Copertina

The Orthogonal Vulnerabilities of Generative AI Watermarks: A Comparative Empirical Benchmark of Spatial and Latent Provenance

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Jesse, Wei, Nicholas
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking
di: Saberi, Mehrdad, et al.
Pubblicazione: (2024)

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

Learning to Watermark in the Latent Space of Generative Models
di: Rebuffi, Sylvestre-Alvise, et al.
Pubblicazione: (2026)

HMARK: Radioactive Multi-Bit Semantic-Latent Watermarking for Diffusion Models
di: Li, Kexin, et al.
Pubblicazione: (2025)

Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks
di: Diao, Yunfeng, et al.
Pubblicazione: (2024)

Authenticated Contradictions from Desynchronized Provenance and Watermarking
di: Nemecek, Alexander, et al.
Pubblicazione: (2026)

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

Provenance of AI-Generated Images: A Vector Similarity and Blockchain-based Approach
di: Sharma, Jitendra, et al.
Pubblicazione: (2025)

Invisible Image Watermarks Are Provably Removable Using Generative AI
di: Zhao, Xuandong, et al.
Pubblicazione: (2023)

LAID: Lightweight AI-Generated Image Detection in Spatial and Spectral Domains
di: Chivaran, Nicholas, et al.
Pubblicazione: (2025)

Evading Data Provenance in Deep Neural Networks
di: Zhu, Hongyu, et al.
Pubblicazione: (2025)

WAVES: Benchmarking the Robustness of Image Watermarks
di: An, Bang, et al.
Pubblicazione: (2024)

Mesh Watermark Removal Attack and Mitigation: A Novel Perspective of Function Space
di: Zhu, Xingyu, et al.
Pubblicazione: (2023)

Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
di: Ba, Zhongjie, et al.
Pubblicazione: (2025)

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
di: Sun, Yuhao, et al.
Pubblicazione: (2025)

Guidance Watermarking for Diffusion Models
di: Gesny, Enoal, et al.
Pubblicazione: (2025)

Watermark Anything with Localized Messages
di: Sander, Tom, et al.
Pubblicazione: (2024)

NWaaS: Nonintrusive Watermarking as a Service for X-to-Image DNN
di: An, Haonan, et al.
Pubblicazione: (2025)

Video Signature: Implicit Watermarking for Video Diffusion Models
di: Huang, Yu, et al.
Pubblicazione: (2025)

Training-Free Watermarking for Autoregressive Image Generation
di: Tong, Yu, et al.
Pubblicazione: (2025)

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
di: Yang, Zijin, et al.
Pubblicazione: (2024)

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
di: Lu, Shilin, et al.
Pubblicazione: (2024)

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking
di: Gao, Zheng, et al.
Pubblicazione: (2026)

Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation
di: Wang, Yuchen, et al.
Pubblicazione: (2024)

AI-generated Image Detection: Passive or Watermark?
di: Guo, Moyang, et al.
Pubblicazione: (2024)

WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
di: Dong, Ziping, et al.
Pubblicazione: (2025)

RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
di: Xian, Xun, et al.
Pubblicazione: (2024)

FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
di: Guo, Yiyang, et al.
Pubblicazione: (2024)

Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models
di: Yang, Zijin, et al.
Pubblicazione: (2025)

From Attack to Protection: Leveraging Watermarking Attack Network for Advanced Add-on Watermarking
di: Nam, Seung-Hun, et al.
Pubblicazione: (2020)

On the Robustness of Watermarking for Autoregressive Image Generation
di: Müller, Andreas, et al.
Pubblicazione: (2026)

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
di: Li, Kecen, et al.
Pubblicazione: (2025)

Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection
di: Yang, Jijia, et al.
Pubblicazione: (2024)

When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
di: Zhao, Shiqian, et al.
Pubblicazione: (2025)

DLOVE: A new Security Evaluation Tool for Deep Learning Based Watermarking Techniques
di: Padhi, Sudev Kumar, et al.
Pubblicazione: (2024)

SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Training
di: Zhang, Lu, et al.
Pubblicazione: (2024)

IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
di: Zhang, Lingyun, et al.
Pubblicazione: (2026)

Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
di: Zhang, Yi, et al.
Pubblicazione: (2026)

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

Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows?
di: Gesny, Enoal, et al.
Pubblicazione: (2026)