Deep hiding, embedding images into another using deep neural networks, has shown its great power in increasing the message capacity and robustness. In this paper, we conduct an in-depth study of state-of-the-art deep hiding schemes and analyze their hidden vulnerabilities. Then, according to our observations and analysis, we propose a novel ProvablE rEmovaL attack (PEEL) using image inpainting to remove secret images from containers without any prior knowledge about the deep hiding scheme. We also propose a systemic methodology to improve the efficiency and image quality of PEEL by carefully designing a removal strategy and fully utilizing the visual information of containers. Extensive evaluations show our attacks can completely remove secret images and has negligible impact on the quality of containers.
@article{arxiv.2106.02779,
title = {PEEL: A Provable Removal Attack on Deep Hiding},
author = {Tao Xiang and Hangcheng Liu and Shangwei Guo and Tianwei Zhang},
journal= {arXiv preprint arXiv:2106.02779},
year = {2021}
}