Darker than Black-Box: Face Reconstruction from Similarity Queries
arXiv:2106.14290
Abstract
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.
References in corpus (6)
- Deep Residual Learning for Image Recognition
- Understanding Neural Networks Through Deep Visualization
- Deep Face Recognition: A Survey
- On the Reconstruction of Face Images from Deep Face Templates
- Generating Images with Perceptual Similarity Metrics based on Deep Networks
- Inverting Supervised Representations with Autoregressive Neural Density Models