Research Article
BibTex RIS Cite

The Impact of Device Type Number on IoT Device Classification

Year 2024, Volume: 7 Issue: 3, 488 - 494, 15.05.2024
https://doi.org/10.34248/bsengineering.1353999

Abstract

Today, connected systems are widely used with the recent developments in technology. The internet- connected devices create data traffic when communicating with each other. These data may contain extremely confidential information. Observers can obtain confidential information from the traffic when the security of this traffic cannot be adequately ensured. This confidential information can be personal information as well as information about the type of device used by the person. Even if the traffic is en- crypted, the attacker can obtain information about these devices using machine learning algorithms. This paper presents the importance of the effect of device type number for the classification of IoT devices. Therefore, inference attacks on privacy with machine learning algorithms, attacks on machine learning models, and the padding method that is commonly used against such attacks are presented. Moreover, experiments are carried out by using the dataset of the traffic generated by the Internet of Things (IoT) devices. For this purpose, Random Forest, Decision Tree, and k-Nearest Neighbors (k-NN) classification algorithms are compared and the accuracy rate changes according to the number of devices are presented. According to the results, the Random Forest and Decision Tree algorithms found to be more effective than the k-NN algorithm.

Supporting Institution

Ege University Scientific Research Projects Committee

Project Number

FM-HZP-2023-29550

References

  • Abdulkareem NM, Abdulazeez AM. 2021. Machine learning classification based on Random Forest Algorithm: A review. IJSB, 5(2): 128-142.
  • Aksoy A, Gunes MH. 2019. Automated IoT device identification using network traffic. In: ICC 2019 - IEEE International Conference on Communications, 20-24 May, Shanghai, China, pp: 1-7.

The Impact of Device Type Number on IoT Device Classification

Year 2024, Volume: 7 Issue: 3, 488 - 494, 15.05.2024
https://doi.org/10.34248/bsengineering.1353999

Abstract

Günümüzde, teknolojinin son gelişmeleri ile birlikte bağlantılı sistemler yaygın bir şekilde kullanılmaktadır. İnternet bağlantılı cihazlar birbirleriyle iletişim kurduğunda veri trafiği oluştururlar. Bu veriler son derece gizli bilgiler içerebilir. Güvenliği yeterince sağlanamadığında, gözlemciler bu trafiğin içinden gizli bilgileri elde edebilirler. Bu gizli bilgiler, kişisel bilgilerin yanı sıra kişinin kullandığı cihaz türü hakkında bilgiler içerebilir. Trafiğin şifrelenmiş olması durumunda bile, saldırganlar bu cihazlar hakkında bilgi elde edebilirler, bu da makine öğrenme algoritmalarını kullanarak mümkün olur. Bu makale, Nesnelerin İnterneti (IoT) cihazlarını sınıflandırmak için cihaz türü sayısının etkisini vurgulamaktadır. Bu nedenle, makine öğrenme algoritmaları ile gizlilik üzerine çıkarım saldırıları, makine öğrenme modellerine yönelik saldırılar ve genellikle bu tür saldırılara karşı kullanılan dolgu yöntemi sunulmaktadır. Ayrıca, IoT cihazlarının ürettiği trafiği kullanarak deneyler gerçekleştirilmektedir. Bu amaçla, Random Forest, Decision Tree ve k-NN sınıflandırma algoritmaları karşılaştırılmakta ve cihaz sayısına göre doğruluk oranındaki değişiklikler sunulmaktadır. Sonuçlara göre, Random Forest ve Decision Treeı algoritmalarının k-NN algoritmasından daha etkili olduğu bulunmuştur.

Project Number

FM-HZP-2023-29550

References

  • Abdulkareem NM, Abdulazeez AM. 2021. Machine learning classification based on Random Forest Algorithm: A review. IJSB, 5(2): 128-142.
  • Aksoy A, Gunes MH. 2019. Automated IoT device identification using network traffic. In: ICC 2019 - IEEE International Conference on Communications, 20-24 May, Shanghai, China, pp: 1-7.
There are 2 citations in total.

Details

Primary Language English
Subjects Information Security Management, Information Systems (Other)
Journal Section Research Articles
Authors

Ahmet Emre Ergün 0000-0002-3025-5640

Özgü Can 0000-0002-8064-2905

Project Number FM-HZP-2023-29550
Publication Date May 15, 2024
Submission Date September 1, 2023
Acceptance Date April 26, 2024
Published in Issue Year 2024 Volume: 7 Issue: 3

Cite

APA Ergün, A. E., & Can, Ö. (2024). The Impact of Device Type Number on IoT Device Classification. Black Sea Journal of Engineering and Science, 7(3), 488-494. https://doi.org/10.34248/bsengineering.1353999
AMA Ergün AE, Can Ö. The Impact of Device Type Number on IoT Device Classification. BSJ Eng. Sci. May 2024;7(3):488-494. doi:10.34248/bsengineering.1353999
Chicago Ergün, Ahmet Emre, and Özgü Can. “The Impact of Device Type Number on IoT Device Classification”. Black Sea Journal of Engineering and Science 7, no. 3 (May 2024): 488-94. https://doi.org/10.34248/bsengineering.1353999.
EndNote Ergün AE, Can Ö (May 1, 2024) The Impact of Device Type Number on IoT Device Classification. Black Sea Journal of Engineering and Science 7 3 488–494.
IEEE A. E. Ergün and Ö. Can, “The Impact of Device Type Number on IoT Device Classification”, BSJ Eng. Sci., vol. 7, no. 3, pp. 488–494, 2024, doi: 10.34248/bsengineering.1353999.
ISNAD Ergün, Ahmet Emre - Can, Özgü. “The Impact of Device Type Number on IoT Device Classification”. Black Sea Journal of Engineering and Science 7/3 (May 2024), 488-494. https://doi.org/10.34248/bsengineering.1353999.
JAMA Ergün AE, Can Ö. The Impact of Device Type Number on IoT Device Classification. BSJ Eng. Sci. 2024;7:488–494.
MLA Ergün, Ahmet Emre and Özgü Can. “The Impact of Device Type Number on IoT Device Classification”. Black Sea Journal of Engineering and Science, vol. 7, no. 3, 2024, pp. 488-94, doi:10.34248/bsengineering.1353999.
Vancouver Ergün AE, Can Ö. The Impact of Device Type Number on IoT Device Classification. BSJ Eng. Sci. 2024;7(3):488-94.

                                                24890