A trained neural network model contains information on the training data. Given such a model, malicious parties can leverage the "knowledge" in this model and design ways to print out any usable information (known as model inversion attack). Therefore, it is valuable to explore the ways to conduct a such attack and demonstrate its severity. In this work, we proposed ways to generate a data point of the target class without prior knowledge of the exact target distribution by using a pre-trained diffusion model.
Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm
Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria；Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, USA；Chandra Family Department of Electrical Engineering, University of Texas at Austin, USA；Department of Diagnostic Medicine, Dell Medical School, University of Texas at Austin, USA
A Targeted Sampling Strategy for Compressive Cryo Focused Ion Beam Scanning Electron Microscopy
University of Liverpool（利物浦大学）；Rosalind Franklin Institute（罗莎琳德·富兰克林研究所）；King’s College London（伦敦国王学院）；University of Oxford（牛津大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）；Sivananthan Laboratories（西瓦南坦实验室）
Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）
Adaptive sampling using variational autoencoder and reinforcement learning
Department of Engineering Cybernetics, Norwegian University of Science and Technology（工程 cybernetics 系，挪威科学与技术大学）；Department of Engineering Sciences, University of Agder（工程科学系，阿格德大学）
