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

arXiv: https://arxiv.org/abs/2609.38722 · HTML: https://mlsanity.com/paper/2609.38722/

## 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 16 of its 25 references that are in the map.
- First posted on arXiv 30 Sep 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, 16 of 16)

- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [On the Possibilities of AI-Generated Text Detection](https://mlsanity.com/paper/2304.04736/) (2023)
- [No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices](https://mlsanity.com/paper/2402.16187/) (2024)
- [Pseudorandom Error-Correcting Codes](https://mlsanity.com/paper/2402.09370/) (2024)
- [Robust Detection of Watermarks for Large Language Models Under Human Edits](https://mlsanity.com/paper/2411.13868/) (2024)
- [A Watermark for Order-Agnostic Language Models](https://mlsanity.com/paper/2410.13805/) (2024)
- [Watermarking Language Models with Error Correcting Codes](https://mlsanity.com/paper/2406.10281/) (2024)
- [WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents](https://mlsanity.com/paper/2409.05112/) (2024)
- [Efficiently Identifying Watermarked Segments in Mixed-Source Texts](https://mlsanity.com/paper/2410.03600/) (2024)
- [Segmenting Watermarked Texts From Language Models](https://mlsanity.com/paper/2410.20670/) (2024)
- [Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking](https://mlsanity.com/paper/2510.01637/) (2025)

## Abstract (arXiv)

LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during generation. However, a small post-generation edit may change the meaning of the text without removing its overall watermark signal, creating a risk that the modified content is still attributed to the original model. We propose Anchor-ECC, which incorporates the error-correcting code (ECC) constraints and explicit boundary anchors into the watermark structure and pairs them with a dynamic-programming decoder to detect and localize post-generation edits. Across Qwen3-8B, Mistral-7B-Instruct-v0.3, and OPT-125M, the approximate-hard setting achieves about 99.7% block-level true positive rate (TPR) with at most 7.6% false alarm rate (FAR) for edit detection under mixed insertions, deletions, and substitutions, while preserving the distinction between watermarked outputs and unwatermarked text. Additional quality experiments identify lower-perplexity configurations that retain strong edit-detection performance. Together, these results extend LLM watermarking from source identification to local integrity verification while supporting configurable trade-offs between detection reliability and generation quality.