DiffMark: Diffusion-based Robust Watermark Against Deepfakes

TL;DR

DiffMark is a diffusion-based watermarking framework designed to embed robust watermarks into facial images, effectively resisting Deepfake manipulations through innovative training, sampling, and adversarial guidance techniques.

Contribution

The paper introduces a novel diffusion model-based watermarking method with a cross information fusion module and Deepfake-resistant guidance, enhancing robustness against Deepfake attacks.

Findings

DiffMark effectively resists Deepfake manipulations.

Watermarks are seamlessly fused during image generation.

Experimental results show superior robustness compared to existing methods.

Abstract

Deepfakes pose significant security and privacy threats through malicious facial manipulations. While robust watermarking can aid in authenticity verification and source tracking, existing methods often lack the sufficient robustness against Deepfake manipulations. Diffusion models have demonstrated remarkable performance in image generation, enabling the seamless fusion of watermark with image during generation. In this study, we propose a novel robust watermarking framework based on diffusion model, called DiffMark. By modifying the training and sampling scheme, we take the facial image and watermark as conditions to guide the diffusion model to progressively denoise and generate corresponding watermarked image. In the construction of facial condition, we weight the facial image by a timestep-dependent factor that gradually reduces the guidance intensity with the decrease of noise, thus better adapting to the sampling process of diffusion model. To achieve the fusion of watermark condition, we introduce a cross information fusion (CIF) module that leverages a learnable embedding table to adaptively extract watermark features and integrates them with image features via cross-attention. To enhance the robustness of the watermark against Deepfake manipulations, we integrate a frozen autoencoder during training phase to simulate Deepfake manipulations. Additionally, we introduce Deepfake-resistant guidance that employs specific Deepfake model to adversarially guide the diffusion sampling process to generate more robust watermarked images. Experimental results demonstrate the effectiveness of the proposed DiffMark on typical Deepfakes. Our code will be available at https://github.com/vpsg-research/DiffMark.