Design Novel CNN Architecture to Protect Personal Devices from Unauthorized Access Using Face Recognition

Salim S. K., Msallam M. M., Olewi H. I.

Nanotechnology Perceptions, vol.20, no.3, pp.82-93, 2024 (Scopus) identifier

  • Publication Type: Article / Article
  • Volume: 20 Issue: 3
  • Publication Date: 2024
  • Doi Number: 10.62441/nano-ntp.v20i3.7
  • Journal Name: Nanotechnology Perceptions
  • Journal Indexes: Scopus, PASCAL, INSPEC
  • Page Numbers: pp.82-93
  • Keywords: Biometric, Convolutional Neural Networks, Cyber security., Face recognition, Machine learning
  • Ankara University Affiliated: Yes

Abstract

With the advancement of technology and the development of the Internet of Things (IoT), the importance of protecting devices is becoming increasingly important to secure them from unauthorized access. The emergence of personal devices such as Personal Computers (PC) and smartphones increases the need for advanced security techniques because these devices contain important and personal information. Thus, technology companies tend to use biometrics to protect devices. This study proposes a novel Convolutional Neural Networks (CNN) architecture designed to use biometrics to protect personal devices from unauthorized access. Face image is one of the biometrics used to secure the device using the proposed CNN architecture. The device allows access to data if the proposed CNN architecture makes a high match rate. The proposed CNN architecture had trained on the AT&T standard database where it had high accuracy.