26942@AAAI

Total: 1

#1 IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract) [PDF1] [Copy] [Kimi] [REL]

Authors: Harshil Bhatia, Jaisidh Singh, Gaurav Sangwan, Aparna Bharati, Richa Singh, Mayank Vatsa

Recent advancements in Generative Adversarial Networks (GANs) have made it possible to obtain high-quality face images of synthetic identities. These networks see large amounts of real faces in order to learn to generate realistic looking synthetic images. However, the concept of a synthetic identity for these images is not very well-defined. In this work, we verify identity leakage from the training set containing real images into the latent space and propose a novel method, IdProv, that uses image composition to trace the source of identity signals in the generated image.

Subject: AAAI.2023 - Student Abstract and Poster Program