|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
With increasing applications in Internet of Things (IoT) increased the productivity of individuals and organisation, and further it simplified the daily activities of humans. These technologies are prone to attacks due to multiple attacks by the intruders in large-scale IT systems. Such attacks pose severe threats to the user in terms of their confidential data and privacy. Hence, a strong intrusion system is required to improve the detection ability in IoT networks. In this paper, we develop a classifier enabled with dense neural network (DenseNet) that classifies the input data from the given datasets. The steps of the classification contain a series of processing involving pre-processing and feature extraction, which boosts the process of classification. The simulation is conducted on IoT environment to test the efficacy of DenseNetsability to classify the threats. The simulation results show that the proposed method is efficient in improving the rate of classification than other existing deep learning architectures.
Keyword
Deep Neural Network, Threats, IoT Network, Intrusion Detection, Internet of Things
PDF Download (click here)
|
|
|
|
|