Predicting Distributed Network Malicious Data Packets in Smart City using Deep Learning

Smart city completely employs the new expertise in the development of built-up informatization to enhance the whole city management and service. Smart city collects wide range of information from people and monitor their social activities. However, this arise privacy and security issue in smart city...

Full description

Saved in:
Bibliographic Details
Published in2022 International Conference on Business Analytics for Technology and Security (ICBATS) pp. 1 - 8
Main Authors Khan, Wasim Ahmad, Saleem, Komal, Faiz, Tauqeer, Malik, Javaid Ahmad, Khan, Muhammad Saeed, Sadaf, Zawaria
Format Conference Proceeding
LanguageEnglish
Published IEEE 16.02.2022
Subjects
DDoS
Deep learning
DENN
Distributed databases
DoS
Internet of Things
Malicious Attacks
Neural networks
Privacy
Safety
Security
Smart cities
Smart city
Support vector machines
Online AccessGet full text

Cover

More Information
Summary:Smart city completely employs the new expertise in the development of built-up informatization to enhance the whole city management and service. Smart city collects wide range of information from people and monitor their social activities. However, this arise privacy and security issue in smart city, which is a prevalent concern. Potential threat to privacy and confidential data leads to a myriad of concerns in today's world, particularly encircling smart city accesses. Previously various methods were used such as SVM, Logistic Regression, Naïve Bayes and more, using large datasets their limitations included lack of accuracy increasing the risk. To tackle the harmful packets from multiple virtual sources an optimal solution of Deep Extreme Neural Network (DENN) expert system is rendered and presented using a dataset of requests received by smart city. Accuracy of 92% is attained. In addition, ample medians of attacks are discussed that can be prevented using the same safety barrier.
DOI:10.1109/ICBATS54253.2022.9759078