arXiv AI September 1, 2026 By Gehao Zhang, Mingzhe Li, Eugene Bagdasarian, Shiqing Ma, Juan Zhai

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.

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

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 12

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

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.

By Ruisi Zhang, Neusha Javidnia, Nojan Sheybani, Farinaz Koushanfar

llms

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 Machine Learning

4d ago

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

Jun 11

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

arXiv:2606. 11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code.

By Yitong Zhang, Shiteng Lu, Jia Li

llms benchmarks safety

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

One email a morning, machine-written

Related stories

Multi-Channel Spread-Spectrum Code Watermarking

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

Adaptively Robust LLM Monitoring via Activation Watermarking

OpenStamp: A Watermark for Open-Source Language Models

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

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