Cover Image

Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Zhengmian, Huang, Heng
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
by: He, Weiqing, et al.
Published: (2026)

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

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

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
by: Wu, Yihan, et al.
Published: (2023)

Large Language Model Watermark Stealing With Mixed Integer Programming
by: Zhang, Zhaoxi, et al.
Published: (2024)

Downstream Trade-offs of a Family of Text Watermarks
by: Ajith, Anirudh, et al.
Published: (2023)

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking
by: Zhao, Yizhou, et al.
Published: (2025)

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

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

Watermarking Techniques for Large Language Models: A Survey
by: Liang, Yuqing, et al.
Published: (2024)

Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
by: Ng, Jonathan Hong Jin, et al.
Published: (2026)

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

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

CEFW: A Comprehensive Evaluation Framework for Watermark in Large Language Models
by: Zhang, Shuhao, et al.
Published: (2025)

MirrorMark: Generalizable Mirrored Sampling for Multi-bit LLM Watermarking
by: Jiang, Ya, et al.
Published: (2026)

Watermarking Diffusion Language Models
by: Gloaguen, Thibaud, et al.
Published: (2025)

StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
by: Jiang, Ya, et al.
Published: (2025)

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

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

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

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

DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language Models
by: Lin, Qihao, et al.
Published: (2025)

Learnable Linguistic Watermarks for Tracing Model Extraction Attacks on Large Language Models
by: Bai, Minhao, et al.
Published: (2024)

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

Watermark Stealing in Large Language Models
by: Jovanović, Nikola, et al.
Published: (2024)

Watermarking Discrete Diffusion Language Models
by: Bagchi, Avi, et al.
Published: (2025)

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

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
by: Lv, Peizhuo, et al.
Published: (2025)

Discovering Spoofing Attempts on Language Model Watermarks
by: Gloaguen, Thibaud, et al.
Published: (2024)

Watermarking Language Models for Many Adaptive Users
by: Cohen, Aloni, et al.
Published: (2024)

Optimized Couplings for Watermarking Large Language Models
by: Tsur, Dor, et al.
Published: (2025)

Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity
by: An, Hongjun, et al.
Published: (2026)

Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
by: Shen, Huanming, et al.
Published: (2025)

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

Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
by: Chen, Huajie, et al.
Published: (2026)

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

Provably Robust Watermarks for Open-Source Language Models
by: Christ, Miranda, et al.
Published: (2024)

Unforgeable Watermarks for Language Models via Robust Signatures
by: Lin, Huijia, et al.
Published: (2026)

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

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark
by: Cai, Yuhang, et al.
Published: (2025)