Imagen de Portada

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Aremu, Toluwani, Hussein, Noor, Nwadike, Munachiso, Poppi, Samuele, Zhang, Jie, Nandakumar, Karthik, Gong, Neil, Lukas, Nils
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Robust Safety Monitoring of Language Models via Activation Watermarking
por: Aremu, Toluwani, et al.
Publicado: (2026)

Optimizing Adaptive Attacks against Watermarks for Language Models
por: Diaa, Abdulrahman, et al.
Publicado: (2024)

Watermarking Should Be Treated as a Monitoring Primitive
por: Aremu, Toluwani, et al.
Publicado: (2026)

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
por: Hussein, Noor, et al.
Publicado: (2024)

SPQR: A Standardized Benchmark for Modern Safety Alignment Methods in Text-to-Image Diffusion Models
por: Alam, Mohammed Talha, et al.
Publicado: (2025)

SPDMark: Selective Parameter Displacement for Robust Video Watermarking
por: Fares, Samar, et al.
Publicado: (2025)

MOLM: Mixture of LoRA Markers
por: Fares, Samar, et al.
Publicado: (2025)

Leveraging Optimization for Adaptive Attacks on Image Watermarks
por: Lukas, Nils, et al.
Publicado: (2023)

Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models
por: Zhu, Chaoyi, et al.
Publicado: (2025)

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

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

MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
por: Fang, Liancheng, et al.
Publicado: (2025)

MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks
por: Zhou, Tong, et al.
Publicado: (2025)

SWIFT: Semantic Watermarking for Image Forgery Thwarting
por: Evennou, Gautier, et al.
Publicado: (2024)

The importance of the clustering model to detect new types of intrusion in data traffic
por: Abd, Noor Saud, et al.
Publicado: (2024)

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

A Transfer Attack to Image Watermarks
por: Hu, Yuepeng, et al.
Publicado: (2024)

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)

Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions
por: Wu, Yihan, et al.
Publicado: (2024)

Cyber Attack Mitigation Framework for Denial of Service (DoS) Attacks in Fog Computing
por: Khurshid, Fizza, et al.
Publicado: (2025)

Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness
por: Yang, Peiru, et al.
Publicado: (2025)

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
por: Müller, Andreas, et al.
Publicado: (2024)

Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization
por: Wang, Chenrui, et al.
Publicado: (2025)

SimKey: A Semantically Aware Key Module for Watermarking Language Models
por: Kodama, Shingo, et al.
Publicado: (2025)

Towards Generalized and Stealthy Watermarking for Generative Code Models
por: Li, Haoxuan, et al.
Publicado: (2025)

A Technique for the Detection of PDF Tampering or Forgery
por: Grobler, Gabriel, et al.
Publicado: (2025)

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

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
por: Wang, Yaopeng, et al.
Publicado: (2026)

RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
por: Huang, Hanbo, et al.
Publicado: (2026)

Watermarking LLM-Generated Datasets in Downstream Tasks
por: Liu, Yugeng, et al.
Publicado: (2025)

Adaptive and Robust Watermark for Generative Tabular Data
por: Ngo, Dung Daniel, et al.
Publicado: (2024)

VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection
por: Liu, Weizhi, et al.
Publicado: (2026)

Agentic Copyright Watermarking against Adversarial Evidence Forgery with Purification-Agnostic Curriculum Proxy Learning
por: Bao, Erjin, et al.
Publicado: (2024)

Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
por: Xie, Yueqi, et al.
Publicado: (2024)

Phantom Events: Demystifying the Issues of Log Forgery in Blockchain
por: Liu, Yixuan, et al.
Publicado: (2025)

"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking
por: Zhang, Xinyu, et al.
Publicado: (2026)

DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
por: Chen, Yuchen, et al.
Publicado: (2026)

Prompt Injection Attack to Tool Selection in LLM Agents
por: Shi, Jiawen, et al.
Publicado: (2025)

Efficient and Universal Watermarking for LLM-Generated Code Detection
por: Li, Boquan, et al.
Publicado: (2024)

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