InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance

TL;DR

InvisMark introduces a highly imperceptible, robust watermarking method for AI-generated images that supports large payloads and maintains high accuracy under various manipulations, enhancing media provenance verification.

Contribution

The paper presents InvisMark, a novel neural network-based watermarking technique that achieves state-of-the-art imperceptibility, high payload capacity, and robustness against image manipulations.

Findings

Achieves PSNR~51 and SSIM~0.998 indicating high imperceptibility.

Maintains over 97% bit accuracy across various image manipulations.

Successfully encodes 256-bit watermarks with near-perfect decoding rates.

Abstract

The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages advanced neural network architectures and training strategies to embed imperceptible yet highly robust watermarks. InvisMark achieves state-of-the-art performance in imperceptibility (PSNR$\sim$51, SSIM $\sim$ 0.998) while maintaining over 97\% bit accuracy across various image manipulations. Notably, we demonstrate the successful encoding of 256-bit watermarks, significantly expanding payload capacity while preserving image quality. This enables the embedding of UUIDs with error correction codes, achieving near-perfect decoding success rates even under challenging image distortions. We also address potential vulnerabilities against advanced attacks and propose mitigation strategies. By combining high imperceptibility, extended payload capacity, and resilience to manipulations, InvisMark provides a robust foundation for ensuring media provenance in an era of increasingly sophisticated AI-generated content. Source code of this paper is available at: https://github.com/microsoft/InvisMark.