3 accepted papers
Latent diffusion models have achieved remarkable success in high-fidelity text-to-image generation, but their tendency to memorize training data raises critical privacy and intellectual property concerns. Membership inference attacks (MIAs) provide a principled way to audit such memorization by dete…
The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversaries exploiting diffusion models for inpainting tasks, such as replacing a specific region with a celebrity. While existin…
Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes. However existing methods select only informative and relevant views using predefined scores for training and testing phases. This constr…