DeepAI AI Chat
Log In Sign Up

On adversarial patches: real-world attack on ArcFace-100 face recognition system

by   Mikhail Pautov, et al.

Recent works showed the vulnerability of image classifiers to adversarial attacks in the digital domain. However, the majority of attacks involve adding small perturbation to an image to fool the classifier. Unfortunately, such procedures can not be used to conduct a real-world attack, where adding an adversarial attribute to the photo is a more practical approach. In this paper, we study the problem of real-world attacks on face recognition systems. We examine security of one of the best public face recognition systems, LResNet100E-IR with ArcFace loss, and propose a simple method to attack it in the physical world. The method suggests creating an adversarial patch that can be printed, added as a face attribute and photographed; the photo of a person with such attribute is then passed to the classifier such that the classifier's recognized class changes from correct to the desired one. Proposed generating procedure allows projecting adversarial patches not only on different areas of the face, such as nose or forehead but also on some wearable accessory, such as eyeglasses.


Efficient Decision-based Black-box Adversarial Attacks on Face Recognition

Face recognition has obtained remarkable progress in recent years due to...

Detection of Face Recognition Adversarial Attacks

Deep Learning methods have become state-of-the-art for solving tasks suc...

Threat of Adversarial Attacks on Face Recognition: A Comprehensive Survey

Face recognition (FR) systems have demonstrated outstanding verification...

Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition

Deep learning models have shown their vulnerability when dealing with ad...

On Brightness Agnostic Adversarial Examples Against Face Recognition Systems

This paper introduces a novel adversarial example generation method agai...

AdvHat: Real-world adversarial attack on ArcFace Face ID system

In this paper we propose a novel easily reproducible technique to attack...

Real-world attack on MTCNN face detection system

Recent studies proved that deep learning approaches achieve remarkable r...