IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract)

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

AAAI 2023 pp. 16164-16165

doi:10.1609/AAAI.V37I13.26942 /aaai/2023/bhatia2023aaai-idprov/

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.

PDF AAAI Semantic Scholar

Cite

Text

Bhatia et al. "IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26942

Markdown

[Bhatia et al. "IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/bhatia2023aaai-idprov/) doi:10.1609/AAAI.V37I13.26942

BibTeX

@inproceedings{bhatia2023aaai-idprov,
  title     = {{IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract)}},
  author    = {Bhatia, Harshil and Singh, Jaisidh and Sangwan, Gaurav and Bharati, Aparna and Singh, Richa and Vatsa, Mayank},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16164-16165},
  doi       = {10.1609/AAAI.V37I13.26942},
  url       = {https://mlanthology.org/aaai/2023/bhatia2023aaai-idprov/}
}