Image de couverture de livre

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yue, Yi, Xin, Shi, Dongsheng, Cui, Yongyi, de Melo, Gerard, Wang, Linlin
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Test-Time Attention Purification for Backdoored Large Vision Language Models
par: Zhang, Zhifang, et autres
Publié: (2026)

Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models
par: Liang, Shuang, et autres
Publié: (2025)

Learning to Watermark in the Latent Space of Generative Models
par: Rebuffi, Sylvestre-Alvise, et autres
Publié: (2026)

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
par: Zhang, Zhicheng, et autres
Publié: (2025)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
par: Zhang, Xinwei, et autres
Publié: (2026)

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models
par: Zheng, Ziwei, et autres
Publié: (2025)

Revisiting Data Auditing in Large Vision-Language Models
par: Zhu, Hongyu, et autres
Publié: (2025)

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

ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
par: Huang, Huayang, et autres
Publié: (2024)

X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks
par: Cheng, Zihang, et autres
Publié: (2025)

mAVE: A Watermark for Joint Audio-Visual Generation Models
par: Si, Luyang, et autres
Publié: (2026)

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

On the Robustness of Watermarking for Autoregressive Image Generation
par: Müller, Andreas, et autres
Publié: (2026)

ZK-WAGON: Imperceptible Watermark for Image Generation Models using ZK-SNARKs
par: Ramakrishnan, Aadarsh Anantha, et autres
Publié: (2025)

SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models
par: Yang, Yang, et autres
Publié: (2026)

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
par: Cui, Yingqian, et autres
Publié: (2023)

Training-Free Watermarking for Autoregressive Image Generation
par: Tong, Yu, et autres
Publié: (2025)

Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
par: Zhang, Yi, et autres
Publié: (2026)

Text is All You Need for Vision-Language Model Jailbreaking
par: Chen, Yihang, et autres
Publié: (2026)

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

Video Signature: Implicit Watermarking for Video Diffusion Models
par: Huang, Yu, et autres
Publié: (2025)

Guidance Watermarking for Diffusion Models
par: Gesny, Enoal, et autres
Publié: (2025)

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

Tell-Tale Watermarks for Explanatory Reasoning in Synthetic Media Forensics
par: Chang, Ching-Chun, et autres
Publié: (2025)

Invisible Image Watermarks Are Provably Removable Using Generative AI
par: Zhao, Xuandong, et autres
Publié: (2023)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
par: Li, Jiayu, et autres
Publié: (2025)

Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion
par: Guo, Ji, et autres
Publié: (2024)

Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
par: Liu, Yepeng, et autres
Publié: (2024)

IConMark: Robust Interpretable Concept-Based Watermark For AI Images
par: Sadasivan, Vinu Sankar, et autres
Publié: (2025)

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
par: Xie, Chunlong, et autres
Publié: (2025)

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
par: Liu, Qin, et autres
Publié: (2025)

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

Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?
par: Amebley, David, et autres
Publié: (2025)

DeMark: A Query-Free Black-Box Attack on Deepfake Watermarking Defenses
par: Song, Wei, et autres
Publié: (2026)

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
par: Lu, Shilin, et autres
Publié: (2024)

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
par: Ye, Mang, et autres
Publié: (2025)

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
par: Gao, Kuofeng, et autres
Publié: (2024)

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

Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing
par: Chen, Pengzhen, et autres
Publié: (2026)

Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models
par: Yang, Zijin, et autres
Publié: (2025)