Image de couverture de livre

Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Peiru, Li, Xintian, Ni, Wanchun, Yin, Jinhua, Wang, Huili, Nan, Guoshun, Wang, Shangguang, Huang, Yongfeng, Qi, Tao
Format:	Preprint
Publié:	2025
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

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
par: Yin, Jinhua, et autres
Publié: (2025)

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
par: Yang, Peiru, et autres
Publié: (2026)

Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes
par: Tao, Qi, et autres
Publié: (2025)

Towards Next-Generation Steganalysis: LLMs Unleash the Power of Detecting Steganography
par: Yang, Minhao Bai. Jinshuai, et autres
Publié: (2024)

ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
par: Pang, Kaiyi, et autres
Publié: (2024)

KGMark: A Diffusion Watermark for Knowledge Graphs
par: Peng, Hongrui, et autres
Publié: (2025)

MarkSweep: A No-box Removal Attack on AI-Generated Image Watermarking via Noise Intensification and Frequency-aware Denoising
par: Cao, Jie, et autres
Publié: (2026)

Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
par: Hoang, Duy C., et autres
Publié: (2024)

MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
par: Jin, Yutong, et autres
Publié: (2026)

Robustness of Watermarking on Text-to-Image Diffusion Models
par: Wu, Xiaodong, et autres
Publié: (2024)

Learnable Linguistic Watermarks for Tracing Model Extraction Attacks on Large Language Models
par: Bai, Minhao, et autres
Publié: (2024)

Cluster-Aware Attacks on Graph Watermarks
par: Nemecek, Alexander, et autres
Publié: (2025)

Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID
par: Han, Xia, et autres
Publié: (2025)

VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection
par: Liu, Weizhi, et autres
Publié: (2026)

WAPITI: A Watermark for Finetuned Open-Source LLMs
par: Chen, Lingjie, et autres
Publié: (2024)

Efficient and Universal Watermarking for LLM-Generated Code Detection
par: Li, Boquan, et autres
Publié: (2024)

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

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

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
par: Wang, Yaopeng, et autres
Publié: (2026)

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

An LLM-based Self-Evolving Security Framework for 6G Space-Air-Ground Integrated Networks
par: Qin, Qi, et autres
Publié: (2025)

On the Information-Theoretic Fragility of Robust Watermarking under Diffusion Editing
par: Ni, Yunyi, et autres
Publié: (2025)

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
par: Fu, Yu, et autres
Publié: (2023)

Provably Robust Multi-bit Watermarking for AI-generated Text
par: Qu, Wenjie, et autres
Publié: (2024)

Reference Recommendation based Membership Inference Attack against Hybrid-based Recommender Systems
par: Chi, Xiaoxiao, et autres
Publié: (2025)

Accelerating Vertical Federated Learning
par: Cai, Dongqi, et autres
Publié: (2022)

Towards Generalized and Stealthy Watermarking for Generative Code Models
par: Li, Haoxuan, et autres
Publié: (2025)

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
par: Ren, Jie, et autres
Publié: (2023)

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

Robust Reversible Watermarking in Encrypted Images Based on Dual-MSBs Spiral Embedding
par: Shen, Haoyu, et autres
Publié: (2026)

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

Adaptive and Robust Watermark for Generative Tabular Data
par: Ngo, Dung Daniel, et autres
Publié: (2024)

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
par: Liu, Bing, et autres
Publié: (2026)

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
par: Wu, Xiaodong, et autres
Publié: (2025)

Exploring Advanced Methodologies in Security Evaluation for LLMs
par: Huang, Jun, et autres
Publié: (2024)

EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning
par: Zhang, Tianyun, et autres
Publié: (2026)

WATER-GS: Toward Copyright Protection for 3D Gaussian Splatting via Universal Watermarking
par: Tan, Yuqi, et autres
Publié: (2024)

SEAL: Subspace-Anchored Watermarks for LLM Ownership
par: Dai, Yanbo, et autres
Publié: (2025)

Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack
par: Hui, Siqi, et autres
Publié: (2025)

Generative Model Watermarking Suppressing High-Frequency Artifacts
par: Zhang, Li, et autres
Publié: (2023)