Towards automatic embedding cost learning for JPEG steganography
Document Type
Conference Proceeding
Publication Date
7-2-2019
Abstract
Current mainstream methods for digital image steganography are content adaptive. That is, the secret messages are embedded in the complicated region in the cover image while minimizing the embedding distortion so as to suppress statistical detectability. Since there is already a practical encoding scheme for data embedding near the payload-distortion bound, the design of the embedding cost function becomes a deterministic part in steganography. Unlike the traditional heuristic hand-crafted method, this paper proposes a novel generative adversarial network based framework to automatically learn the embedding cost function for JPEG steganography. The proposed framework consists of a generator, a gradient-descent friendly inverse discrete cosine transformation module, an embedding simulator and a discriminator for steganalysis. Through training the generator and discriminator in alternation, the embedding cost function can finally be obtained by the trained generator. Experimental results demonstrate that our method can automatically learn a reasonable embedding cost function and achieve a satisfying performance.
Identifier
85069957865 (Scopus)
ISBN
[9781450368216]
Publication Title
Ih and Mmsec 2019 Proceedings of the ACM Workshop on Information Hiding and Multimedia Security
External Full Text Location
https://doi.org/10.1145/3335203.3335713
First Page
37
Last Page
46
Grant
61772571
Fund Ref
National Natural Science Foundation of China
Recommended Citation
Yang, Jianhua; Ruan, Danyang; Kang, Xiangui; and Shi, Yun Qing, "Towards automatic embedding cost learning for JPEG steganography" (2019). Faculty Publications. 7461.
https://digitalcommons.njit.edu/fac_pubs/7461