Redirigiendo al acceso original de articulo en 24 segundos...
Inicio  /  Future Internet  /  Vol: 13 Par: 9 (2021)  /  Artículo
ARTÍCULO
TITULO

A Study of Gender Bias in Face Presentation Attack and Its Mitigation

Norah Alshareef    
Xiaohong Yuan    
Kaushik Roy and Mustafa Atay    

Resumen

In biometric systems, the process of identifying or verifying people using facial data must be highly accurate to ensure a high level of security and credibility. Many researchers investigated the fairness of face recognition systems and reported demographic bias. However, there was not much study on face presentation attack detection technology (PAD) in terms of bias. This research sheds light on bias in face spoofing detection by implementing two phases. First, two CNN (convolutional neural network)-based presentation attack detection models, ResNet50 and VGG16 were used to evaluate the fairness of detecting imposer attacks on the basis of gender. In addition, different sizes of Spoof in the Wild (SiW) testing and training data were used in the first phase to study the effect of gender distribution on the models? performance. Second, the debiasing variational autoencoder (DB-VAE) (Amini, A., et al., Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure) was applied in combination with VGG16 to assess its ability to mitigate bias in presentation attack detection. Our experiments exposed minor gender bias in CNN-based presentation attack detection methods. In addition, it was proven that imbalance in training and testing data does not necessarily lead to gender bias in the model?s performance. Results proved that the DB-VAE approach (Amini, A., et al., Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure) succeeded in mitigating bias in detecting spoof faces.

 Artículos similares

       
 
James Dele Owolabi, Kunle Elizah Ogundipe, Babatunde Fatai Ogunbayo and Clinton Ohis Aigbavboa    
Increasing women?s representation in male-dominated professions has become an unending debate due to different gender barriers across various sectors. This study examined the barriers to female construction graduates? employment as construction faculty i... ver más
Revista: Buildings

 
Tiago P. Pagano, Rafael B. Loureiro, Fernanda V. N. Lisboa, Gustavo O. R. Cruz, Rodrigo M. Peixoto, Guilherme A. de Sousa Guimarães, Ewerton L. S. Oliveira, Ingrid Winkler and Erick G. Sperandio Nascimento    
The majority of current approaches for bias and fairness identification or mitigation in machine learning models are applications for a particular issue that fails to account for the connection between the application context and its associated sensitive... ver más

 
Bongjun Ji, Julian Kang, Chaehyeon Kim, Sojung Kim, Yooseob Song and Jaeheum Yeon    
In the Architecture, Engineering, and Construction (AEC) industry, virtual environments are being utilized to enhance communication among stakeholders and improve visual comprehension. However, stakeholders possess diverse personal characteristics which ... ver más
Revista: Buildings

 
Maren Wesselow    
Social capital is the basis of community-based action and constitutes an important resource for the poor in urban areas. However, social class, age, ethnicity and gender play an important role in shaping social capital outcomes. This article provides a l... ver más
Revista: Urban Science

 
Kushagra Sinha and Sanjay Gupta    
With the considerable growth in the information and communication technology (ICT), several smartphone-based mobility platforms have already sprung up and they have the potential of transforming the mobility ecosystem completely. However, there is close ... ver más
Revista: Urban Science