# Latent Secret Spin: Keyed Orthogonal Rotations for Blind Speech Watermarking in Anisotropic Latent Spaces

Source: [Latent Secret Spin: Keyed Orthogonal Rotations for Blind Speech Watermarking in Anisotropic Latent Spaces](<https://www.sota2.com/research/paper/6a02b428dbc836b87d824730>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-13T05:00:05.563Z

Authors: Emma Coletta, Massimiliano Todisco, Michele Panariello, Antonio Faonio, Nicholas Evans

Published: 2026-05-08T19:53:31.000Z

## Abstract

We introduce Latent Secret Spin (LSS), a blind speech watermarking method based on geometric operations in codec latent space. Based upon orthogonal rotations to principal components, LSS induces imperceptible but detectable covariance signatures according to a pseudo-random watermarking schedule. The scheme generalises across datasets, preserves perceptual quality and, unlike some learned, neural watermarking schemes, it does not require neural network training, is resistant to common signal manipulations and is flexible to payload size. Analyses show that structured latent-space watermarking is a promising and interpretable alternative to existing approaches.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Watermark Detection on VoxPopuli-100k Scenario T1](<https://www.sota2.com/research/sota/watermark-detection-on-voxpopuli-100k-scenario-t1.md>): Watermark Detection; VoxPopuli-100k Scenario T1; AUC: 99.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.08431>)

[PDF](<https://arxiv.org/pdf/2605.08431.pdf>)