Image de couverture de livre

WAPITI: A Watermark for Finetuned Open-Source LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Lingjie, Qiu, Ruizhong, Yuan, Siyu, Liu, Zhining, Wei, Tianxin, Yoo, Hyunsik, Zeng, Zhichen, Yang, Deqing, Tong, Hanghang
Format:	Preprint
Publié:	2024
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Saffron-1: Safety Inference Scaling
par: Qiu, Ruizhong, et autres
Publié: (2025)

BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
par: Lin, Xiao, et autres
Publié: (2024)

Towards Watermarking of Open-Source LLMs
par: Gloaguen, Thibaud, et autres
Publié: (2025)

PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
par: Xue, Jiaqi, et autres
Publié: (2025)

Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
par: Li, Shuai, et autres
Publié: (2023)

DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
par: Chen, Yuchen, et autres
Publié: (2026)

Provably Robust Watermarks for Open-Source Language Models
par: Christ, Miranda, et autres
Publié: (2024)

Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security
par: Kim, Hajun, et autres
Publié: (2025)

SEW: Strengthening Robustness of Black-box DNN Watermarking via Specificity Enhancement
par: Qiu, Huming, et autres
Publié: (2026)

GuardPhish: Securing Open-Source LLMs from Phishing Abuse
par: Mishra, Rina, et autres
Publié: (2026)

Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness
par: Yang, Peiru, et autres
Publié: (2025)

Towards Code Watermarking with Dual-Channel Transformations
par: Yang, Borui, et autres
Publié: (2023)

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
par: Yang, Yuxin, et autres
Publié: (2024)

Open Source, Open Threats? Investigating Security Challenges in Open-Source Software
par: Akhavani, Seyed Ali, et autres
Publié: (2025)

RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewriting
par: Shi, Zhan, et autres
Publié: (2025)

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
par: Wang, Xin, et autres
Publié: (2026)

EditMark: Watermarking Large Language Models based on Model Editing
par: Li, Shuai, et autres
Publié: (2025)

NOIR: Privacy-Preserving Generation of Code with Open-Source LLMs
par: Nguyen, Khoa, et autres
Publié: (2026)

SoK: Are Watermarks in LLMs Ready for Deployment?
par: Dang, Kieu, et autres
Publié: (2025)

Certified Defense on the Fairness of Graph Neural Networks
par: Dong, Yushun, et autres
Publié: (2023)

Watermarking Recommender Systems
par: Zhang, Sixiao, et autres
Publié: (2024)

Watermarking LLM Agent Trajectories
par: Meng, Wenlong, et autres
Publié: (2026)

MarkLLM: An Open-Source Toolkit for LLM Watermarking
par: Pan, Leyi, et autres
Publié: (2024)

Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal
par: Goonatilake, Yevin Nikhel, et autres
Publié: (2026)

Let Watermarks Speak: A Robust and Unforgeable Watermark for Language Models
par: Bai, Minhao
Publié: (2024)

Watermarking LLM-Generated Datasets in Downstream Tasks
par: Liu, Yugeng, et autres
Publié: (2025)

An Ensemble Framework for Unbiased Language Model Watermarking
par: Wu, Yihan, et autres
Publié: (2025)

Analyzing and Evaluating Unbiased Language Model Watermark
par: Wu, Yihan, et autres
Publié: (2025)

Performance-lossless Black-box Model Watermarking
par: Zhao, Na, et autres
Publié: (2023)

Watermarking of Quantum Circuits
par: Roy, Rupshali, et autres
Publié: (2024)

Composability in Watermarking Schemes
par: Liu, Jiahui, et autres
Publié: (2024)

Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarking
par: Guo, Fan, et autres
Publié: (2026)

EmbTracker: Traceable Black-box Watermarking for Federated Language Models
par: Zhao, Haodong, et autres
Publié: (2026)

Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
par: Li, Qinfeng, et autres
Publié: (2025)

ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples
par: Yang, Yunfei, et autres
Publié: (2025)

Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption
par: Frery, Jordan, et autres
Publié: (2025)

DINVMark: A Deep Invertible Network for Video Watermarking
par: Ji, Jianbin, et autres
Publié: (2025)

SiGRRW: A Single-Watermark Robust Reversible Watermarking Framework with Guiding Strategy
par: Xu, Zikai, et autres
Publié: (2026)

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
par: Li, Hao, et autres
Publié: (2025)

A Watermark-Conditioned Diffusion Model for IP Protection
par: Min, Rui, et autres
Publié: (2024)