Face Pasting Attack

TL;DR

This paper presents a face pasting attack method against black box face recognition models, achieving successful targeted attacks with minimal queries by pasting and manipulating target faces in source images.

Contribution

It introduces a face pasting attack technique that effectively fools face recognition models with low query counts, advancing attack strategies in black box settings.

Findings

Achieved 3rd place in the MLSec face recognition challenge.

Approximately 7.7 queries needed for a successful attack.

200 queries used for the highest scoring attack.

Abstract

Cujo AI and Adversa AI hosted the MLSec face recognition challenge. The goal was to attack a black box face recognition model with targeted attacks. The model returned the confidence of the target class and a stealthiness score. For an attack to be considered successful the target class has to have the highest confidence among all classes and the stealthiness has to be at least 0.5. In our approach we paste the face of a target into a source image. By utilizing position, scaling, rotation and transparency attributes we reached 3rd place. Our approach took approximately 200 queries per attack for the final highest score and about ~7.7 queries minimum for a successful attack. The code is available at https://github.com/bunni90/FacePastingAttack .