Imagen de Portada

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Xiaodong, Tang, Tianyi, Li, Xiangman, Ni, Jianbing, Yu, Yong
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Robustness of Watermarking on Text-to-Image Diffusion Models
por: Wu, Xiaodong, et al.
Publicado: (2024)

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
por: Li, Xiangman, et al.
Publicado: (2025)

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models
por: Wu, Xiaodong, et al.
Publicado: (2025)

MarkSweep: A No-box Removal Attack on AI-Generated Image Watermarking via Noise Intensification and Frequency-aware Denoising
por: Cao, Jie, et al.
Publicado: (2026)

SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
por: Wu, Xiaodong, et al.
Publicado: (2025)

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
por: Feng, Weitao, et al.
Publicado: (2024)

Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
por: Yao, Lingfeng, et al.
Publicado: (2026)

Performance-lossless Black-box Model Watermarking
por: Zhao, Na, et al.
Publicado: (2023)

Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID
por: Han, Xia, et al.
Publicado: (2025)

MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
por: Jin, Yutong, et al.
Publicado: (2026)

Stable Signature is Unstable: Removing Image Watermark from Diffusion Models
por: Hu, Yuepeng, et al.
Publicado: (2024)

Robust and Imperceptible Black-box DNN Watermarking Based on Fourier Perturbation Analysis and Frequency Sensitivity Clustering
por: Liu, Yong, et al.
Publicado: (2022)

Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal
por: Goonatilake, Yevin Nikhel, et al.
Publicado: (2026)

A Game Between the Defender and the Attacker for Trigger-based Black-box Model Watermarking
por: Huang, Chaoyue, et al.
Publicado: (2025)

AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection
por: Gao, Jianbo, et al.
Publicado: (2025)

The Efficacy of Transfer-based No-box Attacks on Image Watermarking: A Pragmatic Analysis
por: Wu, Qilong, et al.
Publicado: (2024)

EmbTracker: Traceable Black-box Watermarking for Federated Language Models
por: Zhao, Haodong, et al.
Publicado: (2026)

Generative Model Watermarking Suppressing High-Frequency Artifacts
por: Zhang, Li, et al.
Publicado: (2023)

Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey
por: Cao, Jie, et al.
Publicado: (2025)

On the Information-Theoretic Fragility of Robust Watermarking under Diffusion Editing
por: Ni, Yunyi, et al.
Publicado: (2025)

Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
por: Li, Shuai, et al.
Publicado: (2023)

A Watermark-Conditioned Diffusion Model for IP Protection
por: Min, Rui, et al.
Publicado: (2024)

Watermarking Visual Concepts for Diffusion Models
por: Lei, Liangqi, et al.
Publicado: (2024)

Traceable Black-box Watermarks for Federated Learning
por: Xu, Jiahao, et al.
Publicado: (2025)

SEW: Strengthening Robustness of Black-box DNN Watermarking via Specificity Enhancement
por: Qiu, Huming, et al.
Publicado: (2026)

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation
por: Oh, Giyeong, et al.
Publicado: (2025)

VideoMark: A Distortion-Free Robust Watermarking Framework for Video Diffusion Models
por: Hu, Xuming, et al.
Publicado: (2025)

When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models
por: Hu, Ruihan, et al.
Publicado: (2026)

Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios
por: Lei, Liangqi, et al.
Publicado: (2025)

CLUE-MARK: Watermarking Diffusion Models using CLWE
por: Shehata, Kareem, et al.
Publicado: (2024)

Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
por: An, Haonan, et al.
Publicado: (2025)

Removal Attack and Defense on AI-generated Content Latent-based Watermarking
por: Lee, De Zhang, et al.
Publicado: (2025)

Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
por: Bulychev, Maria, et al.
Publicado: (2026)

SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark
por: Bao, Rui, et al.
Publicado: (2026)

PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility
por: Gai, Keke, et al.
Publicado: (2025)

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
por: Lv, Peizhuo, et al.
Publicado: (2025)

ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models
por: Qian, Yuqi, et al.
Publicado: (2026)

Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarking
por: Guo, Fan, et al.
Publicado: (2026)

Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
por: Lu, Yifan, et al.
Publicado: (2023)

Security, Privacy, and Ethical Risks in OpenClaw
por: Jin, Yutong, et al.
Publicado: (2026)