Purified and Unified Steganographic Network

TL;DR

PUSNet introduces a purified, unified steganographic network that conceals both secret encoding and decoding networks within a single sparse backbone. By using a key-driven sparse weight filling mechanism, the purified network can be switched to hidden steganographic modes without side information, enabling covert embedding, recovery, and legitimate denoising in one architecture. The method employs embedding, recovery, and purified losses and a shared sparse weight set, achieving high visual quality for stego and recovered images while maintaining strong undetectability against traditional steganalysis and DNN-based detectors. Experiments on DIV2K, COCO, and ImageNet demonstrate competitive denoising performance, effective secret embedding/recovery, and practical stealth, with code available online.

Abstract

Steganography is the art of hiding secret data into the cover media for covert communication. In recent years, more and more deep neural network (DNN)-based steganographic schemes are proposed to train steganographic networks for secret embedding and recovery, which are shown to be promising. Compared with the handcrafted steganographic tools, steganographic networks tend to be large in size. It raises concerns on how to imperceptibly and effectively transmit these networks to the sender and receiver to facilitate the covert communication. To address this issue, we propose in this paper a Purified and Unified Steganographic Network (PUSNet). It performs an ordinary machine learning task in a purified network, which could be triggered into steganographic networks for secret embedding or recovery using different keys. We formulate the construction of the PUSNet into a sparse weight filling problem to flexibly switch between the purified and steganographic networks. We further instantiate our PUSNet as an image denoising network with two steganographic networks concealed for secret image embedding and recovery. Comprehensive experiments demonstrate that our PUSNet achieves good performance on secret image embedding, secret image recovery, and image denoising in a single architecture. It is also shown to be capable of imperceptibly carrying the steganographic networks in a purified network. Code is available at \url{https://github.com/albblgb/PUSNet}

Figures (8)

• Figure 1: Administrator covertly transmits the secret steganographic networks to agents using the proposed PUSNet.
• Figure 2: The agents (i.e., sender and receiver) perform the covert communication task using the received steganographic networks.
• Figure 3: An overview of our proposed method.
• Figure 4: The architecture of the PUSNet.
• Figure 5: Examples of the stego and recovered images generated using different schemes, with a green border on the original images, an orange border on the generated images, and a blue border on × 5 magnified residuals between them. The cover/stego and secret/recovered images are given in the first two rows and the last two rows, respectively.