Imagen de Portada

Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Fangqi, Zhao, Haodong, Du, Wei, Wang, Shilin
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
por: Zhu, Hongyu, et al.
Publicado: (2024)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
por: Zhao, Haodong, et al.
Publicado: (2024)

Probabilistically Robust Watermarking of Neural Networks
por: Pautov, Mikhail, et al.
Publicado: (2024)

Watermarking Graph Neural Networks via Explanations for Ownership Protection
por: Downer, Jane, et al.
Publicado: (2025)

Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking
por: Harel-Canada, Fabrice Y, et al.
Publicado: (2025)

WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks
por: Li, Tingzhi, et al.
Publicado: (2025)

Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
por: Evennou, Gautier, et al.
Publicado: (2025)

Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
por: Dai, Zhiyang, et al.
Publicado: (2026)

Protecting Deep Neural Network Intellectual Property with Chaos-Based White-Box Watermarking
por: B, Sangeeth, et al.
Publicado: (2025)

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
por: Xu, Yixiao, et al.
Publicado: (2025)

On Protecting Agentic Systems' Intellectual Property via Watermarking
por: Wang, Liwen, et al.
Publicado: (2026)

PromptLA: Towards Integrity Verification of Black-box Text-to-Image Diffusion Models
por: Zhang, Zhuomeng, et al.
Publicado: (2024)

Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models
por: Zhang, Shuhao, et al.
Publicado: (2026)

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

UOR: Universal Backdoor Attacks on Pre-trained Language Models
por: Du, Wei, et al.
Publicado: (2023)

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

On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective
por: Hu, Aoting, et al.
Publicado: (2024)

AgentMark: Utility-Preserving Behavioral Watermarking for Agents
por: Huang, Kaibo, et al.
Publicado: (2026)

MaXsive: High-Capacity and Robust Training-Free Generative Image Watermarking in Diffusion Models
por: Mao, Po-Yuan, et al.
Publicado: (2025)

Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond
por: Wang, Xuhong, et al.
Publicado: (2024)

CODE ACROSTIC: Robust Watermarking for Code Generation
por: Lin, Li, et al.
Publicado: (2025)

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
por: Lin, Chenhao, et al.
Publicado: (2025)

Multi-Designated Detector Watermarking for Language Models
por: Huang, Zhengan, et al.
Publicado: (2024)

Functional Subspace Watermarking for Large Language Models
por: Ding, Zikang, et al.
Publicado: (2026)

Asking Back: Interaction-Layer Antidistillation Watermarks
por: Yang, Guang, et al.
Publicado: (2026)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
por: Fei, Zekun, et al.
Publicado: (2024)

SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
por: Wang, Yingjia, et al.
Publicado: (2025)

ChainMarks: Securing DNN Watermark with Cryptographic Chain
por: Choi, Brian, et al.
Publicado: (2025)

FreeMark: A Non-Invasive White-Box Watermarking for Deep Neural Networks
por: Chen, Yuzhang, et al.
Publicado: (2024)

InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
por: Xu, Rui, et al.
Publicado: (2024)

A Survey of Fragile Model Watermarking
por: Gao, Zhenzhe, et al.
Publicado: (2024)

Sequential Behavioral Watermarking for LLM Agents
por: An, Hyeseon, et al.
Publicado: (2026)

Detecting Benchmark Contamination Through Watermarking
por: Sander, Tom, et al.
Publicado: (2025)

Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection
por: Mikulec, Ján, et al.
Publicado: (2026)

Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
por: Li, Wenjie, et al.
Publicado: (2025)

Invariant-based Robust Weights Watermark for Large Language Models
por: Guo, Qingxiao, et al.
Publicado: (2025)

Protecting Your Voice: Temporal-aware Robust Watermarking
por: Li, Yue, et al.
Publicado: (2025)

Advancing Beyond Identification: Multi-bit Watermark for Large Language Models
por: Yoo, KiYoon, et al.
Publicado: (2023)

The Coding Limits of Robust Watermarking for Generative Models
por: Francati, Danilo, et al.
Publicado: (2025)

Character-Level Perturbations Disrupt LLM Watermarks
por: Zhang, Zhaoxi, et al.
Publicado: (2025)