Imagen de Portada

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Zhuoshang, Ren, Yubing, Cao, Yanan, Fang, Fang, Li, Xiaoxue, Guo, Li
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

WorldCup Sampling for Multi-bit LLM Watermarking
por: Wang, Yidan, et al.
Publicado: (2026)

From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
por: Wang, Yidan, et al.
Publicado: (2025)

From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
por: Li, Hao, et al.
Publicado: (2025)

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
por: Li, Hao, et al.
Publicado: (2025)

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
por: Wang, Yidan, et al.
Publicado: (2025)

Cross-Lingual Summarization as a Black-Box Watermark Removal Attack
por: Ganesan, Gokul
Publicado: (2025)

A Watermark for Black-Box Language Models
por: Bahri, Dara, et al.
Publicado: (2024)

RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection
por: Zhu, He, et al.
Publicado: (2026)

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
por: Zhang, Chiyu, et al.
Publicado: (2025)

Exploring Answer Set Programming for Provenance Graph-Based Cyber Threat Detection: A Novel Approach
por: Li, Fang, et al.
Publicado: (2025)

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
por: Chen, Bocheng, et al.
Publicado: (2024)

Watermarking LLM Agent Trajectories
por: Meng, Wenlong, et al.
Publicado: (2026)

Multi-use LLM Watermarking and the False Detection Problem
por: Fu, Zihao, et al.
Publicado: (2025)

Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
por: An, Haonan, et al.
Publicado: (2025)

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
por: Li, Yu, et al.
Publicado: (2026)

Black-Box Detection of Language Model Watermarks
por: Gloaguen, Thibaud, et al.
Publicado: (2024)

TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking
por: Yoon, Sung-Hoon, et al.
Publicado: (2026)

PSM: Prompt Sensitivity Minimization via LLM-Guided Black-Box Optimization
por: Jawad, Huseein, et al.
Publicado: (2025)

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

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications
por: Yang, Ruozhao, et al.
Publicado: (2026)

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
por: An, Li, et al.
Publicado: (2025)

Black-Box Guardrail Reverse-engineering Attack
por: Yao, Hongwei, et al.
Publicado: (2025)

REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models
por: Zhang, Ruisi, et al.
Publicado: (2023)

Rethinking Backdoor Detection Evaluation for Language Models
por: Yan, Jun, et al.
Publicado: (2024)

SLIM: Stealthy Low-Coverage Black-Box Watermarking via Latent-Space Confusion Zones
por: Wu, Hengyu, et al.
Publicado: (2026)

ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples
por: Yang, Yunfei, et al.
Publicado: (2025)

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
por: Liang, Jiacheng, et al.
Publicado: (2024)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
por: Gu, Tianle, et al.
Publicado: (2025)

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
por: Fu, Yu, et al.
Publicado: (2023)

Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection
por: Dang, Kieu, et al.
Publicado: (2026)

Attacks on Third-Party APIs of Large Language Models
por: Zhao, Wanru, et al.
Publicado: (2024)

BinarySelect to Improve Accessibility of Black-Box Attack Research
por: Ghosh, Shatarupa, et al.
Publicado: (2024)

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
por: Hastuti, Rochana Prih, et al.
Publicado: (2025)

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
por: Liu, Yepeng, et al.
Publicado: (2025)

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
por: Zhu, Xiaoyuan, et al.
Publicado: (2025)

Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
por: Li, Xiangfang, et al.
Publicado: (2025)

No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
por: Pang, Qi, et al.
Publicado: (2024)

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

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
por: Li, Jiate, et al.
Publicado: (2026)

Mark My Words: Analyzing and Evaluating Language Model Watermarks
por: Piet, Julien, et al.
Publicado: (2023)