arXiv Machine Learning June 18, 2026 By Chih-Duo Hong, Yen-Pang Chen, Fang Yu

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

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 30

Adaptively Robust LLM Monitoring via Activation Watermarking

arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.

By Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas

llms fine-tuning benchmarks safety

arXiv AI

Jul 22

ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration

arXiv:2607. 18445v1 Announce Type: cross Abstract: Regulatory regimes such as the EU AI Act mandate machine-readable marking of synthetic text, but existing watermark detectors rely on the generating LM and on heuristic thresholds with no closed-form calibration.

By Chengheng Li-Chen, Kyuhee Kim

llms

arXiv Machine Learning

Jul 8

Multi-Channel Spread-Spectrum Code Watermarking

arXiv:2607. 06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need.

By Soohyeon Choi, Debin Gao, Yue Duan

llms rag

arXiv AI

Jun 2

Linguistics-Aware Non-Distortionary LLM Watermarking

arXiv:2606. 00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verification to the model provider.

By Shinwoo Park, Hyejin Park, Hyeseon An, Yo-Sub Han

llms computer-vision nlp

arXiv AI

5d ago

Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models

arXiv:2512. 13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models.

By Malte Hellmeier

llms rag

arXiv Machine Learning

Jul 8

Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking

arXiv:2607. 05694v1 Announce Type: cross Abstract: Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and semantic distortion.

By Xiaopu Wang, Zelin He, Chengyuan Liu, Runze Li

llms

Related stories

Adaptively Robust LLM Monitoring via Activation Watermarking

ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration

Multi-Channel Spread-Spectrum Code Watermarking

Linguistics-Aware Non-Distortionary LLM Watermarking

Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models

Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking