CLUE-MARK: Watermarking Diffusion Models using CLWE
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909758748884992 |
|---|---|
| author | Shehata, Kareem Kolluri, Aashish Saxena, Prateek |
| author_facet | Shehata, Kareem Kolluri, Aashish Saxena, Prateek |
| contents | As AI-generated images become widespread, reliable watermarking is essential for content verification, copyright enforcement, and combating disinformation. Existing techniques rely on heuristic approaches and lack formal guarantees of undetectability, making them vulnerable to steganographic attacks that can expose or erase the watermark. Additionally, these techniques often degrade output quality by introducing perceptible changes, which is not only undesirable but an important barrier to adoption in practice.
In this work, we introduce CLUE-Mark, the first provably undetectable watermarking scheme for diffusion models. CLUE-Mark requires no changes to the model being watermarked, is computationally efficient, and because it is provably undetectable is guaranteed to have no impact on model output quality. Our approach leverages the Continuous Learning With Errors (CLWE) problem -- a cryptographically hard lattice problem -- to embed watermarks in the latent noise vectors used by diffusion models. By proving undetectability via reduction from a cryptographically hard problem we ensure not only that the watermark is imperceptible to human observers or adhoc heuristics, but to \emph{any} efficient detector that does not have the secret key. CLUE-Mark allows multiple keys to be embedded, enabling traceability of images to specific users without altering model parameters. Empirical evaluations on state-of-the-art diffusion models confirm that CLUE-Mark achieves high recoverability, preserves image quality, and is robust to minor perturbations such JPEG compression and brightness adjustments. Uniquely, CLUE-Mark cannot be detected nor removed by recent steganographic attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_11434 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CLUE-MARK: Watermarking Diffusion Models using CLWE Shehata, Kareem Kolluri, Aashish Saxena, Prateek Cryptography and Security As AI-generated images become widespread, reliable watermarking is essential for content verification, copyright enforcement, and combating disinformation. Existing techniques rely on heuristic approaches and lack formal guarantees of undetectability, making them vulnerable to steganographic attacks that can expose or erase the watermark. Additionally, these techniques often degrade output quality by introducing perceptible changes, which is not only undesirable but an important barrier to adoption in practice. In this work, we introduce CLUE-Mark, the first provably undetectable watermarking scheme for diffusion models. CLUE-Mark requires no changes to the model being watermarked, is computationally efficient, and because it is provably undetectable is guaranteed to have no impact on model output quality. Our approach leverages the Continuous Learning With Errors (CLWE) problem -- a cryptographically hard lattice problem -- to embed watermarks in the latent noise vectors used by diffusion models. By proving undetectability via reduction from a cryptographically hard problem we ensure not only that the watermark is imperceptible to human observers or adhoc heuristics, but to \emph{any} efficient detector that does not have the secret key. CLUE-Mark allows multiple keys to be embedded, enabling traceability of images to specific users without altering model parameters. Empirical evaluations on state-of-the-art diffusion models confirm that CLUE-Mark achieves high recoverability, preserves image quality, and is robust to minor perturbations such JPEG compression and brightness adjustments. Uniquely, CLUE-Mark cannot be detected nor removed by recent steganographic attacks. |
| title | CLUE-MARK: Watermarking Diffusion Models using CLWE |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2411.11434 |