Performance Evaluation of Deep Learning Models for Intrusion Detection in IoT Devices

• Valdir Carvalho UFRPE
• Ewerton Queiroz UFRPE
• Júlio Mendonça IFAL
• Gustavo Callou UFRPE
• Ermeson Andrade UFRPE

DOI: https://doi.org/10.5753/wperformance.2021.15718

Abstract

With the high growth in the number of devices connected to the Internet of Things (IoT), digital security has become one of the main points to be addressed. Many of these devices use outdated technologies, which create vulnerabilities that can be exploited by criminals. New security techniques emerge through the use of Artificial Intelligence models to improve old implementations, such as Deep Learning-based intrusion detection systems to identify cyber attacks. However, the existing works do not evaluate the impacts of these systems on the performance of environments with computational restrictions, such as IoT devices. Thus, this work aims to evaluate the performance of two intrusion detection models based on Deep Learning developed for IoT environments. The results reveal that different models have different impacts on the performance of IoT devices. Additionally, the model that receives a greater volume of attacks, and has greater accuracy, consumes more resources, which can be quite problematic for IoT environments.

Keywords: Internet of Things, Deep Learning, Intrusion Detection System, Performance evaluation

References

Aloqaily, M., Otoum, S., Al Ridhawi, I., and Jararweh, Y. (2019). An intrusion detection system for connected vehicles in smart cities. Ad Hoc Networks, 90:101842.

Ashton, K. (1999). An introduction to the internet of things (iot). RFID Journal.

Atzori, L., Iera, A., and Morabito, G. (2010). The internet of things: A survey. Computer networks, 54(15):2787–2805.

Chen, M., Mao, S., and Liu, Y. (2014). Big data: A survey. Mobile networks and applications, 19(2):171–209.

de Araujo, R. B. (2003). Computação ubı́qua: Princı́pios, tecnologias e desafios. In XXI Simpósio Brasileiro de Redes de Computadores, volume 8, pages 11–13.

Din, I. U., Guizani, M., Rodrigues, J. J., Hassan, S., and Korotaev, V. V. (2019). Machine learning in the internet of things: Designed techniques for smart cities. Future Generation Computer Systems, 100:826–843.

Dürr, O., Pauchard, Y., Browarnik, D., Axthelm, R., and Loeser, M. (2015). Deep learning on a raspberry pi for real time face recognition. In Eurographics (Posters), pages 11–12

Eremia, M., Toma, L., and Sanduleac, M. (2017). The smart city concept in the 21st century. Procedia Engineering, 181:12–19.

Farahnakian, F. and Heikkonen, J. (2018). A deep auto-encoder based approach for intrusion detection system. In 2018 20th International Conference on Advanced Communication Technology (ICACT), pages 178–183. IEEE.

Ge, M., Fu, X., Syed, N., Baig, Z., Teo, G., and Robles-Kelly, A. (2019). Deep learning-based intrusion detection for iot networks. In 2019 IEEE 24th Pacific Rim International Symposium on Dependable Computing (PRDC), pages 256–25609. IEEE.

Gómez, A., Cuiñas, D., Catalá, P., Xin, L., Li, W., Conway, S., and Lack, D. (2015). Use of single board computers as smart sensors in the manufacturing industry. Procedia engineering, 132:153–159.

Koroniotis, N., Moustafa, N., Sitnikova, E., and Turnbull, B. (2019). Towards the development of realistic botnet dataset in the internet of things for network forensic analytics: Bot-iot dataset. Future Generation Computer Systems, 100:779–796.

LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.

Liao, H.-J., Lin, C.-H. R., Lin, Y.-C., and Tung, K.-Y. (2013). Intrusion detection system: A comprehensive review. Journal of Network and Computer Applications, 36(1):16–24

Lunt, T. F. (1993). A survey of intrusion detection techniques. Computers & Security, 12(4):405–418.

Martinez, F. J., Toh, C. K., Cano, J.-C., Calafate, C. T., and Manzoni, P. (2011). A survey and comparative study of simulators for vehicular ad hoc networks (vanets). Wireless Communications and Mobile Computing, 11(7):813–828.

Miraz, M. H., Ali, M., Excell, P. S., and Picking, R. (2015). A review on internet of things (iot), internet of everything (ioe) and internet of nano things (iont). In 2015 Internet Technologies and Applications (ITA), pages 219–224. IEEE.

Morabito, R. (2017). Virtualization on internet of things edge devices with container technologies: a performance evaluation. IEEE Access, 5:8835–8850.

Nurse, J. R., Creese, S., and De Roure, D. (2017). Security risk assessment in internet of things systems. IT professional, 19(5):20–26.

Pannu, A. (2015). Artificial intelligence and its application in different areas. Artificial Intelligence, 4(10):79–84.

Quincozes, S. E., Kazienko, J. F., and Copetti, A. (2018). Avaliação de conjuntos de atributos para a detecção de ataques de personificação na internet das coisas. In Anais Estendidos do VIII Simpósio Brasileiro de Engenharia de Sistemas Computacionais. SBC.

Tama, B. A. and Rhee, K.-H. (2017). Performance evaluation of intrusion detection system using classifier ensembles. International Journal of Internet Protocol Technology, 10(1):22–29

Thamilarasu, G. and Chawla, S. (2019). Towards deep-learning-driven intrusion detection for the internet of things. Sensors, 19(9):1977.

Vinayakumar, R., Alazab, M., Soman, K., Poornachandran, P., Al-Nemrat, A., and Ven katraman, S. (2019). Deep learning approach for intelligent intrusion detection system. IEEE Access, 7:41525–41550.

Xu, P., Shi, S., and Chu, X. (2017). Performance evaluation of deep learning tools in docker containers. In 2017 3rd International Conference on Big Data Computing and Communications (BIGCOM), pages 395–403. IEEE.