Copertina

On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical Validation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Omidi, Romina, Dong, Yun, Wang, Binghui
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID
di: Han, Xia, et al.
Pubblicazione: (2025)

SynthID-Image: Image watermarking at internet scale
di: Gowal, Sven, et al.
Pubblicazione: (2025)

Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective
di: Wang, Zifan, et al.
Pubblicazione: (2024)

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

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

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

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
di: Ai, Zhenxin, et al.
Pubblicazione: (2026)

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

LLM Watermark Evasion via Bias Inversion
di: Hwang, Jeongyeon, et al.
Pubblicazione: (2025)

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
di: Xu, Jiahao, et al.
Pubblicazione: (2026)

Learning to Watermark LLM-generated Text via Reinforcement Learning
di: Xu, Xiaojun, et al.
Pubblicazione: (2024)

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

RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
di: Wang, Kun, et al.
Pubblicazione: (2025)

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

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

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

An Empirical Study of Code Obfuscation Practices in the Google Play Store
di: Niroshan, Akila, et al.
Pubblicazione: (2025)

Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2026)

Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking
di: You, Ziyang, et al.
Pubblicazione: (2026)

Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code
di: Kim, Jungin, et al.
Pubblicazione: (2025)

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

A Unified Framework for LLM Watermarks
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2026)

Security and Detectability Analysis of Unicode Text Watermarking Methods Against Large Language Models
di: Hellmeier, Malte
Pubblicazione: (2025)

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

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

SynthCTI: LLM-Driven Synthetic CTI Generation to enhance MITRE Technique Mapping
di: Ruiz-Ródenas, Álvaro, et al.
Pubblicazione: (2025)

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

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

Smark: A Watermark for Text-to-Speech Diffusion Models via Discrete Wavelet Transform
di: Zhang, Yichuan, et al.
Pubblicazione: (2025)

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
di: Xu, Bingxin, et al.
Pubblicazione: (2026)

Detecting Benchmark Contamination Through Watermarking
di: Sander, Tom, et al.
Pubblicazione: (2025)

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

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

Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs
di: Lau, Gregory Kang Ruey, et al.
Pubblicazione: (2024)

Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
di: Hoang, Duy C., et al.
Pubblicazione: (2024)

SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking
di: Gu, Chenxi, et al.
Pubblicazione: (2026)

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

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

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

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