Injection Attack Detection on Internet of Things Device with Machine Learning Method

Mara Muda Pohan(1*), Benfano Soewito(2),

(1) Bina Nusantara University, Jakarta, Indonesia
(2) Bina Nusantara University, Jakarta, Indonesia
(*) Corresponding Author

Abstract


The Internet of Things (IoT) Industry is growing rapidly, security surrounding this Industry has to be upgraded. This study analyzes which machine learning performs the best in detecting Injection Attacks in IoT devices. The proposed machine learning methods includes Catboost, Decision Tree, Support Vector Machine (SVM), and Multilayer Perceptron (MLP). This study uses Edge-IIoTset dataset. The traffic data obtained in this dataset comes from 13 different types of IoT devices which contains 10 files with normal traffic and 14 files of attack traffics. This study takes normal traffic and injection attacks traffic from Edge-IIoTset. Results shows that Catboost machine learning model performs the best in terms of performance score with 0.95599 score in Accuracy, Precision, F1-Score, and recall score where as Decision Tree model performs the fastest with 0.09 seconds of runtime and achieving 0.93 score in the performance.

Full Text:

PDF

References


Acharya, S. (2022, March 17). Why IoT Security is Important for Today’s Networks? SECTRIO. https://sectrio.com/why-iot-security-is-important-for-todays-networks/.

Statista. (2022a, May). Number of Internet of Things (IoT) connected devices worldwide from 2019 to 2030. Statista. https://www.statista.com/statistics/1183457/iot-connected-devices-worldwide/.

Weinberg, A. (2021, October 24). Top 4 Challenges in IoT Data Collection and Management. FirstPoint. https://www.firstpoint-mg.com/blog/top-4-challenges-in-iotdata-collection-and-management/.

Tawalbeh, L., Muheidat, F., Tawalbeh, M., & Quwaider, M. (2020). IoT privacy and security: Challenges and solutions. Applied Sciences (Switzerland), 10(12). https://doi.org/10.3390/APP10124102.

Conti, M., Dehghantanha, A., Franke, K., & Watson, S. (2018). Internet of Things security and forensics: Challenges and opportunities. In Future Generation Computer Systems (Vol. 78, pp. 544–546). Elsevier B.V. https://doi.org/10.1016/j.future.2017.07.060.

Ferrag, M. A., Friha, O., Hamouda, D., Maglaras, L., & Janicke, H. (2022). Edge-IIoTset: A New Comprehensive Realistic Cyber Security Dataset of IoT and IIoT Applications for Centralized and Federated Learning. IEEE Access, 10, 40281–40306. https://doi.org/10.1109/ACCESS.2022.3165809.

Kidd, I. (2021, September 30). The Shocking DDoS Attack Statistics That Prove You Need Protection. Info Security Magazine. https://www.infosecuritymagazine.com/blogs/ddos-attacks-stats-protection/.

Warburton, D. (2021, May 7). DDoS Attack Trends for 2020. F5 Application Threat Intelligence. https://www.f5.com/labs/articles/threat-intelligence/ddos-attack-trendsfor-2020.

Gaber, T., El-Ghamry, A., & Hassanien, A. E. (2022). Injection attack detection using machine learning for smart IoT applications. Physical Communication, 52. https://doi.org/10.1016/j.phycom.2022.101685.

Danardono, E. (2021). Detection of Distributed Denial of Service Attacks from Internet of Things Devices using SVM and NN-MLP methods [Thesis, Bina Nusantara]. http://library.binus.ac.id/Collections/ethesis_detail/RS2-KG-MTI-2021-0011.

Zhou, F., Pan, H., Gao, Z., Huang, X., Qian, G., Zhu, Y., & Xiao, F. (2021). Fire Prediction Based on CatBoost Algorithm. Mathematical Problems in Engineering, 2021. https://doi.org/10.1155/2021/1929137.

Nugroho, K. S. (2019, October 13). Confusion Matrix for Model Evaluation on Supervised Learning. Medium. https://ksnugroho.medium.com/confusion-matrixfor-evaluation-model-pada-unsupervised-machine-learning-bc4b1ae9ae3f.

Businesswire. (2019). The Growth in Connected IoT Devices is Expected to Generate 79.4ZB of Data in 2025, According to a New IDC Forecast. Businesswire. https://www.businesswire.com/news/home/20190618005012/en/The-Growth-inConnected-IoT-Devices-is-Expected-to-Generate-79.4ZB-of-Data-in-2025-Accordingto-a-New-IDC-Forecast.

Hussain, F., Hussain, R., Hassan, S. A., & Hossain, E. (2019). Machine Learning in IoT Security: Current Solutions and Future Challenges. http://arxiv.org/abs/1904.05735.

Garcia-Alfaro, J., & Navarro-Arribas, G. (2009). A Survey on Cross-Site Scripting Attacks. http://arxiv.org/abs/0905.4850.




DOI: http://dx.doi.org/10.30645/jurasik.v8i1.556

DOI (PDF): http://dx.doi.org/10.30645/jurasik.v8i1.556.g534

Refbacks

  • There are currently no refbacks.



JURASIK (Jurnal Riset Sistem Informasi dan Teknik Informatika)
Published Papers Indexed/Abstracted By:

Jumlah Kunjungan : View My Stats