Invisible Watermarks: Attacks and Robustness

TL;DR

This paper enhances invisible watermarking techniques for generated images by introducing a watermark remover network and localized blurring attacks, improving robustness while minimizing image quality degradation.

Contribution

It proposes a novel watermark remover network that preserves one watermark modality while removing the other and introduces localized blurring attacks based on GradCAM heatmaps.

Findings

Watermark remover slightly improves decoding performance.

Localized blurring attacks cause less image degradation than uniform blurring.

The methods enhance robustness of invisible watermarks against attacks.

Abstract

As Generative AI continues to become more accessible, the case for robust detection of generated images in order to combat misinformation is stronger than ever. Invisible watermarking methods act as identifiers of generated content, embedding image- and latent-space messages that are robust to many forms of perturbations. The majority of current research investigates full-image attacks against images with a single watermarking method applied. We introduce novel improvements to watermarking robustness as well as minimizing degradation on image quality during attack. Firstly, we examine the application of both image-space and latent-space watermarking methods on a single image, where we propose a custom watermark remover network which preserves one of the watermarking modalities while completely removing the other during decoding. Then, we investigate localized blurring attacks (LBA) on watermarked images based on the GradCAM heatmap acquired from the watermark decoder in order to reduce the amount of degradation to the target image. Our evaluation suggests that 1) implementing the watermark remover model to preserve one of the watermark modalities when decoding the other modality slightly improves on the baseline performance, and that 2) LBA degrades the image significantly less compared to uniform blurring of the entire image. Code is available at: https://github.com/tomputer-g/IDL_WAR