-
AR Database
The dataset used in the paper is the AR database, which consists of 100 individuals, 2 sessions, and total 26 images for each person. The images are resized to 64 x 64 and the... -
MegaFace Challenge 1
The MegaFace Challenge 1 dataset contains 1 million images of 690K individuals. -
FFHQ Dataset
The FFHQ dataset is a large dataset of high-quality face images with 1024 × 1024 resolution with variations in age, gender, and glasses. -
Face Research London Lab (FRLL) dataset
The Face Research London Lab (FRLL) dataset contains images of faces with varying lighting conditions, expressions, and poses. -
Face Recognition Grand Challenge (FRGCv2)
The Face Recognition Grand Challenge (FRGCv2) dataset contains images of faces with varying lighting conditions, expressions, and poses. -
CelebA Dataset
Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model.