AAAI 2023technical1 citations
IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract)
Harshil Bhatia, Jaisidh Singh, Gaurav Sangwan, Aparna Bharati, Richa Singh, Mayank Vatsa
Abstract
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.
BibTeX
@article{Bhatia_Singh_Sangwan_Bharati_Singh_Vatsa_2024, title={IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract)}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26942}, DOI={10.1609/aaai.v37i13.26942}, abstractNote={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.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Bhatia, Harshil and Singh, Jaisidh and Sangwan, Gaurav and Bharati, Aparna and Singh, Richa and Vatsa, Mayank}, year={2024}, month={Jul.}, pages={16164-16165} }