Automatic Steganographic Distortion Learning Using a Generative Adversarial Network

TLDR

Generative adversarial networks can produce artificial samples indistinguishable from real ones by having two subnetworks compete. This work proposes an automatic steganographic distortion learning framework that uses a GAN composed of a steganographic generative subnetwork and a steganalytic discriminative subnetwork. The framework alternately trains these subnetworks to learn per‑pixel embedding change probabilities, converts them into embedding distortions, and links the distortion function to the evolving steganalyzer’s undetectability. Experiments show that adversarial learning evolves the embedding from naive random ±1 to advanced content‑adaptive embedding in textural regions, with security performance steadily improving as training progresses.

Abstract

Generative adversarial network has shown to effectively generate artificial samples indiscernible from their real counterparts with a united framework of two subnetworks competing against each other. In this letter, we first propose an automatic steganographic distortion learning framework using a generative adversarial network, which is composed of a steganographic generative subnetwork and a steganalytic discriminative subnetwork. Via alternately training these two oppositional subnetworks, our proposed framework can automatically learn embedding change probabilities for every pixel in a given spatial cover image. The learnt embedding change probabilities can then be converted to embedding distortions, which can be adopted in the existing framework of minimal-distortion embedding. Under this framework, the distortion function is directly related to the undetectability against the oppositional evolving steganalyzer. Experimental results show that with adversarial learning, our proposed framework can effectively evolve from nearly naive random ±1 embedding at the beginning to much more advanced content-adaptive embedding which tries to embed secret bits in textural regions. The security performance is also steadily improved with increasing training iterations.