Imagen de Portada

Dataset Watermarking for Closed LLMs with Provable Detection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Pengrun, Chaudhuri, Kamalika, Wang, Yu-Xiang
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Better Membership Inference Privacy Measurement through Discrepancy
por: Wu, Ruihan, et al.
Publicado: (2024)

Can We Infer Confidential Properties of Training Data from LLMs?
por: Huang, Pengrun, et al.
Publicado: (2025)

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
por: Wang, Erchi, et al.
Publicado: (2026)

A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection
por: Garov, Konstantin, et al.
Publicado: (2025)

Learning-Time Encoding Shapes Unlearning in LLMs
por: Wu, Ruihan, et al.
Publicado: (2025)

Distribution Learning with Valid Outputs Beyond the Worst-Case
por: Rittler, Nick, et al.
Publicado: (2024)

Unified Uncertainty Calibration
por: Chaudhuri, Kamalika, et al.
Publicado: (2023)

Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift
por: Bhattacharjee, Robi, et al.
Publicado: (2024)

Z0-Inf: Zeroth Order Approximation for Data Influence
por: Kokhlikyan, Narine, et al.
Publicado: (2025)

Data Redaction from Conditional Generative Models
por: Kong, Zhifeng, et al.
Publicado: (2023)

Provable Watermarking for Data Poisoning Attacks
por: Zhu, Yifan, et al.
Publicado: (2025)

Auditing $f$-Differential Privacy in One Run
por: Mahloujifar, Saeed, et al.
Publicado: (2024)

Influence-based Attributions can be Manipulated
por: Yadav, Chhavi, et al.
Publicado: (2024)

Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
por: Liu, Hongyi, et al.
Publicado: (2025)

Ward: Provable RAG Dataset Inference via LLM Watermarks
por: Jovanović, Nikola, et al.
Publicado: (2024)

Déjà Vu Memorization in Vision-Language Models
por: Jayaraman, Bargav, et al.
Publicado: (2024)

Privacy Blur: Quantifying Privacy and Utility for Image Data Release
por: Mahloujifar, Saeed, et al.
Publicado: (2025)

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
por: Liu, Bing, et al.
Publicado: (2026)

RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
por: Wen, Yuxin, et al.
Publicado: (2025)

Machine Learning with Privacy for Protected Attributes
por: Mahloujifar, Saeed, et al.
Publicado: (2025)

Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs
por: Zhang, Xingyu, et al.
Publicado: (2026)

Privacy Amplification for the Gaussian Mechanism via Bounded Support
por: Hu, Shengyuan, et al.
Publicado: (2024)

FairProof : Confidential and Certifiable Fairness for Neural Networks
por: Yadav, Chhavi, et al.
Publicado: (2024)

On Differentially Private U Statistics
por: Chaudhuri, Kamalika, et al.
Publicado: (2024)

ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
por: Yadav, Chhavi, et al.
Publicado: (2025)

Measuring Déjà vu Memorization Efficiently
por: Kokhlikyan, Narine, et al.
Publicado: (2025)

On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
por: He, Weiqing, et al.
Publicado: (2025)

Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking
por: Xie, Liyan, et al.
Publicado: (2025)

SecAlign: Defending Against Prompt Injection with Preference Optimization
por: Chen, Sizhe, et al.
Publicado: (2024)

Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
por: Chen, Yu, et al.
Publicado: (2024)

Differentially Private Representation Learning via Image Captioning
por: Sander, Tom, et al.
Publicado: (2024)

Towards Watermarking of Open-Source LLMs
por: Gloaguen, Thibaud, et al.
Publicado: (2025)

Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
por: Chaudhuri, Kamalika, et al.
Publicado: (2024)

Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation
por: Wang, Yu, et al.
Publicado: (2025)

BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks
por: Li, Zhuang, et al.
Publicado: (2025)

Towards Better Statistical Understanding of Watermarking LLMs
por: Cai, Zhongze, et al.
Publicado: (2024)

Provable Training for Graph Contrastive Learning
por: Yu, Yue, et al.
Publicado: (2023)

WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking
por: Trias, Carl De Sousa, et al.
Publicado: (2024)

The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs
por: Baidya, Avinash, et al.
Publicado: (2025)

Refined Detection for Gumbel Watermarking
por: Lattimore, Tor
Publicado: (2026)