Work

OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting

Year: 2025

Type: conference-paper

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 (

Source: Proceedings of the AAAI Conference on Artificial Intelligence

DOI: 10.1609/aaai.v39i16.33818

Authors: Jianwei Fei, Yunshu Dai, Zhihua Xia, Fangjun Huang, Jiantao Zhou

Institutions: University of Macau, Sun Yat-sen University, Jinan University, University of Jinan

Language: English

Topic: Advanced Steganography and Watermarking Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond