|
|
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
Network requirement increases in different sector for various situation for ease of human like, research, etc. Dependency of machines are shift towards cloud but this brings many challenges of security. Out of many security issue this paper monitors node malicious activity for trust evaluation. In order to reduce false alarm social trust evaluation function Jaccard trust was used. Further node machines status were used to learn its activity as a feature. Obtained Jaccard trust and feature set used for training the convolutional neural network. Experiment was done on different number of nodes and attack environment. Trained deep learning model has efficiently detect the malicious node in the network. Result shows that proposed model has increased the true alarm precision, recall, accuracy comparing parameters as compared to existing models.
Keyword
Cloud computing, Trust Coefficient, Page Rank, Classification, Neural Network.
PDF Download (click here)
|
|
|
|
|