Steganalysis for Small-Scale Training Image Pairs with Cover-Stego Feature Difference Model
Chao Ying Xia, Yaqi Liu, Qingxiao Guan, Sai Ma, Yu Nan, Jiahui Fu · 2022
Current steganalytic classifiers always need a large number of cover-stego image pairs for training. However in this paper we focus on a scenario where steganalysts have a few cover-stego image pairs in hand. Meanwhile steganalysts have no knowledge of the embedding algorithm, and cannot generate corresponding stego images after collecting additional cover images. Hence in this scenario steganalysts cannot match more cover-stego image pairs to augment the training set. To address this issue, we propose a stego feature simulation method to artificially generate cover-stego feature pairs for training. First, we design a cover-stego feature difference model to build the relationship between cover and stego features in pairs. Then, we estimate the model parameters from a few existing cover-stego image pairs in hand. Finally, after extracting steganalytic features from additionally collected cover images, we simulate corresponding stego features with the cover-stego feature difference model to match artificial feature pairs. The experimental results demonstrate that our method can effectively mitigate the shortage of training image pairs by adding adequate artificial feature pairs into training.