Local error checks improve detection of edits in watermarked AI text
Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes
Cryptography and SecurityComputation and Language
Summary
AI models can add hidden patterns, or watermarks, to text they generate, helping people tell AI text from human text. But if someone slightly changes the AI-written text afterward, the original watermark might still look present even though the meaning changes. The authors created Anchor-ECC, a method that uses special error-correcting codes and markers to spot and locate those small edits within the watermarked text. This method works well across different AI models, detecting most edits while keeping the watermark reliable. Anchor-ECC helps not just verify where AI text came from but also checks if the text has been altered after it was generated.
What this means in practice
- •For content moderators: Detect precise locations of small edits in AI-generated text to verify content integrity and attribution.
- •For online publishers: Ensure articles labeled as AI-generated remain unaltered after publication by identifying localized text changes.
Authors
Zewei Deng, Muhammad Siddeek, Liyan Xie, Mohamed Seif, Mengdi Wang, H. Vincent Poor, Andrea Goldsmith
Abstract
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.