Artificial Neural Network Based Cryptography for Secure Operation of Ethio-Djibouti Railway using Wireless Sensor Networks
No Thumbnail Available
Date
2019-09
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Railway transportation is a reasonable choice to transport an enormous volume of passengers and cargos. But guaranteeing the safety and reliability of transport is the main issue. In this research reliability and security issues will be discussed along with types of attacks and measures to be taken. Unreliable communication which is a result of unreliable transfer, conflicts and latency and unattended operation which is due to exposure to physical attacks, remote management and lack of central management point is used to describe reliability.
Secure operation is a combined effect of data confidentiality, data integrity, data freshness, availability, self-organization, time synchronization, secure localization and authentication. The attacks against this security metrics includes: Denial of service attacks, the Sybil attack, traffic analysis attack, node replication attacks, attacks against privacy (i.e. this includes monitor and eavesdropping, traffic analysis and camouflage) and physical attacks.
There are some efficient and effective measures that are discussed briefly such as: measures against DoS attacks, secure broadcasting and multicasting. Encryption using Artificial Neural Network is used to communicate the nodes in a secure and reliable manner. 6 hidden layers are used to update the weight functions. And it is simulated using MATLAB simulation Software.
Description
Keywords
Artificial Neural Network, Wireless Sensor Networks, Ethio-Djibouti Railway, Cryptography