Darker than Black-Box: Face Reconstruction from Similarity Queries
This addresses a security and privacy challenge for face recognition systems by enabling reconstruction in more restrictive scenarios, representing an incremental improvement over prior black-box methods.
The paper tackles the problem of reconstructing faces from black-box face recognition models when only similarity scores are available, proposing a novel approach that is query-efficient and outperforms existing methods.
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.