PEEL: A Provable Removal Attack on Deep Hiding
This addresses security concerns for users of deep hiding by exposing and exploiting hidden vulnerabilities, representing a novel attack method rather than an incremental improvement.
The paper tackled vulnerabilities in deep hiding schemes by proposing a provable removal attack (PEEL) using image inpainting, which completely removes secret images with negligible impact on container quality.
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.