ML Anthology

OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting

Jianwei Fei, Yunshu Dai, Zhihua Xia, Fangjun Huang, Jiantao Zhou
AAAI 2025 pp. 16550-16558
doi:10.1609/AAAI.V39I16.33818 /aaai/2025/fei2025aaai-omnimark/

Abstract

We introduce OmniMark, a novel and efficient fingerprinting method for Latent Diffusion Models (LDM). OmniMark can encode user-specific fingerprints across diverse dimensions of the weights of the LDM, including kernels, filters, channels, and spatial domains. The LDM is fine-tuned to encode the invisible fingerprint into generated images, which can be decoded by a decoder. By altering fingerprints and re-encoding the weights, OmniMark supports efficient and scalable ad-hoc generation (

AAAI Semantic Scholar

Cite

Text

Fei et al. "OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I16.33818

Markdown

[Fei et al. "OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/fei2025aaai-omnimark/) doi:10.1609/AAAI.V39I16.33818

BibTeX

@inproceedings{fei2025aaai-omnimark,
  title     = {{OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting}},
  author    = {Fei, Jianwei and Dai, Yunshu and Xia, Zhihua and Huang, Fangjun and Zhou, Jiantao},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {16550-16558},
  doi       = {10.1609/AAAI.V39I16.33818},
  url       = {https://mlanthology.org/aaai/2025/fei2025aaai-omnimark/}
}