SS-Net and ordinary network training methods.

(A) Ordinary network. (B) SS-Net.

Figure 3. The process of pixel-shuffle down-sampling.

Figure 4. The overall architecture of the purification module.

Figure 5. The overall process of refinement module.

Figure 6. Illustration of the experiment through the SS-Net method.