Adaptive Spatial Steganography Based on Probability-Controlled Adversarial Examples
This work addresses steganography methods for hiding data in images, but it is incremental and currently invalid due to errors.
The paper originally tackled adaptive spatial steganography using probability-controlled adversarial examples, but the abstract reveals that the experiments were flawed due to a misused API in Caffe, leading to incorrect results and analysis, with a corrected version submitted for revision.
Explanation from Sai Ma: The experiments in this paper are conducted on Caffe framework. In Caffe, there is an API to directly set the gradient in Matlab. I wrongly use it to control the 'probability', in fact, I modify the gradient directly. The misusage of API leads to wrong experiment results, and wrong theoretical analysis. Apologize to readers who have read this paper. We have submitted a correct version of this paper to Multimedia Tools and Applications and it is under revision. Thanks to Dr. Patrick Bas, who is the Associate Editor of TIFS and the anonymous reviewers of this paper. Thanks to Tingting Song from Sun Yat-sen University. We discussed some problems of this paper. Her advice helps me to improve the submitted paper to Multimedia Tools and Applications.