Black-Box Face Recovery from Identity Features

TL;DR

This paper introduces a new black-box face recovery algorithm that reconstructs face images from identity features using iterative Gaussian sampling, successfully attacking face recognition systems with fewer queries.

Contribution

It proposes a novel iterative sampling method for face reconstruction from identity features, demonstrating effectiveness across different models with minimal queries.

Findings

Successfully reconstructs face images from identity features

Attacks state-of-the-art face recognition systems effectively

Requires fewer queries than existing methods

Abstract

In this work, we present a novel algorithm based on an it-erative sampling of random Gaussian blobs for black-box face recovery, given only an output feature vector of deep face recognition systems. We attack the state-of-the-art face recognition system (ArcFace) to test our algorithm. Another network with different architecture (FaceNet) is used as an independent critic showing that the target person can be identified with the reconstructed image even with no access to the attacked model. Furthermore, our algorithm requires a significantly less number of queries compared to the state-of-the-art solution.