Copertina

"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Xinyu, Dong, Ziping, Liu, Qingyu, Hong, Yuan, Ba, Zhongjie, Ren, Kui
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
di: Dong, Ziping, et al.
Pubblicazione: (2025)

Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
di: Ba, Zhongjie, et al.
Pubblicazione: (2025)

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
di: Zhang, Xinyu, et al.
Pubblicazione: (2023)

Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection
di: Liu, Qingyu, et al.
Pubblicazione: (2026)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
di: Hong, Hanbin, et al.
Pubblicazione: (2023)

A Certified Robust Watermark For Large Language Models
di: Feng, Xianheng, et al.
Pubblicazione: (2024)

SWAT: A System-Wide Approach to Tunable Leakage Mitigation in Encrypted Data Stores
di: Zheng, Leqian, et al.
Pubblicazione: (2023)

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
di: Yang, Yuxin, et al.
Pubblicazione: (2024)

XNN: Paradigm Shift in Mitigating Identity Leakage within Cloud-Enabled Deep Learning
di: Liu, Kaixin, et al.
Pubblicazione: (2024)

Deep Learning model integrity checking mechanism using watermarking technique
di: Hoque, Shahinul, et al.
Pubblicazione: (2023)

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
di: He, Yu, et al.
Pubblicazione: (2025)

Leakage-abuse Attack Against Substring-SSE with Partially Known Dataset
di: Ba, Xijie, et al.
Pubblicazione: (2025)

Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning
di: Ma, Binhao, et al.
Pubblicazione: (2024)

WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
di: Giboulot, Eva, et al.
Pubblicazione: (2024)

Optimizing watermarks for large language models
di: Wouters, Bram
Pubblicazione: (2023)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
di: Meng, Jiayang, et al.
Pubblicazione: (2025)

Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations
di: Ioniţă, Alexandru, et al.
Pubblicazione: (2025)

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

CycleGANWM: A CycleGAN watermarking method for ownership verification
di: Lin, Dongdong, et al.
Pubblicazione: (2022)

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

SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI
di: Ren, Kui, et al.
Pubblicazione: (2024)

SoK: On Gradient Leakage in Federated Learning
di: Du, Jiacheng, et al.
Pubblicazione: (2024)

Provably Robust Multi-bit Watermarking for AI-generated Text
di: Qu, Wenjie, et al.
Pubblicazione: (2024)

Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarking
di: Guo, Fan, et al.
Pubblicazione: (2026)

RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent
di: Xu, Huiyu, et al.
Pubblicazione: (2024)

Phoneme-Based Proactive Anti-Eavesdropping with Controlled Recording Privilege
di: Huang, Peng, et al.
Pubblicazione: (2024)

SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
di: Ba, Zhongjie, et al.
Pubblicazione: (2023)

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
di: Ren, Jie, et al.
Pubblicazione: (2023)

Zebrafix: Mitigating Memory-Centric Side-Channel Leakage via Interleaving
di: Pätschke, Anna, et al.
Pubblicazione: (2025)

POLARIS: Explainable Artificial Intelligence for Mitigating Power Side-Channel Leakage
di: Mahfuz, Tanzim, et al.
Pubblicazione: (2025)

SiGRRW: A Single-Watermark Robust Reversible Watermarking Framework with Guiding Strategy
di: Xu, Zikai, et al.
Pubblicazione: (2026)

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
di: Wang, Yaopeng, et al.
Pubblicazione: (2026)

PT-Mark: Invisible Watermarking for Text-to-image Diffusion Models via Semantic-aware Pivotal Tuning
di: Wang, Yaopeng, et al.
Pubblicazione: (2025)

EGNInfoLeaker: Unveiling the Risks of Public Key Reuse and User Identity Leakage in Blockchain
di: Li, Chenyu, et al.
Pubblicazione: (2025)

Robustness of Watermarking on Text-to-Image Diffusion Models
di: Wu, Xiaodong, et al.
Pubblicazione: (2024)

Adaptive and Robust Watermark for Generative Tabular Data
di: Ngo, Dung Daniel, et al.
Pubblicazione: (2024)

Perfect message authentication codes are robust to small deviations from uniform key distributions
di: Ryabko, Boris
Pubblicazione: (2025)

WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
di: Huang, Baizhou, et al.
Pubblicazione: (2024)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
di: Fu, Jie, et al.
Pubblicazione: (2026)

Robust-Wide: Robust Watermarking against Instruction-driven Image Editing
di: Hu, Runyi, et al.
Pubblicazione: (2024)