DeepAI AI Chat
Log In Sign Up

Black-Box Face Recovery from Identity Features

by   Anton Razzhigaev, et al.

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.


page 2

page 4

page 6

page 8

page 11


Is Face Recognition Safe from Realizable Attacks?

Face recognition is a popular form of biometric authentication and due t...

Darker than Black-Box: Face Reconstruction from Similarity Queries

Several methods for inversion of face recognition models were recently p...

Controllable Inversion of Black-Box Face-Recognition Models via Diffusion

Face recognition models embed a face image into a low-dimensional identi...

Face Verification Bypass

Face verification systems aim to validate the claimed identity using fea...

Face Pasting Attack

Cujo AI and Adversa AI hosted the MLSec face recognition challenge. The ...

Examining the Human Perceptibility of Black-Box Adversarial Attacks on Face Recognition

The modern open internet contains billions of public images of human fac...

Pairwise Relational Networks using Local Appearance Features for Face Recognition

We propose a new face recognition method, called a pairwise relational n...