arXiv AI November 5, 2026 By Elise L. Han, Tatsunori Hashimoto

Reconciling Privacy with Provenance for Language Model Watermarks

The paper proposes a new approach to watermarking language models that balances privacy and provenance. By shifting the focus from tracking individual texts to estimating aggregate usage, the authors develop locally differentially private watermarks that limit the evidence any single text can contribute to detection. The Red‑Green Sequence (RGS) watermark achieves accurate frequency estimation with low error rates even at stringent privacy levels (ε=1–2) across various models and realistic deployment scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 31

OpenStamp: A Watermark for Open-Source Language Models

arXiv:2608.27899v1 Announce Type: cross Abstract: With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to...

By Miroojin Bakshi, Saksham Rastogi, Danish Pruthi

llms fine-tuning

arXiv Machine Learning

Jun 18

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.

By Chih-Duo Hong, Yen-Pang Chen, Fang Yu

llms rag benchmarks

arXiv AI

Oct 21

A Unified Attack Framework against Statistical Generative Watermarks for Large Language Models

arXiv:2610.27653v1 Announce Type: cross Abstract: Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical sig...

By Romina Omidi, Nima Naderloui, Yuan Hong, Binghui Wang

llms rag safety

arXiv Computation and Language

Oct 15

Majority Bit-Aware Watermarking For Large Language Models

arXiv:2508.03829v3 Announce Type: replace Abstract: The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To addres...

By Jiahao Xu, Rui Hu, Olivera Kotevska, Zikai Zhang

llms benchmarks

arXiv AI

Jun 10

Advancing the State-of-the-Art in Empirical Privacy Auditing

arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.

By Nicole Mitchell, Galen Andrew, Arun Ganesh, Brendan McMahan, Peter Kairouz

llms fine-tuning benchmarks safety

Hugging Face Trending Papers

Jun 8

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Language Models (MLLMs), which process both text and images, introduce unique privacy challenges that remain underexplored.

llms multimodal safety