Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation

TL;DR

This paper introduces a novel, practical physical adversarial attack on face recognition systems using LED illumination modulation, exploiting the rolling shutter effect to generate imperceptible luminance changes that fool detection and verification models with high success rates.

Contribution

The authors propose a new low-cost, inconspicuous physical attack method leveraging LED modulation and rolling shutter effect, addressing limitations of digital and existing physical attacks.

Findings

Achieves up to 100% success rate in dodging face verification.

Reaches over 97% success in denial-of-service attacks on face detection.

Demonstrates effectiveness against multiple face recognition models.

Abstract

Although face recognition starts to play an important role in our daily life, we need to pay attention that data-driven face recognition vision systems are vulnerable to adversarial attacks. However, the current two categories of adversarial attacks, namely digital attacks and physical attacks both have drawbacks, with the former ones impractical and the latter one conspicuous, high-computational and inexecutable. To address the issues, we propose a practical, executable, inconspicuous and low computational adversarial attack based on LED illumination modulation. To fool the systems, the proposed attack generates imperceptible luminance changes to human eyes through fast intensity modulation of scene LED illumination and uses the rolling shutter effect of CMOS image sensors in face recognition systems to implant luminance information perturbation to the captured face images. In summary,we present a denial-of-service (DoS) attack for face detection and a dodging attack for face verification. We also evaluate their effectiveness against well-known face detection models, Dlib, MTCNN and RetinaFace , and face verification models, Dlib, FaceNet,and ArcFace.The extensive experiments show that the success rates of DoS attacks against face detection models reach 97.67%, 100%, and 100%, respectively, and the success rates of dodging attacks against all face verification models reach 100%.