Joint Adaptive Robust Steganography Network

Transmission distortions within steganography systems easily cause dramatic degradations of revealing and invisibility performances. Previous works lacked sufficient adaptation for different distortions, which hinders the performance improvement of robust image steganography. This article proposes joint adaptive robust steganography network (JARS-Net). Specifically, the hierarchical attentive invertible (HAI) mechanism is first proposed to achieve adaptive feature tuning by gradually adjusting and fusing the cover-secret information from different depths and scales. Moreover, adaptive key learning (AKL) is proposed as an adaptive steganography strategy to generate adaptive keys for secret recovery under different distortions. Furthermore, benefiting from the joint of reversible HAI and the soft AKL, revealed secret images can be progressively decoupled from the received stego images along the backward HAI flow. Extensive experiments demonstrate that the proposed JARS-Net can significantly promote the invisibility and revealing performances of covert communication under different distortions.