METR: Image Watermarking with Large Number of Unique Messages

TL;DR

This paper introduces METR and METR++, innovative watermarking algorithms for images that can encode numerous unique messages, resist attacks, and maintain high image quality, especially tailored for diffusion models.

Contribution

The paper presents METR and METR++, new watermarking methods capable of encoding many messages with robustness and high image fidelity, extending capabilities for diffusion model applications.

Findings

METR encodes multiple messages without compromising attack resistance or image quality.

METR++ can inject an unlimited number of unique messages within the Latent Diffusion Model.

Both methods demonstrate robustness to attacks and suitability for real-world use.

Abstract

Improvements in diffusion models have boosted the quality of image generation, which has led researchers, companies, and creators to focus on improving watermarking algorithms. This provision would make it possible to clearly identify the creators of generative art. The main challenges that modern watermarking algorithms face have to do with their ability to withstand attacks and encrypt many unique messages, such as user IDs. In this paper, we present METR: Message Enhanced Tree-Ring, which is an approach that aims to address these challenges. METR is built on the Tree-Ring watermarking algorithm, a technique that makes it possible to encode multiple distinct messages without compromising attack resilience or image quality. This ensures the suitability of this watermarking algorithm for any Diffusion Model. In order to surpass the limitations on the quantity of encoded messages, we propose METR++, an enhanced version of METR. This approach, while limited to the Latent Diffusion Model architecture, is designed to inject a virtually unlimited number of unique messages. We demonstrate its robustness to attacks and ability to encrypt many unique messages while preserving image quality, which makes METR and METR++ hold great potential for practical applications in real-world settings. Our code is available at https://github.com/deepvk/metr