سیستم تشخیص نفوذ مبتنی بر یادگیری عمیق و الگوریتم‌های فرا ابتکاری برای اینترنت اشیاء

نوع مقاله : مقاله کامپیوتر

نویسندگان

1 دانش آموخته کارشناسی ارشد مهندسی معماری کامپیوتر، گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشگاه رازی، ایران

2 دانشیار گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشگاه رازی، ایران

چکیده

امروزه به خاطر فواید قابل ملاحظه‌ی اینترنت اشیاء (IoT) در حوزه‌های مختلف از قبیل خانه‌های هوشمند، صنایع، خودروها، کشاورزی و ... کاربرد آن بسیار گسترش یافته است. با توجه به این مطلب، امنیت این شبکه‌ها روز به روز مورد توجه بیشتری قرار می‌گیرد. یکی از روش‌های تأمین امنیت در شبکه‌ها و همینطور شبکه‌ی اینترنت اشیاء، سیستم‌های تشخیص نفوذ می‌باشد. سیستم‌های تشخیص نفوذ سنتی کارایی مناسبی برای استفاده در شبکه‌ی اینترنت اشیاء ندارند، لذا استفاده از روش‌های جدید مورد نیاز است. یکی از این روش‌ها، سیستم‌های تشخیص نفوذ مبتنی بر یادگیری ماشین و یادگیری عمیق هستند که در این حوزه مورد توجه قرار گرفته‌اند. در یادگیری ماشین و یادگیری عمیق، شبکه‌ی عصبی برای تشخیص الگوهای حمله آموزش داده می‌شوند. پارامترهای مهمی برای تنظیم شبکه‌ی یادگیری ماشین وجود دارند که انتخاب مقدار مناسب برای این پارامترها تأثیر فراوانی در دقت سیستم دارد. در این پژوهش، روشی ارائه شده است که با استفاده از الگوریتم‌های فراابتکاری نظیر الگوریتم ژنتیک، بهینه‌سازی ازدحام ذرات، کلونی زنبور عسل مصنوعی و گرگ خاکستری، ابرپارامترهای بهینه برای شبکه‌ی یادگیری عمیق را یافته و سیستم تشخیص نفوذی براساس این ابرپارامترها ایجاد می‌شود تا تشخیص نفوذ در شبکه‌ی اینترنت اشیاء انجام گردد. این روش با استفاده از کتابخانه‌های Tensorflow و keras پیاده‌سازی شده و روی مجموعه داده‌های  KDDCup99، UNSW-NB15  و Bot-IoT  آزمایش شده است. نتایج نشان داده است که روش پیشنهادی با دقت بالای 99.6% می‌تواند حملات را تشخیص دهد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

An Intrusion Detection System Based on Deep Learning and Metaheuristic Algorithm for IOT

نویسندگان [English]

  • Bahman Sanjabi 1
  • Mahmood Ahmadi 2
1 Master's degree in Computer Architecture Engineering, Department of Computer Engineering and Information Technology, Razi University, Iran
2 Associate Professor, Department of Computer Engineering and Information Technology, Razi University, Iran
چکیده [English]

oday, due to the considerable benefits of the Internet of Things (IoT) in various fields such as smart homes, industry, cars, agriculture, etc., its application is very widespread. Due to this, the security of these networks is receiving more and more attention. One of the methods of providing security in networks as well as IoT network is intrusion detection systems. Traditional intrusion detection systems are not very efficient for use in the Internet of Things, so the use of new methods is required. One of these methods is intrusion detection systems based on machine learning and deep learning that have been considered in this area. They are trained in machine learning and deep neural network learning to detect attack patterns. There are important parameters for setting up a machine learning network, and choosing the right value for these parameters has a great impact on system accuracy. In this paper, a method is presented that uses meta-heuristic algorithms such as genetic algorithm, particle swarm optimization, artificial bee colony and gray wolf to find the optimal hyperparameters for the deep learning network and the intrusion detection system is created based on these hyperparameters. This method was implemented using the Tensorflow and keras libraries and tested on the KDDCup99, UNSW-NB15 and Bot-IoT datasets. The results showed that the proposed method can detect attacks with a high accuracy of 99%.
.

کلیدواژه‌ها [English]

  • Deep learning
  • Inrusion detection systems
  • Internet of things
  • Meta-heuristic algorithms
  • Geray wolf optimizer
[1] H.H. Pajouh, R. Javidan, R. Khayami, A. Dehghantanha, and K.K. Raymond Choo. "A two-layer dimension reduction and two-tier classification model for anomaly-based intrusion detection in IoT backbone networks." IEEE Transactions on Emerging Topics in Computing 7, no. 2 (2016): 314-323.
[2] J. Asharf, N. Moustafa, H. Khurshid, E. Debie, W.Haider, and A. Wahab. "A review of intrusion detection systems using machine and deep learning in internet of things: Challenges, solutions and future directions." Electronics 9, no. 7 (2020): 1177.
[3] A. Thakkar, and R. Lohiya. "A review on machine learning and deep learning perspectives of IDS for IoT: recent updates, security issues, and challenges." Archives of Computational Methods in Engineering 28, no. 4 (2021): 3211-3243.
[4] Z.Y. Chen Yuanfang, M. Sabita, A. Muhammad, and W. Ting. “Deep learning for secure mobile edge computing.”  IEEE Network 43, no. 4 (2019): 36-41.
[5] M. Abdel-Basset, L. Abdel-Fatah, and A.K. Sangaiah. "Metaheuristic algorithms: A comprehensive review." Computational Intelligence for Multimedia Big Data on the Cloud with Engineering Applications (2018): 185-231.
[6] M.H. Ahmadi Taheri. "Providing a method based on deep learning to detect computer network." penetration Thesis. Abne Sina Institute of Higher Education. 2017. (inPersian)
[7] P.D. Cervantes Christian, , N. Michele, and S. Aldri.  “Detection of sinkhole attacks for supporting secure routing on 6LoWPAN for Internet of Things.”  In: 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM), IEEE,(1015): 606-611.
[8] E.J. Cho, J.H. Kim and C.S. Hong. “Attack model and detection scheme for botnet on 6LoWPAN.”  In: Asia-Pacific Network Operations and Management Symposium, Springer (2009): 515–518.
[9] J.P.Amaral, L.M. Oliveira, J.J. Rodrigues, G. Han, and L. Shu. "Policy and network-based intrusion detection system for IPv6-enabled wireless sensor networks." In 2014 IEEE International Conference on Communications (ICC), pp. 1796-1801. IEEE, 2014.
[10] A. Alghuried. “A Model for anomalies detection in Internet of Things (IoT) using inverse weight clustering and decision tree.”  Masters dissertation, Technological University Dublin (2017).
[11] R. Atefinia, and M. Ahmadi. “Network intrusion detection using multi-architectural modular deep neural network.”  Journal of Supercomputing 71, no. 4 (2021): 3571–3593.‏
[12] S. Chawla. Deep learning based intrusion detection system for Internet of Things. University of Washington, 2017.
[13] Y. Zhang, P. Li, and X. Wang. "Intrusion detection for IoT based on improved genetic algorithm and deep belief network." IEEE Access 7 (2019): 31711-31722.
[14] K. James, and E. Russell, “Particle swarm optimization.” In Proceedings of ICNN'95-International Conference on Neural Networks 4, no.2, (1995):1942-1948.‏
[15] H. Rania, C. Babak, D.W. Olivier and V. Gerhard. “A comparison of particle swarm optimization and the genetic algorithm.”  In 46th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials conference (2005): 1897-1903 .‏
[16] S.I. Popoola, B. Adebisi, R. Ande, M. Hammoudeh, K. Anoh, and A.A. Atayero. “SMOTE-DRNN: A deep learning algorithm for botnet detection in the Internet-of-Things networks.”  Sensors 21, no .9, (2021): 2851-2861.
[17] I. Idrissi, M. Boukabous, M. Azizi, O. Moussaoui, and H. El Fadili.  “Toward a deep learning-based intrusion detection system for IoT against botnet attacks.” IAES International Journal of Artificial Intelligence 10, no.1, (2021): 110-122.‏
[18] P. Leonid, E. Eleazar, and  J.S. Salvatore. “Intrusion detection with unlabeled data using clustering.” Proceedings of ACM CSS Workshop on Data Mining Applied to Security. (2001):123-132.
[19]   N. Moustafa, and J. Slay. "UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set)." In 2015 military communications and information systems conference (MilCIS), pp. 1-6. IEEE, 2015.
[20]  F. Chollet. “keras,” https://github.com/fchollet/keras, 2021.
[21]  M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, and S. Ghemawat. "Tensorflow: Large-scale machine learning on heterogeneous distributed systems." arXiv Preprint arXiv:1603.04467 (2016).
[22] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, P. Prettenhofer, R. Weiss, V. Dubourg, and J. Vanderplas. "Scikit-learn: Machine learning in Python." The Journal of Machine Learning Research 12 (2011): 2825-2830.
[23] N. Attiratanasunthron, J. Fakcharoenphol. “A running time analysis of an Ant Colony Optimization algorithm for shortest paths in directed acyclic graphs.”  Information Processing Letters 105, no. 3, (2008): 88-92.
[24] F. Yan, J. Xu, K. Yun. “Dynamically dimensioned search grey wolf optimizer based on positional interaction information.” Computational Methods for Modeling, Simulating, and Optimizing Complex Systems 2019, (2019):1-37.