arXiv Machine Learning August 12, 2026 By Ruisi Zhang, Neusha Javidnia, Nojan Sheybani, Farinaz Koushanfar

Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign

Read the original on arXiv Machine Learning →

arXiv:2502. 02068v3 Announce Type: replace-cross Abstract: This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations and inappropriate misuse in software development.

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 Machine Learning.

llms

arXiv AI

Sep 1

Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice

The paper demonstrates that N‑gram based code watermarking schemes, widely used to identify machine‑generated code, are ineffective when faced with realistic code obfuscation. By modeling semantics‑preserving transformations as a Markov random walk and introducing the assumption of distribution consistency, the authors prove that obfuscation can drive the failure rate of any detector to nearly 1 minus its false‑positive rate. Extensive experiments across multiple watermarking methods, LLMs, languages, benchmarks, and obfuscators confirm that detectors collapse to near‑random performance (AUROC ≈ 0.5) after obfuscation.

By Gehao Zhang, Mingzhe Li, Eugene Bagdasarian, Shiqing Ma, Juan Zhai

llms benchmarks

arXiv AI

Aug 14

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

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 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 AI

Aug 5

Attribute-based Undetectable Watermarking for Generative AI Models

arXiv:2608. 03174v1 Announce Type: cross Abstract: Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs.

By Miryam Mi-Ying Huang, Chung-Wei Lee, Max Raffel, Er-Cheng Tang

safety

arXiv Computation and Language

3d ago

Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes

arXiv:2609.38722v1 Announce Type: cross Abstract: LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during...

By Zewei Deng, Muhammad Siddeek, Liyan Xie, Mohamed Seif, Mengdi Wang, H. Vincent Poor, Andrea Goldsmith

llms rag

One email a morning, machine-written

Related stories

Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice

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

Multi-Channel Spread-Spectrum Code Watermarking

OpenStamp: A Watermark for Open-Source Language Models

Attribute-based Undetectable Watermarking for Generative AI Models

Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes