Extracting Training Data from Unconditional Diffusion Models

Y Chen, X Ma, D Zou, YG Jiang - arXiv preprint arXiv:2406.12752, 2024 - arxiv.org
As diffusion probabilistic models (DPMs) are being employed as mainstream models for
generative artificial intelligence (AI), the study of their memorization of the raw training data …

Multi‐view synergistic enhanced fault recording data for transmission line fault classification

M Jia, X Huang, F Han, D Yan, W Wang… - IET …, 2024 - Wiley Online Library
Fault recorded data has been proven to be effective for fault diagnosis of overhead
transmission lines. Utilizing deep learning to mine potential fault patterns in fault recording …