SemField: A Simple, Linear, Continuous, yet Robust Semantic Watermark

Summary

SemField is a training-free semantic watermark that embeds a continuous, linear signal into the sentence embedding space, using a shared secret key to define a Gaussian direction. SemField-PL, a polarity-locked variant, fixes the orientation from the initial sentence and reinforces it during generation. Across clean detection and four paraphrasing attacks, both variants reach a mean True Positive Rate of 88.2% to 90.4% at a 1% False Positive Rate, across three models and against 12 baselines.