Deep Composite Face Image Attacks: Generation, Vulnerability and Detection

11/20/2022
by   Jag Mohan Singh, et al.
0

Face manipulation attacks have drawn the attention of biometric researchers because of their vulnerability to Face Recognition Systems (FRS). This paper proposes a novel scheme to generate Composite Face Image Attacks (CFIA) based on the Generative Adversarial Networks (GANs). Given the face images from contributory data subjects, the proposed CFIA method will independently generate the segmented facial attributes, then blend them using transparent masks to generate the CFIA samples. The primary motivation for CFIA is to utilize deep learning to generate facial attribute-based composite attacks, which has been explored relatively less in the current literature. We generate 14 different combinations of facial attributes resulting in 14 unique CFIA samples for each pair of contributory data subjects. Extensive experiments are carried out on our newly generated CFIA dataset consisting of 1000 unique identities with 2000 bona fide samples and 14000 CFIA samples, thus resulting in an overall 16000 face image samples. We perform a sequence of experiments to benchmark the vulnerability of CFIA to automatic FRS (based on both deep-learning and commercial-off-the-shelf (COTS). We introduced a new metric named Generalized Morphing Attack Potential (GMAP) to benchmark the vulnerability effectively. Additional experiments are performed to compute the perceptual quality of the generated CFIA samples. Finally, the CFIA detection performance is presented using three different Face Morphing Attack Detection (MAD) algorithms. The proposed CFIA method indicates good perceptual quality based on the obtained results. Further, FRS is vulnerable to CFIA (much higher than SOTA), making it difficult to detect by human observers and automatic detection algorithms. Lastly, we performed experiments to detect the CFIA samples using three different detection techniques automatically.

READ FULL TEXT

page 3

page 4

page 5

page 6

page 7

page 10

page 11

research
07/06/2020

On the Influence of Ageing on Face Morph Attacks: Vulnerability and Detection

Face morphing attacks have raised critical concerns as they demonstrate ...
research
01/10/2022

3D Face Morphing Attacks: Generation, Vulnerability and Detection

Face Recognition systems (FRS) have been found vulnerable to morphing at...
research
07/07/2020

Can GAN Generated Morphs Threaten Face Recognition Systems Equally as Landmark Based Morphs? – Vulnerability and Detection

The primary objective of face morphing is to combine face images of diff...
research
09/03/2020

MIPGAN – Generating Robust and High Quality Morph Attacks Using Identity Prior Driven GAN

Face morphing attacks target to circumvent Face Recognition Systems (FRS...
research
03/24/2023

Vulnerability of Face Morphing Attacks: A Case Study on Lookalike and Identical Twins

Face morphing attacks have emerged as a potential threat, particularly i...
research
04/07/2023

Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study

Face morphing attack detection is emerging as an increasingly challengin...
research
01/26/2019

On Detecting GANs and Retouching based Synthetic Alterations

Digitally retouching images has become a popular trend, with people post...

Please sign up or login with your details

Forgot password? Click here to reset