Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.19090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908982858219520 |
|---|---|
| author | Xie, JinFeng Ou, Chengfu Yu, Peipeng Zhou, Xiaoyu Huang, Dingding Fei, Jianwei Shen, Zixuan Xia, Zhihua |
| author_facet | Xie, JinFeng Ou, Chengfu Yu, Peipeng Zhou, Xiaoyu Huang, Dingding Fei, Jianwei Shen, Zixuan Xia, Zhihua |
| contents | The rapid adoption of diffusion-based generative models has intensified concerns over the attribution and integrity of AI-generated content (AIGC). Existing single-domain watermarking methods either fail under regeneration, remain vulnerable to black-box reprompting that enables adversarial framing, or provide no spatial evidence for tampered regions. We propose Dual-Guard, a dual-channel latent watermarking framework for practical provenance verification, framing resistance, and region-level tamper localization. Dual-Guard combines two complementary anchors: a Gaussian Shading watermark in the initial diffusion noise as a global provenance signal, and a Latent Fingerprint Codec in the final denoised latent as a structured content anchor. Reprompting tends to preserve the former while breaking the latter, whereas localized edits disturb the content anchor only in tampered regions. In Full mode on a 2,400-sample benchmark, Dual-Guard keeps clean-image authentication false rejection and tamper false alarm below one half of one percent, while maintaining near-complete detection under reprompting, diffusion editing, and eight local tampering attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19090 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images Xie, JinFeng Ou, Chengfu Yu, Peipeng Zhou, Xiaoyu Huang, Dingding Fei, Jianwei Shen, Zixuan Xia, Zhihua Cryptography and Security The rapid adoption of diffusion-based generative models has intensified concerns over the attribution and integrity of AI-generated content (AIGC). Existing single-domain watermarking methods either fail under regeneration, remain vulnerable to black-box reprompting that enables adversarial framing, or provide no spatial evidence for tampered regions. We propose Dual-Guard, a dual-channel latent watermarking framework for practical provenance verification, framing resistance, and region-level tamper localization. Dual-Guard combines two complementary anchors: a Gaussian Shading watermark in the initial diffusion noise as a global provenance signal, and a Latent Fingerprint Codec in the final denoised latent as a structured content anchor. Reprompting tends to preserve the former while breaking the latter, whereas localized edits disturb the content anchor only in tampered regions. In Full mode on a 2,400-sample benchmark, Dual-Guard keeps clean-image authentication false rejection and tamper false alarm below one half of one percent, while maintaining near-complete detection under reprompting, diffusion editing, and eight local tampering attacks. |
| title | Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2604.19090 |