ANNIDS: Artificial Neural Network based Intrusion Detection System for Internet of Things
A. Arul Anitha1, L. Arockiam2
1A. Arul Anitha, Department of Computer Science, St. Joseph’s College (Autonomous), Tiruchirappalli-620002, Tamilnadu, India,
2Dr. L. Arockiam, Department of Computer Science, St. Joseph’s College (Autonomous), Tiruchirappalli-620002, Tamilnadu, India,
Manuscript received on 28 August 2019. | Revised Manuscript received on 02 September 2019. | Manuscript published on 30 September 2019. | PP: 2583-2588 | Volume-8 Issue-11, September 2019. | Retrieval Number: K18750981119/2019©BEIESP | DOI: 10.35940/ijitee.K1875.0981119
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: Internet of Things (IoT) makes everything in the real world to get connected. The resource constrained characteristics and the different types of technology and protocols tend to the IoT be more vulnerable than the conventional networks. Intrusion Detection System (IDS) is a tool which monitors analyzes and detects the abnormalities in the network activities. Machine Learning techniques are implemented with the Intrusion detection systems to enhance the performance of IDS. Various studies on IoT reveals that Artificial Neural Network (ANN) provides better accuracy and detection rate than other approaches. In this paper, an Artificial Neural Network based IDS (ANNIDS) technique based on Multilayer Perceptron (MLP) is proposed to detect the attacks initiated by the Destination Oriented Direct Acyclic Graph Information Solicitation (DIS) attack and Version attack in IoT environment. Contiki O.S/Cooja Simulator 3.0 is used for the IoT simulation.
Keywords: Artificial Neural Network, IDS, IoT, Multilayer Perceptron.
Scope of the Article: Internet of Things (IoT) & IoE & Edge Computing