Cover Image

Towards Better Statistical Understanding of Watermarking LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Zhongze, Liu, Shang, Wang, Hanzhao, Zhong, Huaiyang, Li, Xiaocheng
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Cryptography and Security Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Optimal Statistical Watermarking
by: Huang, Baihe, et al.
Published: (2023)

Distributional Information Embedding: A Framework for Multi-bit Watermarking
by: He, Haiyun, et al.
Published: (2025)

Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
by: He, Haiyun, et al.
Published: (2024)

TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding
by: Pagnotta, Giulio, et al.
Published: (2022)

Better and Simpler Lower Bounds for Differentially Private Statistical Estimation
by: Narayanan, Shyam
Published: (2023)

Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack
by: Wang, Xuesong, et al.
Published: (2025)

Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy
by: Jin, Richeng, et al.
Published: (2023)

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

Universal Exact Compression of Differentially Private Mechanisms
by: Liu, Yanxiao, et al.
Published: (2024)

Explainable Semantic Federated Learning Enabled Industrial Edge Network for Fire Surveillance
by: Dong, Li, et al.
Published: (2024)

Enabling Deep Learning-based Physical-layer Secret Key Generation for FDD-OFDM Systems in Multi-Environments
by: Zhang, Xinwei, et al.
Published: (2022)

Watermarking Recommender Systems
by: Zhang, Sixiao, et al.
Published: (2024)

Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
by: Huang, Alyssa, et al.
Published: (2023)

Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference
by: Wang, Zhanwei, et al.
Published: (2023)

Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacy
by: Xie, Songjie, et al.
Published: (2024)

DRGW: Learning Disentangled Representations for Robust Graph Watermarking
by: Li, Jiasen, et al.
Published: (2026)

Robustness Implies Privacy in Statistical Estimation
by: Hopkins, Samuel B., et al.
Published: (2022)

Differentially Private Fair Binary Classifications
by: Ghoukasian, Hrad, et al.
Published: (2024)

Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation
by: Vithana, Sajani, et al.
Published: (2024)

CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness
by: Salehi, Hojat Allah, et al.
Published: (2024)

An Efficient Difference-of-Convex Solver for Privacy Funnel
by: Huang, Teng-Hui, et al.
Published: (2024)

In-Application Defense Against Evasive Web Scans through Behavioral Analysis
by: Ousat, Behzad, et al.
Published: (2024)

Collaborative Inference over Wireless Channels with Feature Differential Privacy
by: Seif, Mohamed, et al.
Published: (2024)

Modular Neural Wiretap Codes for Fading Channels
by: Seifert, Daniel, et al.
Published: (2024)

Machine Learning Predictors for Min-Entropy Estimation
by: Blanco-Romero, Javier, et al.
Published: (2024)

Inference Privacy: Properties and Mechanisms
by: Tian, Fengwei, et al.
Published: (2024)

On Homomorphic Encryption Based Strategies for Class Imbalance in Federated Learning
by: Guleria, Arpit, et al.
Published: (2024)

Adversary-Aware Private Inference over Wireless Channels
by: Seif, Mohamed, et al.
Published: (2025)

Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning
by: Kim, Benjamin D., et al.
Published: (2026)

STAMP: Selective Task-Aware Mechanism for Text Privacy
by: Tian, Fengwei, et al.
Published: (2026)

Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity
by: Pour, Alireza F., et al.
Published: (2023)

The importance of feature preprocessing for differentially private linear optimization
by: Sun, Ziteng, et al.
Published: (2023)

Rao Differential Privacy
by: Soto, Carlos
Published: (2025)

GeoClip: Geometry-Aware Clipping for Differentially Private SGD
by: Gilani, Atefeh, et al.
Published: (2025)

Comparing privacy notions for protection against reconstruction attacks in machine learning
by: Biswas, Sayan, et al.
Published: (2025)

FedNC: A Secure and Efficient Federated Learning Method with Network Coding
by: Shi, Yuchen, et al.
Published: (2023)

Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost
by: Pathegama, Madhura, et al.
Published: (2026)

ScionFL: Efficient and Robust Secure Quantized Aggregation
by: Ben-Itzhak, Yaniv, et al.
Published: (2022)

Privacy Against Agnostic Inference Attacks in Vertical Federated Learning
by: Varasteh, Morteza
Published: (2023)

Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing
by: Malekzadeh, Mohammad, et al.
Published: (2022)