Khan, W A, Saleem, K, Faiz, T, Malik, J A, Khan, M S and Sadaf, Z (2022) Predicting Distributed Network Malicious Data Packets in Smart City using Deep Learning. In: 2022 International Conference on Business Analytics for Technology and Security (ICBATS), 16-17 Feb. 2022, Dubai, United Arab Emirates.
Full text not available from this repository. (Request a copy)Abstract
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.
Affiliation: | Skyline University College |
---|---|
SUC Author(s): | Faiz, T |
All Author(s): | Khan, W A, Saleem, K, Faiz, T, Malik, J A, Khan, M S and Sadaf, Z |
Item Type: | Conference or Workshop Item (Paper) |
Uncontrolled Keywords: | Smart city, DENN, Deep learning, Internet of Things, Malicious Attacks, DDoS, DoS |
Subjects: | B Information Technology > BR Deep Learning |
Divisions: | Skyline University College > School of IT |
Depositing User: | Mr Veeramani Rasu |
Date Deposited: | 25 May 2022 14:32 |
Last Modified: | 25 May 2022 14:32 |
URI: | https://research.skylineuniversity.ac.ae/id/eprint/237 |
Publisher URL: | https://doi.org/10.1109/ICBATS54253.2022.9759078 |
Publisher OA policy: | |
Related URLs: |
Actions (login required)
Statistics for this ePrint Item |