InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917841487265792 |
|---|---|
| author | Xu, Rui Hu, Mengya Lei, Deren Li, Yaxi Lowe, David Gorevski, Alex Wang, Mingyu Ching, Emily Deng, Alex |
| author_facet | Xu, Rui Hu, Mengya Lei, Deren Li, Yaxi Lowe, David Gorevski, Alex Wang, Mingyu Ching, Emily Deng, Alex |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07795 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance Xu, Rui Hu, Mengya Lei, Deren Li, Yaxi Lowe, David Gorevski, Alex Wang, Mingyu Ching, Emily Deng, Alex Cryptography and Security Artificial Intelligence 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. |
| title | InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2411.07795 |