arXiv AI
Jul 7
Selective Disclosure Watermarking for Large Language Models
arXiv:2607. 05353v1 Announce Type: cross Abstract: Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs).
WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading
Related stories
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...
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.
Hugging Face Trending Papers
Jun 23
CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking
Reliable provenance for LLM outputs requires multi-bit watermarks that remain robust under editing while maintaining strict false-positive control. Existing ECC-based LLM watermarks rely largely on hard-decision decoding, discarding token-level reliability information.
arXiv AI
Aug 7
Text Steganography with Dynamic Codebook and Multimodal Large Language Model
arXiv:2604. 20269v2 Announce Type: replace-cross Abstract: With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance.
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.
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.
arXiv Computation and Language
3d ago
More Haste, Less Speed: Weaker Single-Layer Watermark Improves Distortion-Free Watermark Ensembles
The paper investigates watermarking for large language model outputs, noting that stronger single-layer watermarks reduce token entropy and weaken subsequent layers. It demonstrates that detectability is limited by entropy and that watermark ensembles monotonically lower entropy and the green‑list ratio. The authors propose using weaker single‑layer watermarks to maintain entropy, showing through theory and experiments that this approach improves both detectability and robustness compared to strong baselines.
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.
arXiv Computer Vision
3d ago
Asymmetric Phase Coding Video Watermarking
arXiv:2608.29212v1 Announce Type: cross Abstract: Existing video watermarking systems are symmetric: the party that can verify a mark holds the extractor weights or generator secret and can therefore...
arXiv AI
3d ago
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.
arXiv AI
Jul 20
Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.