PhaseMark: A Post-hoc, Optimization-Free Watermarking of AI-generated Images in the Latent Frequency Domain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Sung Ju, Cho, Nam Ik
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909994688970752
author Lee, Sung Ju
Cho, Nam Ik
author_facet Lee, Sung Ju
Cho, Nam Ik
contents The proliferation of hyper-realistic images from Latent Diffusion Models (LDMs) demands robust watermarking, yet existing post-hoc methods are prohibitively slow due to iterative optimization or inversion processes. We introduce PhaseMark, a single-shot, optimization-free framework that directly modulates the phase in the VAE latent frequency domain. This approach makes PhaseMark thousands of times faster than optimization-based techniques while achieving state-of-the-art resilience against severe attacks, including regeneration, without degrading image quality. We analyze four modulation variants, revealing a clear performance-quality trade-off. PhaseMark demonstrates a new paradigm where efficient, resilient watermarking is achieved by exploiting intrinsic latent properties.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13128
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PhaseMark: A Post-hoc, Optimization-Free Watermarking of AI-generated Images in the Latent Frequency Domain
Lee, Sung Ju
Cho, Nam Ik
Computer Vision and Pattern Recognition
The proliferation of hyper-realistic images from Latent Diffusion Models (LDMs) demands robust watermarking, yet existing post-hoc methods are prohibitively slow due to iterative optimization or inversion processes. We introduce PhaseMark, a single-shot, optimization-free framework that directly modulates the phase in the VAE latent frequency domain. This approach makes PhaseMark thousands of times faster than optimization-based techniques while achieving state-of-the-art resilience against severe attacks, including regeneration, without degrading image quality. We analyze four modulation variants, revealing a clear performance-quality trade-off. PhaseMark demonstrates a new paradigm where efficient, resilient watermarking is achieved by exploiting intrinsic latent properties.
title PhaseMark: A Post-hoc, Optimization-Free Watermarking of AI-generated Images in the Latent Frequency Domain
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.13128