Sung Ju Lee

2 accepted papers

2026

PHASEMARK: A POST-HOC, OPTIMIZATION-FREE WATERMARKING OF AI-GENERATED IMAGES IN THE LATENT FREQUENCY DOMAIN

ICASSP 2026poster

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 mod…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integrity

Sung Ju Lee, Nam Ik Cho

ICCV 2025poster

Semantic watermarking techniques for latent diffusion models (LDMs) are robust against regeneration attacks, but often suffer from detection performance degradation due to the loss of frequency integrity. To tackle this problem, we propose a novel embedding method called Hermitian Symmetric Fourier…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗