IdProv: identity-based provenance for synthetic image generation (student abstract)

• DOI: https://doi.org/10.1609/aaai.v37i13.26942
• Keywords: Identity Leakage, Generative Adversarial Networks (GANs), Synthetic Face Images, Image Provenance
• 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.

Recommended citation: Bhatia, H., Singh, J., Sangwan, G., Bharati, A., Singh, R. and Vatsa, M., 2023, June. IdProv: identity-based provenance for synthetic image generation (student abstract). In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 13, pp. 16164-16165). https://ojs.aaai.org/index.php/AAAI/article/download/26942/26714