Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images

• URL: http://arxiv.org/abs/2604.19090v1
• Date: Tue, 21 Apr 2026 05:03:42 GMT
• Title: Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images
• Abstract summary: We propose Dual-Guard, a dual-channel latent watermarking framework for provenance verification, framing resistance, and region-level tamper localization.<n>In Full mode, 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.
• Score: 19.688873186557483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks [68.64050157343334]
  Existing watermarks preserve provenance under editing, but this same robustness allows an adversary to alter critical content while retaining attribution.<n>We introduce an innovative watermark that jointly provides provenance and tamper evidence.<n>The signals share the same mechanism but use independent keys and different seeding windows over normalized text, making one resilient to edits and the other sensitive to reader-visible changes.
  arXiv  Detail & Related papers  (2026-08-13T01:55:16Z)
• BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models [0.0]
  BiSLW is a trainable bi-spectral latent watermarking framework that embeds aligned identity signals across complementary spectral bands.<n>Low-frequency components encode global semantics, while high-frequency components capture fine texture.<n>BiSLW achieves a strong balance between fidelity and robustness, improving PSNR by over 3 dB compared to prior latent diffusion watermarking methods.
  arXiv  Detail & Related papers  (2026-07-02T17:48:54Z)
• PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection [2.9276293999058898]
  dependence of semantic watermarking on diffusion inversion for watermark detection creates a critical vulnerability.<n>We propose Progressive Guided Inversion and Denoising (PGID), the first plug-and-play, training-free noise extraction framework designed to defend against both attack strategies.
  arXiv  Detail & Related papers  (2026-05-10T04:32:57Z)
• High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking [27.912549423920243]
  We present VeriFi, a versatile watermarking framework that unifies copyright protection, pixel-level manipulation localization, and high-fidelity face content recovery.<n>It makes three key contributions: (1) it embeds a compact semantic latent watermark that serves as an content-preserving prior, enabling faithful restoration even after severe manipulations; (2) it achieves fine-grained localization without embedding localization-specific artifacts by correlating image features with decoded provenance signals; and (3) it introduces an AIGC attack simulator that combines latent-space mixing with seamless blending to improve robustness to realistic deepfake pipelines.
  arXiv  Detail & Related papers  (2026-03-25T05:02:48Z)
• Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection [53.789057575175065]
  Region-Aware Prompt Augmentation (RAPTA) and Attention-Driven Multimodal Copy Detection (ADMCD) are presented.<n>RAPTA uses an object detector to find salient regions and turn them into semantically grounded prompt variants.<n>ADMCD aggregates local patch, global semantic, and texture cues with a lightweight transformer to produce a fused representation.<n>Experiments show that RAPTA reduces overfitting while maintaining high synthesis quality, and that ADMCD reliably detects copying, outperforming single-modal metrics.
  arXiv  Detail & Related papers  (2026-03-13T15:16:27Z)
• RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces [16.612226216769262]
  We propose RecoverMark, a watermarking framework that achieves robust manipulation localization, content recovery, and ownership verification simultaneously.<n>Our key insight is twofold. First, we exploit a critical real-world constraint: an adversary must preserve the background's semantic consistency to avoid visual detection.<n>Based on these insights, RecoverMark treats the protected face content itself as the watermark and embeds it into the surrounding background.
  arXiv  Detail & Related papers  (2026-02-24T07:11:40Z)
• DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack [25.681637904431142]
  Cloud-based services have led to growing risks of model abuse in large language models (LLMs)<n>Existing watermarking algorithms primarily focus on defending against paraphrase attacks.<n>We propose DualGuard, the first watermarking algorithm capable of defending against both paraphrase and spoofing attacks.
  arXiv  Detail & Related papers  (2025-12-18T05:08:19Z)
• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models [55.05404953041403]
  We propose a novel framework that seamlessly integrates a binary watermark into the diffusion generation process.<n>We show that StableGuard consistently outperforms state-of-the-art methods in image fidelity, watermark verification, and tampering localization.
  arXiv  Detail & Related papers  (2025-09-22T16:35:19Z)
• TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity [76.98973481600002]
  This paper proposes a Tamper-Aware Generative image WaterMarking method named TAG-WM.<n>The proposed method comprises four key modules: a dual-mark joint sampling (DMJS) algorithm for embedding copyright and localization watermarks into the latent space while preserving generative quality.<n>The experimental results demonstrate that TAG-WM achieves state-of-the-art performance in both tampering robustness and localization capability even under distortion.
  arXiv  Detail & Related papers  (2025-06-30T03:14:07Z)
• Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models [52.877452505561706]
  We propose the first copyright evasion attack specifically designed to undermine dataset ownership verification (DOV)<n>Our CEAT2I comprises three stages: watermarked sample detection, trigger identification, and efficient watermark mitigation.<n>Our experiments show that our CEAT2I effectively evades DOV mechanisms while preserving model performance.
  arXiv  Detail & Related papers  (2025-05-05T17:51:55Z)
• Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal [63.576748565274706]
  This study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks.
  arXiv  Detail & Related papers  (2023-12-22T02:19:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.