استفاده از یادگیری انتقالی برای افزایش امنیت سایبری در شبکه‌های اینترنت اشیا
آرمان سمیعی
1
(
دانشكده مهندسی برق، دانشگاه علم و صنعت، تهران، ايران
)
عرفان خدرصلح
2
(
دانشكده مهندسی برق، دانشگاه علم و صنعت، تهران، ايران
)
هادی شهریار شاه حسینی
3
(
دانشكده مهندسی برق، دانشگاه علم و صنعت، تهران، ايران
)
کلید واژه: اینترنت اشیا, سیستم‌های تشخیص نفوذ, یادگیری انتقالی, یادگیری عمیق.,
چکیده مقاله :
سیستم‌های تشخیص نفوذ (IDS) با شناسایی دسترسی غیرمجاز شبکه‌های کامپیوتری و بررسی نقض‌های امنیتی احتمالی، نقش اساسی در دفاع از شبکه‌های کامپیوتری ایفا می‌کنند. IDS های سنتی برای مبارزه با حملات امنیتی پیچیده جدید ایجاد شده با مشکلاتی مواجه می‌شوند. از این رو، نیاز روزافزونی به راه‌حل تشخیص نفوذ خودکار وجود دارد که می‌تواند فعالیت‌های مخرب را با دقت بیشتری شناسایی کند. در این مقاله، مدل جدید تشخیص نفوذ شبکه اینترنت اشیا با استفاده از یک شبکه عصبی بر اساس معماری VGG16 از پیش آموزش دیده پیشنهاد شده است. مدل یک فرآیند دو مرحله‌ای است که در مرحله اول برخی از لایه‌ها VGG16 را از پیش بر روی مجموعه داده‌ی ImageNet آموزش داده شده و وزن‌های آن را انتقال می‌دهیم و در مرحله دوم به طور خاص برای تشخیص نفوذ در شبکه‌های اینترنت اشیا عمل Fine Tuning انجام می‌شود. زیرا این شبکه‌ها به دلیل محدودیت‌های منابع، پروتکل‌های منحصر به فرد و تنوع دستگاه‌ها، آسیب‌پذیری‌های خاصی دارند که نیازمند روش‌های تشخیص نفوذ مختص به خود هستند. مدل روی مجموعه داده‌های UNSW-NB15 و NSL-KDD ، اعمال شده است. نتایج نشان می‌دهد که روش پیشنهاد شده می‌تواند به طور مؤثر با تولید عملکرد واقعی از نظر accuracy، Precision، Recall و F1_score یاد بگیرد.
چکیده انگلیسی :
Intrusion detection systems (IDS) play a fundamental role in the defense of computer networks by detecting unauthorized access and investigating possible security breaches. Traditional IDSs face difficulties in combating newly developed sophisticated security attacks. Hence, there is a growing need for an automated intrusion detection solution that can detect malicious activities more accurately. In this paper, a new model of Internet of Things (IoT) network intrusion detection using a neural network based on the pre-trained VGG16 architecture is proposed. The model is a two-stage process: in the first stage, some layers of VGG16 are pre-trained on the ImageNet dataset, and we transfer its weights; in the second stage, fine-tuning is performed specifically to detect penetration in IoT networks. These networks have specific vulnerabilities due to resource limitations, unique protocols, and a variety of devices that require their own intrusion detection methods. The model is applied to UNSW-NB15 and NSL-KDD datasets. The results show that the proposed method can learn effectively by producing real performance in terms of accuracy, precision, recall, and F1 score.
[1] X. Wu et al., "Threat analysis for space information network based on network security attributes: a review," Complex & Intelligent Systems, vol. 9, no. 3, pp. 3429-3468, 2023.
[2] M. Lombardi, F. Pascale, and D. Santaniello, "Internet of things: A general overview between architectures, protocols and applications," Information, vol. 12, no. 2, p. 87, 2021.
[3] M. Alkasassbeh and S. Al-Haj Baddar, "Intrusion detection systems: A state-of-the-art taxonomy and survey," Arabian Journal for Science and Engineering, vol. 48, no. 8, pp. 10021-10064, 2023.
[4] M. Pradhan, C. K. Nayak, and S. K. Pradhan, "Intrusion detection system (IDS) and their types," in Securing the internet of things: Concepts, methodologies, tools, and applications: IGI Global, , pp. 481-497, 2020.
[5] A. Khraisat and A. Alazab, "A critical review of intrusion detection systems in the internet of things: techniques, deployment strategy, validation strategy, attacks, public datasets and challenges," Cybersecurity, vol. 4, pp. 1-27, 2021.
[6] M. R. Ahmed, S. Shatabda, A. M. Islam, and M. T. I. Robin, "Intrusion Detection System in Software-Defined Networks Using Machine Learning and Deep Learning Techniques--A Comprehensive Survey," Authorea Preprints, 2023.
[7] G. Kumar, K. Thakur, and M. R. Ayyagari, "MLEsIDSs: machine learning-based ensembles for intrusion detection systems—a review," The Journal of Supercomputing, vol. 76, pp. 8938-8971, 2020.
[8] A. Hkiri, S. Alqurashi, O. Ben Bahri, M. Karmani, H. Faraj, and M. Machhout, "Performance Evaluation of Mobile RPL-Based IoT Networks under Hello Flood Attack," Electronics, vol. 13, no. 11, p. 2226, 2024.
[9] N. Gupta, V. Jindal, and P. Bedi, "CSE-IDS: Using cost-sensitive deep learning and ensemble algorithms to handle class imbalance in network-based intrusion detection systems," Computers & Security, vol. 112, pp. 102-499, 2022.
[10] L. Alzubaidi et al., "Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions," Journal of big Data, vol. 8, pp. 1-74, 2021.
[11] I. Ullah, A. Ullah, and M. Sajjad, "Towards a hybrid deep learning model for anomalous activities detection in internet of things networks," IoT, vol. 2, no. 3, pp. 428-448, 2021.
[12] L. Santos, C. Rabadao, and R. Gonçalves, "Intrusion detection systems in Internet of Things: A literature review," in 2018 13th Iberian Conference on Information Systems and Technologies (CISTI), 2018: IEEE, pp. 1-7, 2018.
[13] H. Jmila, G. Blanc, M. R. Shahid, and M. Lazrag, "A survey of smart home iot device classification using machine learning-based network traffic analysis," IEEE Access, vol. 10, pp. 97117-97141, 2022.
[14] A. Thakkar and R. Lohiya, "A survey on intrusion detection system: feature selection, model, performance measures, application perspective, challenges, and future research directions," Artificial Intelligence Review, vol. 55, no. 1, pp. 453-563, 2022.
[15] S. Dargan, M. Kumar, M. R. Ayyagari, and G. Kumar, "A survey of deep learning and its applications: a new paradigm to machine learning," Archives of Computational Methods in Engineering, vol. 27, pp. 1071-1092, 2020.
[16] D. Swessi and H. Idoudi, "A survey on internet-of-things security: threats and emerging countermeasures," Wireless Personal Communications, vol. 124, no. 2, pp. 1557-1592, 2022.
[17] Z. Wang, Y. Lai, Z. Liu, and J. Liu, "Explaining the attributes of a deep learning based intrusion detection system for industrial control networks," Sensors, vol. 20, no. 14, p. 3817, 2020.
[18] A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, and M. A. Azim, "Transfer learning: a friendly introduction," Journal of Big Data, vol. 9, no. 1, p. 102, 2022.
[19] K. Kim, M. E. Aminanto, H. C. Tanuwidjaja, K. Kim, M. E. Aminanto, and H. C. Tanuwidjaja, "Deep Learning-Based IDSs," Network Intrusion Detection using Deep Learning: A Feature Learning Approach, pp. 35-45, 2018.
[20] L. Vu, Q. U. Nguyen, D. N. Nguyen, D. T. Hoang, and E. Dutkiewicz, "Deep transfer learning for IoT attack detection," IEEE Access, vol. 8, pp. 107335-107344, 2020.
[21] T. V. Khoa et al., "Deep transfer learning: A novel collaborative learning model for cyberattack detection systems in IoT networks," IEEE Internet of Things Journal, 2022.
[22] W. Yutao, L. Zhongtian, B. Yi, L. Jie, X. Fangzheng, and B. Yu, "Internet of Things Intrusion Detection System based on Transfer Learning," in 2022 IEEE 2nd International Conference on Electronic Technology, Communication and Information (ICETCI), pp. 25-30, 2022.
[23] S. T. Mehedi, A. Anwar, Z. Rahman, K. Ahmed, and R. Islam, "Dependable intrusion detection system for IoT: A deep transfer learning based approach," IEEE Transactions on Industrial Informatics, vol. 19, no. 1, pp. 1006-1017, 2022.
[24] S. Choudhary and N. Kesswani, "Analysis of KDD-Cup’99, NSL-KDD and UNSW-NB15 datasets using deep learning in IoT," Procedia Computer Science, vol. 167, pp. 1561-1573, 2020.
[25] G. Kocher and G. Kumar, "Performance analysis of machine learning classifiers for intrusion detection using unsw-nb15 dataset," Comput. Sci. Inf. Technol, vol. 10, no. 20, pp. 31-40, 2020.
[26] X. Larriva-Novo, V. A. Villagrá, M. Vega-Barbas, D. Rivera, and M. Sanz Rodrigo, "An IoT-focused intrusion detection system approach based on preprocessing characterization for cybersecurity datasets," Sensors, vol. 21, no. 2, p. 656, 2021.
[27] R. A. Disha and S. Waheed, "A Comparative study of machine learning models for Network Intrusion Detection System using UNSW-NB 15 dataset," in 2021 International Conference on Electronics, Communications and Information Technology, pp. 1-5, 2021.
[28] E. H. Salman, M. A. Taher, Y. I. Hammadi, O. A. Mahmood, A. Muthanna, and A. Koucheryavy, "An anomaly intrusion detection for high-density internet of things wireless communication network based deep learning algorithms," Sensors, vol. 23, no. 1, p. 206, 2022.
[29] I. Ahmad, Q. E. Ul Haq, M. Imran, M. O. Alassafi, and R. A. AlGhamdi, "An efficient network intrusion detection and classification system," Mathematics, vol. 10, no. 3, p. 530, 2022.
[30] F. Türk, "Analysis of intrusion detection systems in UNSW-NB15 and NSL-KDD datasets with machine learning algorithms," Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 12, no. 2, pp. 465-477, 2023.
[31] L. A. Maghrabi, "Automated Network Intrusion Detection for Internet of Things Security Enhancements," IEEE Access, 2024.
[32] K. Pramilarani and P. V. Kumari, "Cost based Random Forest Classifier for Intrusion Detection System in Internet of Things," Applied Soft Computing, vol. 151, pp. 111-125, 2024.
[33] S. More, M. Idrissi, H. Mahmoud, and A. T. Asyhari, "Enhanced Intrusion Detection Systems Performance with UNSW-NB15 Data Analysis," Algorithms, vol. 17, no. 2, p. 64, 2024.