Paper Info
Title
Mobile network intrusion detection for IoT system based on transfer learning algorithm
Abstract
The open deployment environment and limited resources of the Internet of things (IoT) make it vulnerable to malicious attacks, while the traditional intrusion detection system is difficult to meet the heterogeneous and distributed features of the Internet of things. The security and privacy protection of IoT is directly related to the practical application of IoT. In this paper, We analyze the characteristics of networking security and security problems, and discuss the system framework of Internet security and some key security technologies, including key management, authentication and access control, routing security, privacy protection, intrusion detection and fault tolerance and intrusion etc. This paper introduces the current problems of IoT in network security, and points out the necessity of intrusion detection. Several kinds of intrusion detection technologies are discussed, and its application on IoT architecture is analyzed. We compare the application of different intrusion detection technologies, and make a prospect of the next phase of research. Using data mining and machine learning methods to study network intrusion technology has become a hot issue. A single class feature or a detection model is very difficult to improve the detection rate of network intrusion detection. The performance of the proposed model is validated through the public databases.
Year
DOI
Venue
2019
10.1007/s10586-018-1847-2
Cluster Computing
Keywords
DocType
Volume
Intrusion detection, Internet of things, Information security, Pop learning
Journal
22
Issue
ISSN
Citations 
Supplement
1573-7543
10
PageRank 
References 
Authors
0.51
6
5
Name
Order
Citations
PageRank
Lianbing Deng1426.33
Daming Li2185.72
Xiang Yao3203.49
David D. Cox4100974.53
Haoxiang Wang527615.25