DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910164048674816 |
|---|---|
| author | Graf, Mathias Willi, Marco Mathys, Melanie Aerni, Michael Schwarzer, Christian Melchior, Martin Graber, Michael H. |
| author_facet | Graf, Mathias Willi, Marco Mathys, Melanie Aerni, Michael Schwarzer, Christian Melchior, Martin Graber, Michael H. |
| contents | AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trusted sources pose a serious threat, undermining public trust in image authenticity. We propose DeepSignature, a novel approach that integrates the guarantees of digital signatures with the capabilities of deep neural networks. Neural networks are used both to generate content-encoding watermarks and to embed them imperceptibly into images while ensuring robust extraction. These watermarks are cryptographically verifiable, enabling source attribution and image integrity validation. DeepSignature is compatible with existing image formats and requires no special handling of signed images. It supports client-side verification, requiring only the signer's public key. Additionally, we introduce a novel latent-space verification approach to detect and localize tampering attempts. We evaluate DeepSignature in terms of imperceptibility, robustness to benign transformations, forgery detection, and its resilience against various attack scenarios. Our results highlight the inherent trade-offs between imperceptibility, robustness, and integrity verification. We demonstrate that DeepSignature reliably identifies significant forgery attempts -- achieving near 100\% in our experiments. Finally, we emphasize DeepSignature's modularity and tunable parameters, allowing adaptation to application-specific requirements. Code and model weights will be published. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23016 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication Graf, Mathias Willi, Marco Mathys, Melanie Aerni, Michael Schwarzer, Christian Melchior, Martin Graber, Michael H. Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition I.4.9; K.6.5 AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trusted sources pose a serious threat, undermining public trust in image authenticity. We propose DeepSignature, a novel approach that integrates the guarantees of digital signatures with the capabilities of deep neural networks. Neural networks are used both to generate content-encoding watermarks and to embed them imperceptibly into images while ensuring robust extraction. These watermarks are cryptographically verifiable, enabling source attribution and image integrity validation. DeepSignature is compatible with existing image formats and requires no special handling of signed images. It supports client-side verification, requiring only the signer's public key. Additionally, we introduce a novel latent-space verification approach to detect and localize tampering attempts. We evaluate DeepSignature in terms of imperceptibility, robustness to benign transformations, forgery detection, and its resilience against various attack scenarios. Our results highlight the inherent trade-offs between imperceptibility, robustness, and integrity verification. We demonstrate that DeepSignature reliably identifies significant forgery attempts -- achieving near 100\% in our experiments. Finally, we emphasize DeepSignature's modularity and tunable parameters, allowing adaptation to application-specific requirements. Code and model weights will be published. |
| title | DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication |
| topic | Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition I.4.9; K.6.5 |
| url | https://arxiv.org/abs/2604.23016 |