Loading

Ddos Attack Detection and Prevention using Aodv Routing Mechanism and Ffbp Neural Network in a Manet
Jasmine Batra1, C. Rama Krishna2 

1Jasmine Batra, M.E, Department of Computer Science, NITTTR, Chandigarh.
2Dr. C Rama Krishna, Ph.D. from IIT Kharagpur, M. Tech. from CUSAT, Cochin B.Tech. from JNTU Govt. College of Engg., Anantapur

Manuscript received on 05 March 2019 | Revised Manuscript received on 12 March 2019 | Manuscript published on 30 July 2019 | PP: 4136-4142 | Volume-8 Issue-2, July 2019 | Retrieval Number: B3155078219/19©BEIESP | DOI: 10.35940/ijrte.B3155.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Security is considered as the most important feature in a Mobile Ad-hoc Network (MANET). There are different types of attacks which may affect the data transmission in MANET but Distributed Denial of Service (DDoS) attack is one of the complex and harsh worthy in a MANET. In the existing work, it has been found that the researchers have utilized Support Vector Machine (SVM) and fuzzy logic as a classification algorithm to identify the DoS attack in MANET. The problem with SVM and Fuzzy logic is that they are more complex and more time consuming mechanism to detect attackers. Also, in the existing work, Optimized Link State Routing (OLSR) routing protocol is used to find route and it is a searching mechanism which does not include the concept of trust routing table and hence the searching mechanism consumes more energy. To solve the mentioned problems, we are presenting a machine learning approach that is Feed Forward Back Propagation Neural Network (FFBPNN) as a classifier and Ad hoc On-Demand Distance Vector(AODV) routing protocol for route discovery to shield the network from Distributed Denial of Service (DDoS) attack. The MANET is trained using FFBPNN. Therefore, when malicious node appears in the network, the node is identified on the basis of the node properties like energy consumption and delay. The route is changed by discarding the malicious nodes from the route and hence the network is protected. The throughputs, PDR have been increased by 60.71%, 53.57% and delay has been reduced by 42.21%.
Index Terms: MANET, AODV, FFBPNN, DDoS, PDR, Throughput, Delay, Energy Consumption.

Scope of the Article: Computer Network