Cover Image

Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Harel-Canada, Fabrice Y, Erol, Boran, Choi, Connor, Liu, Jason, Song, Gary Jiarui, Peng, Nanyun, Sahai, Amit
Format:	Preprint
Published:	2025
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

Public Key Encryption from High-Corruption Constraint Satisfaction Problems
by: Hair, Isaac M, et al.
Published: (2026)

SLAM: Structural Linguistic Activation Marking for Language Models
by: Harel-Canada, Fabrice, et al.
Published: (2026)

Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
by: Xiang, Zihang, et al.
Published: (2025)

On (Im)possibility of Network Oblivious Transfer via Noisy Channels and Non-Signaling Correlations
by: Aghaee, Hadi, et al.
Published: (2026)

Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
by: Zhang, Hanlin, et al.
Published: (2023)

I'm Spartacus, No, I'm Spartacus: Measuring and Understanding LLM Identity Confusion
by: Li, Kun, et al.
Published: (2024)

BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
by: Rachapudi, Jagadeesh, et al.
Published: (2026)

Revisiting the Robustness of Watermarking to Paraphrasing Attacks
by: Rastogi, Saksham, et al.
Published: (2024)

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

Quantum Advantage via Solving Multivariate Quadratics
by: Briaud, Pierre, et al.
Published: (2024)

PRIVMARK: Private Large Language Models Watermarking with MPC
by: Fargues, Thomas, et al.
Published: (2025)

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

Let Watermarks Speak: A Robust and Unforgeable Watermark for Language Models
by: Bai, Minhao
Published: (2024)

Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
by: Li, Fangqi, et al.
Published: (2024)

Can you See me? On the Visibility of NOPs against Android Malware Detectors
by: Soi, Diego, et al.
Published: (2023)

Watermarking of Quantum Circuits
by: Roy, Rupshali, et al.
Published: (2024)

Composability in Watermarking Schemes
by: Liu, Jiahui, et al.
Published: (2024)

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

Quantum Advantage via Solving Multivariate Polynomials
by: Briaud, Pierre, et al.
Published: (2025)

SiGRRW: A Single-Watermark Robust Reversible Watermarking Framework with Guiding Strategy
by: Xu, Zikai, et al.
Published: (2026)

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

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
by: Yao, Yuan, et al.
Published: (2025)

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

Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack
by: Hui, Siqi, et al.
Published: (2025)

Ideal Attribution and Faithful Watermarks for Language Models
by: Song, Min Jae, et al.
Published: (2025)

Watermarking Without Standards Is Not AI Governance
by: Nemecek, Alexander, et al.
Published: (2025)

Cluster-Aware Attacks on Graph Watermarks
by: Nemecek, Alexander, et al.
Published: (2025)

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

Revisiting Privacy-Utility Trade-off for DP Training with Pre-existing Knowledge
by: Zheng, Yu, et al.
Published: (2024)

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

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

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

An Ensemble Framework for Unbiased Language Model Watermarking
by: Wu, Yihan, et al.
Published: (2025)

Towards Code Watermarking with Dual-Channel Transformations
by: Yang, Borui, et al.
Published: (2023)

Analyzing and Evaluating Unbiased Language Model Watermark
by: Wu, Yihan, et al.
Published: (2025)

A Nested Watermark for Large Language Models
by: Nagatsuka, Koichi, et al.
Published: (2025)

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

SEAL: Subspace-Anchored Watermarks for LLM Ownership
by: Dai, Yanbo, et al.
Published: (2025)

Achieving Flexible and Secure Authentication with Strong Privacy in Decentralized Networks
by: Xie, Bin, et al.
Published: (2025)

Robust Spectral Watermark for Synthetic Tabular Data
by: Zhao, Yizhou, et al.
Published: (2025)