Semantic watermarking technique detects ai generated text despite paraphrasing
SemField: A Simple, Linear, Continuous, yet Robust Semantic Watermark
Cryptography and Security
Summary
It is hard to tell if text was written by an AI or a human, especially when the AI rephrases sentences to hide its origin. The authors propose SemField, a new way to subtly mark AI-generated text by embedding a special continuous signal into the meanings of sentences. This signal adds up over a whole document, making it easy to detect even if the sentences are moved around or slightly changed. Their method works well against various tricks to hide AI writing and keeps the text sounding natural.
What this means in practice
- •For content moderators: Detect AI-generated text on online platforms even when users rephrase or reorder sentences.
- •For publishing platforms: Identify AI-written documents reliably to maintain proper attribution and transparency in published content.
Authors
Varun Gumma, Navonil Majumdar, Soujanya Poria
Abstract
The rapid proliferation of Large Language Models (LLMs) necessitates reliable watermarking techniques to identify AI-generated text and ensure appropriate attribution. While token-based watermarks are vulnerable to paraphrasing, a central challenge for semantic watermarking is to turn sentence meanings into a stable, well-calibrated document-level signal. To this end, we introduce SemField, a simple, training-free semantic watermark that embeds a continuous, linear signal directly into the sentence embedding space. Using a shared secret key to define a specific Gaussian direction, SemField iteratively evaluates candidate sentences and selects those that maximize the alignment of the cumulative document aggregate with this targeted direction. We also propose SemField-PL, a polarity-locked variant that first determines the optimal orientation from the initial sentence and continuously reinforces it throughout the generation process. The document-level aggregated formulation guarantees exact invariance to sentence reordering and provides theoretical bounds against structural tampering, such as sentence insertion and deletion. Lastly, with extensive evaluations across three models, we demonstrate that both variants outperform 12 recent baselines. Across clean detection and four paraphrasing attacks, both variants achieve a mean True Positive Rate (TPR) of 88.2% to 90.4% at a 1% False Positive Rate (FPR), all while maintaining comparable perplexity and naturalness as human-generated content. We open-source our implementation at https://github.com/declare-lab/SemField