Several methods for inversion of face recognition models were recently presented, attempting to reconstruct a face from deep templates. Although some of these approaches work in a black-box setup using only face embeddings, usually, on the end-user side, only similarity scores are provided. Therefore, these algorithms are inapplicable in such scenarios. We propose a novel approach that allows reconstructing the face querying only similarity scores of the black-box model. While our algorithm operates in a more general setup, experiments show that it is query efficient and outperforms the existing methods.
@article{arxiv.2106.14290,
title = {Darker than Black-Box: Face Reconstruction from Similarity Queries},
author = {Anton Razzhigaev and Klim Kireev and Igor Udovichenko and Aleksandr Petiushko},
journal= {arXiv preprint arXiv:2106.14290},
year = {2021}
}