Deep Learning Modalities for Biometric Alteration Detection in 5G Networks-Based Secure Smart Cities

Abstract

Smart cities and their applications have become attractive research fields birthing numerous technologies. Fifth generation (5G) networks are important components of smart cities where intelligent access control is deployed for identity authentication, online banking, and cyber security. The prevalence of biometrics, such as fingerprints, in authentication and identification make the need to safeguard them important across different areas of smart applications. Our study proposes a system to detect alterations to biometric modalities to discriminate pristine, adulterated, and fake biometrics in 5G-based smart cities. Specifically, we utilise deep learning models based on convolutional neural networks (CNN) and a hybrid model that combines CNN with convolutional long-short term memory (ConvLSTM) to compute a threetier probability that a biometric had been tempered. Simulation-based experiments reported indicate that the alteration detection accuracy matches those recorded in advanced methods with superior performance in terms of detecting central rotation alteration to fingerprints. This makes the proposed system a veritable solution for different biometric authentication applications in smart cities.

RETRACTED ARTICLE: A decision-making algorithm combining the aspect-based sentiment analysis and intuitionistic fuzzy-VIKOR for online hotel reservation

“…Besides, Combining the temporal characteristics of the decision, scholars such as Tao et al, ( 2021 ), Chen et al, ( 2021 ), Gao et al, ( 2020a , b , c ) and Cheng et al, ( 2020 ) introduced a time weight vector to establish a polymorphic intuitionistic fuzzy decision model based on time dimension. Recently, the existing studies combined the intuitionistic fuzzy sets with various multi-attribute decision making methods to obtain decision sorting strategies (Feng et al, 2020 ; Gao et al, 2020a , b , c ; Krishankumar & Ravichandran, 2020 ; Sedik et al, 2021 ; Zeng et al, 2020 ). Besides, some authors integrated the artificial intelligence, data mining technology with the intuitionistic fuzzy sets to present the data-driven intuitionistic fuzzy decision making paradigm (Atanassov, 2015 ; Çalı & Balaman, 2019 ; Liu et al, 2017a , b ; Nguyen et al, 2018 ; Rasty et al, 2020 ; Zhang et al, 2020 ).…”

Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images

“…Wuet al, 2019 , Ozturket al, 2020 , Ardakaniet al, 2020 , Jainet al, 2020 , Marqueset al, 2020 , Ucar, Ferhat, and Deniz Korkmaz. “COVIDiagnosis-Net: Deep Bayes-SqueezeNet based Diagnostic of the Coronavirus Disease, 2019 , Zabirulet al, 2020 , , 2020 , Altan and Karasu, 2020 , , 2020 , Daset al, 2020 , , 2020 , Ohet al, 2020 , Hanet al, 2020 , , 2020 , , 2020 , Ardakaniet al, 2020 , , 2020 , Civit-Masotet al, 2020 , Alghamdiet al, 2020 , Amraniet al, 2018 , Hammadet al, 2018 , Abou-Nassaret al, 2020 , Wanget al, 2014 , Sediket al, 2020 , Ahmadet al, 2021 , Sedik, 2021 , Siamet al, 2021 , , 2022 .…”

A new design of multimedia big data retrieval enabled by deep feature learning and Adaptive Semantic Similarity Function

“…In 2018, Sedik et al . [ 32 ] have implemented a deep learning model based on CNN and a hybrid model that combined CNN with ConvLSTM to compute a three-tier probability that a biometric has been tempered. Simulation-based experiments have indicated that the alteration detection accuracy matches those recorded in advanced methods with superior performance in terms of detecting central rotation alteration to fingerprints.…”

“…Here, the term denotes the convolutional filter concerning with m th feature map, represents the non-linear activation function, and the 2D convolutional operator is denoted as ‘ ’ that is responsible for extracting the non-linear features from the input . The pooling layer of CNN [ 31 , 32 ] is used for minimizing the spatial resolution of the feature maps to get the spatial invariance for input translations and distortions. Most of the model employs average pooling aggregation layers for propagating the average of entire input values.…”