Image de couverture de livre

Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gao, Zheng, Li, Xiaoyu, Bao, Zhicheng, Feng, Xiaoyan, Jiang, Jiaojiao
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Cryptography and Security Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking
par: Gao, Zheng, et autres
Publié: (2026)

SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark
par: Bao, Rui, et autres
Publié: (2026)

SEAL: Semantic Aware Image Watermarking
par: Arabi, Kasra, et autres
Publié: (2025)

Bypassing LLM Watermarks with Color-Aware Substitutions
par: Wu, Qilong, et autres
Publié: (2024)

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
par: Li, Shuai, et autres
Publié: (2024)

SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
par: Zhang, Xin, et autres
Publié: (2026)

HMARK: Radioactive Multi-Bit Semantic-Latent Watermarking for Diffusion Models
par: Li, Kexin, et autres
Publié: (2025)

Privacy-Preserving Semantic Segmentation without Key Management
par: Hirose, Mare, et autres
Publié: (2026)

Certifiably Robust Image Watermark
par: Jiang, Zhengyuan, et autres
Publié: (2024)

WaterVIB: Learning Minimal Sufficient Watermark Representations via Variational Information Bottleneck
par: He, Haoyuan, et autres
Publié: (2026)

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
par: Xiao, Yaxin, et autres
Publié: (2025)

Removing Watermarks with Partial Regeneration using Semantic Information
par: Tallam, Krti, et autres
Publié: (2025)

VIDSTAMP: A Temporally-Aware Watermark for Ownership and Integrity in Video Diffusion Models
par: Teymoorianfard, Mohammadreza, et autres
Publié: (2025)

PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining
par: Li, Kecen, et autres
Publié: (2023)

AI-generated Image Detection: Passive or Watermark?
par: Guo, Moyang, et autres
Publié: (2024)

Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling
par: Chen, Pengzhen, et autres
Publié: (2026)

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
par: Müller, Andreas, et autres
Publié: (2024)

Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
par: Chin, Zhi-Yi, et autres
Publié: (2024)

SWIFT: Semantic Watermarking for Image Forgery Thwarting
par: Evennou, Gautier, et autres
Publié: (2024)

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks
par: Hao, Run, et autres
Publié: (2025)

A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique
par: Sueyoshi, Homare, et autres
Publié: (2025)

Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
par: Ba, Zhongjie, et autres
Publié: (2025)

Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models
par: Thietke, Jonas, et autres
Publié: (2025)

README: Robust Error-Aware Digital Signature Framework via Deep Watermarking Model
par: Choi, Hyunwook, et autres
Publié: (2025)

FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
par: Guo, Yiyang, et autres
Publié: (2024)

WAVES: Benchmarking the Robustness of Image Watermarks
par: An, Bang, et autres
Publié: (2024)

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
par: Yang, Wenkui, et autres
Publié: (2026)

Blind Visible Watermark Removal with Morphological Dilation
par: Robinette, Preston K., et autres
Publié: (2025)

Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
par: Bulychev, Maria, et autres
Publié: (2026)

SPDMark: Selective Parameter Displacement for Robust Video Watermarking
par: Fares, Samar, et autres
Publié: (2025)

METR: Image Watermarking with Large Number of Unique Messages
par: Varlamov, Alexander, et autres
Publié: (2024)

COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks
par: Huang, Zijian, et autres
Publié: (2024)

Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark
par: Ren, Huali, et autres
Publié: (2024)

Your Text Encoder Can Be An Object-Level Watermarking Controller
par: Devulapally, Naresh Kumar, et autres
Publié: (2025)

UnMarker: A Universal Attack on Defensive Image Watermarking
par: Kassis, Andre, et autres
Publié: (2024)

ConSeg: Contextual Backdoor Attack Against Semantic Segmentation
par: Abbasi, Bilal Hussain, et autres
Publié: (2025)

PATE-TripleGAN: Privacy-Preserving Image Synthesis with Gaussian Differential Privacy
par: Jiang, Zepeng, et autres
Publié: (2024)

Delving into Decision-based Black-box Attacks on Semantic Segmentation
par: Chen, Zhaoyu, et autres
Publié: (2024)

NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
par: Goren, Nir, et autres
Publié: (2025)

How does Watermarking Affect Visual Language Models in Document Understanding?
par: Xu, Chunxue, et autres
Publié: (2025)