An Embedding Cost Learning Framework Using GAN

• Published in: IEEE transactions on information forensics and security Vol. 15; pp. 839 - 851
• Main Authors: Yang, Jianhua, Ruan, Danyang, Huang, Jiwu, Kang, Xiangui, Shi, Yun-Qing
• Format: Journal Article
• Language: English
• Published: New York IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive steganography; Artificial neural networks; Back propagation; Computer architecture; Computer simulation; Convolution; Distortion; Embedding; Feature extraction; Gallium nitride; generative adversarial networks (GAN); Generators; High pass filters; Machine learning; Payloads; steganalysis; Steganography; Training
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2019.2922229

Successful adaptive steganography has mainly focused on embedding the payload while minimizing an appropriately defined distortion function. The application of deep learning to steganalysis has greatly challenged present adaptive steganographic methods, but has also shown the potential for the improvement of steganography. This paper proposes a distortion function generating a framework for steganography. It has three modules: a generator with a U-Net architecture to translate a cover image into an embedding change probability map, a no-pre-training-required double-tanh function to approximate the optimal embedding simulator while preserving gradient norm during backpropagation in the adversarial training, and an enhanced steganalyzer based on a convolution neural network together with multiple high pass filters as the discriminator. Extensive experimental results on different datasets have shown that the proposed framework outperforms the current state-of-the-art steganographic schemes. Moreover, the adversarial training time is reduced dramatically compared with the GAN-based automatic steganographic distortion learning framework (ASDL-GAN).