Author

Mario Köppen

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

DeepFreqMark: End-To-End Learnable Frequency-Domain Watermarking with Spherical Attack Simulation for Latent Diffusion Models

DeepFreqMark is proposed, an end-to-end learnable frequency-domain watermarking framework that replaces manual pattern engineering with a neural message encoder and decoder and operates directly on the noise latent while strictly preserving the Gaussian variance.

Chen-Hsiu Huang, Mario Köppen, Ja-Ling Wu · 0 citations