Enhancement Trust Management in IoT to Detect ON-OFF Attacks with Cooja

Öz

In IoT ecosystems, the interaction of devices with each other creates a perfect environment but there are heterogeneous nodes that will supply a variety of services. In the intelligent environment, devices with various processing capacities may operate together and communicate transparently with one other and with users. These IoT gadgets are frequently exposed to the public and interact over wireless channels, making them vulnerable to malicious attacks. ON-OFF attacks (OOAs) are regarded as one of the IoT's trust threats. In these attacks, the malicious nodes alternate between behaving well and behaving badly, jeopardizing the network if they stay trusted nodes. In this paper, we introduce a model to enhance trust management in IoT to detect (OOAs) with the help of Artificial Neural Networks (ANN) to analyze the statuses (ON-OFF) and radio messages for each node which in turn assesses the resource trust automatically in IoT. We implemented our experiment by using Contiki Operating System (OS) and analyzed the data with Microsoft machine learning studio (MMLS) to display the results.

Anahtar Kelimeler

• Trust management
• IoT
• ON-OFF attacks
• Artificial Neural Networks
• Security
• Contiki OS

Kaynakça

1. [1] J. Henrique, “Mitigating On-Off attacks in the internet of things,” Inter. J. Dis. Sensor Networks, pp.1-8, DOI.10.1155/2015/859731, November 2015.
2. [2] A.V., P. Zhang, “Trust management for internet of things,” J. Net. Comp., pp.120–134, Appl. (42), 2014.
3. [3] Ray, S. K., Gutierrez, Airehrour, “Secure routing for the internet of things,” A survey. J. Net. Computer App., 66,198-213, 2016.
4. [4] R. Giraud, L. Atzori, M. N., “Trustworthiness management in the social internet of things,” IEEE Transl. Data Manage, 26 , pp. 1253–1266, May 2014.
5. [5] Y. Saied, D. Zegh., M. Laurent, A. Oli., “Trust management system design for the internet of things,” context-aware and multi-service appro., 39, pp. 351–365, 2013.
6. [6] A. Shenfield, D. Day, A. Ayesh, “Intelligent IDS using ANN,” ICT Express,pp.95.99,DOI:https://doi.org/10.1016/j.icte.2018.04.003,2018
7. [7] Abderrahim, & Elhedhili, “Trust management system mitigating On-Off attacks and dishonest recommendations for the Internet of Things,” DTMS-IoT, 2016.
8. [8] F. Bao, I.R. Chen, J. Guo, “Adaptive and survivable trust management for the community of interest-based internet of things systems,”11th Inter.Symp. on Auto. Decent.Sys., Mexico,2013.

9. [9] C. Mendoza, J. Mendoza, “mitigating on-off attacks in the internet of things using a distributed trust management scheme,” Inter. J. Dis. Sens. Net., Article 859731(11), 2015.
10. [10] D. Chen, G. Chang, D. Sun, X. Wang, “Trust management model based on a fuzzy reputation for the IoT,” TRM-IoT, Comput. Sci. Inf. Syst., pp.1207–1228, April 2011.
11. [11] W. Khreich, B. Khosravifar, A. Hamou-Lhadj, and C. Delhi, “An anomaly detection system based on variable N-gram features and one-class SVM,” Info. and Sof. Techno., vol. 91, pp. 186–197, 2017.
12. [12] K.Costa, J. Papa, C.Lisboa, “Survey on machine learning-based intrusion detection approaches,” IoT ,Compu. Net., PII: S1389-1286(18)308739, DOI:https://doi.org/,10.1016/j.comnet.2019.01.023, 2019.
13. [13] M. Apte,S. Kelkar, A. Dorge ,S. Deshpande. Bomble ,A. Dhamankar, “Gateway based Trust Management System for Internet of Things,” ISSN: 2237-0722, Vol. 11 No. 4 (2021), August 2021.
14. [14] Contiki Operating System for the Internet of Things, Online Available: HTTP:// www.contiki-os.org/.
15. [15] Azure Microsoft for ML, Online Available: https://studio.azureml.net/.