Cover Image

Watermarking Needs Input Repetition Masking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khachaturov, David, Mullins, Robert, Shumailov, Ilia, Dathathri, Sumanth
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adversarial Suffix Filtering: a Defense Pipeline for LLMs
by: Khachaturov, David, et al.
Published: (2025)

Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness
by: Khachaturov, David, et al.
Published: (2024)

ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
by: Clifford, Eleanor, et al.
Published: (2022)

Beyond Slow Signs in High-fidelity Model Extraction
by: Foerster, Hanna, et al.
Published: (2024)

Stealing User Prompts from Mixture of Experts
by: Yona, Itay, et al.
Published: (2024)

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
by: Foerster, Hanna, et al.
Published: (2026)

Interpreting the Repeated Token Phenomenon in Large Language Models
by: Yona, Itay, et al.
Published: (2025)

Architectural Neural Backdoors from First Principles
by: Langford, Harry, et al.
Published: (2024)

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
by: Hayes, Jamie, et al.
Published: (2024)

Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
by: Zhang, Hanlin, et al.
Published: (2023)

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
by: Liang, Jiacheng, et al.
Published: (2024)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
by: Gao, Yue, et al.
Published: (2023)

Buffer Overflow in Mixture of Experts
by: Hayes, Jamie, et al.
Published: (2024)

No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
by: Pang, Qi, et al.
Published: (2024)

On the Learnability of Watermarks for Language Models
by: Gu, Chenchen, et al.
Published: (2023)

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
by: Foerster, Hanna, et al.
Published: (2025)

A Watermark for Large Language Models
by: Kirchenbauer, John, et al.
Published: (2023)

On the Reliability of Watermarks for Large Language Models
by: Kirchenbauer, John, et al.
Published: (2023)

Publicly-Detectable Watermarking for Language Models
by: Fairoze, Jaiden, et al.
Published: (2023)

A Transfer Attack to Image Watermarks
by: Hu, Yuepeng, et al.
Published: (2024)

Revisiting the Robustness of Watermarking to Paraphrasing Attacks
by: Rastogi, Saksham, et al.
Published: (2024)

Watermarking Language Models through Language Models
by: Dasgupta, Agnibh, et al.
Published: (2024)

Topic-Based Watermarks for Large Language Models
by: Nemecek, Alexander, et al.
Published: (2024)

Watermarking Language Models with Error Correcting Codes
by: Chao, Patrick, et al.
Published: (2024)

A Watermark for Black-Box Language Models
by: Bahri, Dara, et al.
Published: (2024)

Robust Distortion-free Watermarks for Language Models
by: Kuditipudi, Rohith, et al.
Published: (2023)

PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
by: Duan, Haohua, et al.
Published: (2025)

Watermarks for Embeddings-as-a-Service Large Language Models
by: Shetty, Anudeex
Published: (2025)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
by: Shumailov, Ilia, et al.
Published: (2024)

Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
by: Joshi, Kunj, et al.
Published: (2025)

ceLLMate: Sandboxing Browser AI Agents
by: Meng, Luoxi, et al.
Published: (2025)

Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
by: Cui, Xinyue, et al.
Published: (2025)

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
by: Rastogi, Saksham, et al.
Published: (2025)

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
by: Wu, Yihan, et al.
Published: (2023)

TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
by: Sander, Tom, et al.
Published: (2026)

Locking Machine Learning Models into Hardware
by: Clifford, Eleanor, et al.
Published: (2024)

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
by: Huo, Mingjia, et al.
Published: (2024)

WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
by: Shetty, Anudeex, et al.
Published: (2024)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
by: Shetty, Anudeex, et al.
Published: (2024)

The Curse of Recursion: Training on Generated Data Makes Models Forget
by: Shumailov, Ilia, et al.
Published: (2023)