# Synchronization-Free Algebraic Fingerprints for Large Language Models: From Autoregressive to Diffusion Models

arXiv: https://arxiv.org/abs/2607.16648 · HTML: https://mlsanity.com/paper/2607.16648/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 18 Jul 2026.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Watermarking Makes Language Models Radioactive](https://mlsanity.com/paper/2402.14904/) (2024)
- [Provably Robust Multi-bit Watermarking for AI-generated Text](https://mlsanity.com/paper/2401.16820/) (2024)
- [GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick](https://mlsanity.com/paper/2402.12948/) (2024)
- [Watermarking Text Data on Large Language Models for Dataset Copyright](https://mlsanity.com/paper/2305.13257/) (2023)
- [Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge](https://mlsanity.com/paper/2503.04036/) (2025)
- [Duwak: Dual Watermarks in Large Language Models](https://mlsanity.com/paper/2403.13000/) (2024)
- [FreqMark: Frequency-Based Watermark for Sentence-Level Detection of LLM-Generated Text](https://mlsanity.com/paper/2410.10876/) (2024)
- [Ensemble Watermarks for Large Language Models](https://mlsanity.com/paper/2411.19563/) (2024)
- [An End-to-End Model for Logits-Based Large Language Models Watermarking](https://mlsanity.com/paper/2505.02344/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have created an urgent need for reliable watermarking methods that enable attribution of generated text while remaining robust to editing and paraphrasing. We propose a novel synchronization-free watermarking scheme in which every watermark consists of a single binary congruence generated from a pair of neighbouring tokens. For each token pair, a cryptographic hash determines an evaluation point of a Reed--Solomon polynomial representing the secret identity, while the parity of the polynomial evaluation determines the watermark bit embedded into the second token of the pair. Since each congruence is self-contained and depends only on the local token pair, the proposed construction is naturally resistant to insertions, deletions, and token reordering. We analyse the recovery problem from an algebraic perspective, discuss several decoding algorithms suitable for different identity sizes, and model watermark corruption as a Binary Symmetric Channel. The analysis shows that reliable recovery requires only a small redundancy even for relatively high token corruption rates. Unlike existing block-based watermarking schemes, the proposed method avoids synchronization problems while providing a flexible framework for embedding both short and long secret identities.