Erase and Repair: An Efficient Box-Free Removal Attack on High-Capacity Deep Hiding

TL;DR

This paper introduces a novel, efficient box-free removal attack on deep hiding schemes that effectively erases secret images from container images without prior knowledge, using inpainting and repair techniques to preserve image quality.

Contribution

The paper presents the first box-free removal attack on deep hiding schemes, including an advanced EBRA method that employs inpainting to remove secrets and repair images, demonstrating high effectiveness and minimal visual impact.

Findings

Successfully removes secret images with high accuracy

Preserves container image quality with negligible distortion

Effective against adversarially trained deep hiding schemes

Abstract

Deep hiding, embedding images with others using deep neural networks, has demonstrated impressive efficacy in increasing the message capacity and robustness of secret sharing. In this paper, we challenge the robustness of existing deep hiding schemes by preventing the recovery of secret images, building on our in-depth study of state-of-the-art deep hiding schemes and their vulnerabilities. Leveraging our analysis, we first propose a simple box-free removal attack on deep hiding that does not require any prior knowledge of the deep hiding schemes. To improve the removal performance on the deep hiding schemes that may be enhanced by adversarial training, we further design a more powerful removal attack, efficient box-free removal attack (EBRA), which employs image inpainting techniques to remove secret images from container images. In addition, to ensure the effectiveness of our attack and preserve the fidelity of the processed container images, we design an erasing phase based on the locality of deep hiding to remove secret information and then make full use of the visual information of container images to repair the erased visual content. Extensive evaluations show our method can completely remove secret images from container images with negligible impact on the quality of container images.