ProMark: Proactive Diffusion Watermarking for Causal Attribution
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10802-10811
Abstract
Generative AI (GenAI) is transforming creative work-flows through the capability to synthesize and manipulate images via high-level prompts. Yet creatives are not well supported to receive recognition or reward for the use of their content in GenAI training. To this end, we propose ProMark, a causal attribution technique to attribute a synthetically generated image to its training data concepts like objects, motifs, templates, artists, or styles. The concept information is proactively embedded into the input training images using imperceptible watermarks, and the diffusion models (unconditional or conditional) are trained to retain the corresponding watermarks in generated images. We show that we can embed as many as 2 16 unique water-marks into the training data, and each training image can contain more than one watermark. ProMark can maintain image quality whilst outperforming correlation-based attribution. Finally, several qualitative examples are presented, providing the confidence that the presence of the watermark conveys a causative relationship between training data and synthetic images.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- On Distillation of Guided Diffusion Models2023
- MaLP: Manipulation Localization Using a Proactive Scheme2023
- RepMix: Representation Mixing for Robust Attribution of Synthesized Images2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Proactive Image Manipulation Detection2022
- A Self-Supervised Descriptor for Image Copy Detection2022
- Deep Image Comparator: Learning to Visualize Editorial Change2021
- Camera Trace Erasing2020
- Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems2020
- ImageNet: A large-scale hierarchical image database2009