DRAW: Defending Camera-shooted RAW against Image Manipulation
This addresses the risk of nefarious image manipulation for users of digital cameras and devices, offering a source-level protection method that is incremental in applying watermarking to RAW files.
The paper tackles the problem of defending digital images against manipulation by protecting camera-shooted RAW files, introducing a lightweight network that embeds invisible watermarks into RAW data, which transfers to RGB images and resists post-processing, enabling accurate localization of forged areas with extensive experimental validation on datasets like RAISE, FiveK, and SIDD.
RAW files are the initial measurement of scene radiance widely used in most cameras, and the ubiquitously-used RGB images are converted from RAW data through Image Signal Processing (ISP) pipelines. Nowadays, digital images are risky of being nefariously manipulated. Inspired by the fact that innate immunity is the first line of body defense, we propose DRAW, a novel scheme of defending images against manipulation by protecting their sources, i.e., camera-shooted RAWs. Specifically, we design a lightweight Multi-frequency Partial Fusion Network (MPF-Net) friendly to devices with limited computing resources by frequency learning and partial feature fusion. It introduces invisible watermarks as protective signal into the RAW data. The protection capability can not only be transferred into the rendered RGB images regardless of the applied ISP pipeline, but also is resilient to post-processing operations such as blurring or compression. Once the image is manipulated, we can accurately identify the forged areas with a localization network. Extensive experiments on several famous RAW datasets, e.g., RAISE, FiveK and SIDD, indicate the effectiveness of our method. We hope that this technique can be used in future cameras as an option for image protection, which could effectively restrict image manipulation at the source.