Imagen de Portada

WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Giboulot, Eva, Furon, Teddy
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Guidance Watermarking for Diffusion Models
por: Gesny, Enoal, et al.
Publicado: (2025)

Proving membership in LLM pretraining data via data watermarks
por: Wei, Johnny Tian-Zheng, et al.
Publicado: (2024)

Watermarking Makes Language Models Radioactive
por: Sander, Tom, et al.
Publicado: (2024)

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
por: Zhao, Xuandong, et al.
Publicado: (2024)

Functional Invariants to Watermark Large Transformers
por: Fernandez, Pierre, et al.
Publicado: (2023)

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

PersonaMark: Personalized LLM watermarking for model protection and user attribution
por: Zhang, Yuehan, et al.
Publicado: (2024)

Backdoor Attacks on Deep Learning Face Detection
por: Roux, Quentin Le, et al.
Publicado: (2025)

Task-Agnostic Attacks Against Vision Foundation Models
por: Pulfer, Brian, et al.
Publicado: (2025)

Learning diverse attacks on large language models for robust red-teaming and safety tuning
por: Lee, Seanie, et al.
Publicado: (2024)

SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems
por: Roux, Quentin Le, et al.
Publicado: (2025)

LLM Unlearning Should Be Form-Independent
por: Ye, Xiaotian, et al.
Publicado: (2025)

GCG Attack On A Diffusion LLM
por: Neyroud, Ruben, et al.
Publicado: (2025)

LLMGuard: Guarding Against Unsafe LLM Behavior
por: Goyal, Shubh, et al.
Publicado: (2024)

Sparse Autoencoders are Capable LLM Jailbreak Mitigators
por: Assogba, Yannick, et al.
Publicado: (2026)

Localizing Malicious Outputs from CodeLLM
por: Borana, Mayukh, et al.
Publicado: (2025)

Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows?
por: Gesny, Enoal, et al.
Publicado: (2026)

Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
por: Gesny, Enoal, et al.
Publicado: (2026)

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
por: Wang, Tianchun, et al.
Publicado: (2024)

Improving LLM Safety Alignment with Dual-Objective Optimization
por: Zhao, Xuandong, et al.
Publicado: (2025)

Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs
por: Liu, Ruixuan, et al.
Publicado: (2026)

Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities
por: Krishna, Arjun, et al.
Publicado: (2025)

PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
por: Duan, Haohua, et al.
Publicado: (2025)

Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
por: Zhang, Boyang, et al.
Publicado: (2026)

Evaluation of LLM Chatbots for OSINT-based Cyber Threat Awareness
por: Shafee, Samaneh, et al.
Publicado: (2024)

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

LLM Dataset Inference: Did you train on my dataset?
por: Maini, Pratyush, et al.
Publicado: (2024)

On Calibration of LLM-based Guard Models for Reliable Content Moderation
por: Liu, Hongfu, et al.
Publicado: (2024)

Robust LLM safeguarding via refusal feature adversarial training
por: Yu, Lei, et al.
Publicado: (2024)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
por: Zeng, Yifan, et al.
Publicado: (2024)

The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
por: Meeus, Matthieu, et al.
Publicado: (2025)

TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
por: Sander, Tom, et al.
Publicado: (2026)

Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
por: Yang, Xikang, et al.
Publicado: (2024)

A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism
por: Chen, Zhiyu, et al.
Publicado: (2024)

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users
por: Hilel, Almog, et al.
Publicado: (2025)

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
por: Cai, Will, et al.
Publicado: (2025)

FreqMark: Frequency-Based Watermark for Sentence-Level Detection of LLM-Generated Text
por: Xu, Zhenyu, et al.
Publicado: (2024)

Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
por: Rao, Zixin, et al.
Publicado: (2025)

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
por: Wang, Fei, et al.
Publicado: (2025)

Is poisoning a real threat to LLM alignment? Maybe more so than you think
por: Pathmanathan, Pankayaraj, et al.
Publicado: (2024)