چارچوب ترکیبی سبکوزن برای امنیت اینترنت اشیا با استفاده از جنگل تصادفی بهینه و انتخاب ویژگی تطبیقی در معماری لبه-ابری
محورهای موضوعی : electrical and computer engineering
1 - گروه مهندسی کامپیوتر، دانشگاه ملی مهارت، تهران، ایران
کلید واژه: اینترنت اشیا, یادگیری ماشین, تشخیص ناهنجاری, امنیت, جنگل تصادفی بهینه (ORF), معماری لبه ابری.,
چکیده مقاله :
امنیت در زیرساختهای اینترنت اشیا (IoT) به دلیل افزایش تهدیدات سایبری، از مهمترین چالشهای این حوزه محسوب میشود. اتصال پیوسته دستگاههای IoT به شبکه و پردازش دادههای حساس، آنها را در معرض حملاتی نظیر انکار سرویس، نفوذ و دستکاری عملکرد قرار میدهد که پیامدهایی چون اختلال در سیستم و افشای اطلاعات محرمانه را به دنبال دارد. از سوی دیگر، تنوع و پیچیدگی حملات، ناهمگونی دادههای حسگرها و تغییرپذیری رفتار نرمال سیستمها، تشخیص تهدیدات را دشوار ساخته است. در این پژوهش، چارچوبی ترکیبی و سبکوزن مبتنی بر جنگل تصادفی بهینه (ORF) و انتخاب ویژگی تطبیقی برای بهبود امنیت IoT ارائه میگردد. به منظور ارزیابی، عملکرد الگوریتمهای مختلف یادگیری ماشین شامل رگرسیون لجستیک، ماشین بردار پشتیبان، درخت تصمیم، جنگل تصادفی، شبکه عصبی مصنوعی و ORF بر روی مجموعهداده OS 2DS بررسی شد. نتایج نشان داد که همه مدلها به دقت بالای 98/0 دست یافتند، در حالی که RF و ORF با امتیاز 1F معادل 9937/0 عملکرد برتر داشتند. همچنین بهکارگیری الگوریتم بهینهسازی ازدحام ذرات (PSO) موجب کاهش نرخ مثبت کاذب تا 57/0% شد و بهرهگیری از معماری لبه-ابری زمان پردازش را حدود 40% بهبود داد. روش پیشنهادی علاوه بر کاهش 29% مصرف حافظه، یک راهکار کارآمد و مقیاسپذیر برای مقابله با تهدیدات امنیتی در محیطهای IoT ارائه میدهد.
Security in Internet of Things (IoT) infrastructures has become a critical challenge due to the rising cyber threats, such as Denial-of-Service (DoS) attacks, data breaches, and device manipulation. IoT devices, as core components of these systems, are highly vulnerable to various attacks and anomalies due to their continuous network connectivity and handling of sensitive data, potentially leading to system disruptions, confidential data leaks, and financial or human losses. Despite significant advancements in IoT security, challenges such as the diversity and complexity of attacks, heterogeneous and voluminous sensor data, variations in normal system behavior, scarcity of high-quality training data, and the need for scalable methods continue to hinder accurate and timely attack detection. This study proposes a lightweight and intelligent hybrid framework based on an Optimized Random Forest (ORF) and adaptive feature selection to enhance IoT system security. The performance of various machine learning algorithms, including Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Artificial Neural Network (ANN), and ORF, was evaluated using the DS2OS dataset. Results demonstrated that all models achieved accuracies ranging from 0.9844 to 0.9948, with RF and ORF exhibiting superior performance at an accuracy of 0.9943, precision of 0.9943, recall of 0.9943, and an F1-score of 0.9937. Furthermore, integrating the Particle Swarm Optimization (PSO) algorithm reduced the false positive rate to 0.57%, while the Edge-Cloud architecture improved processing time by 40%. Compared to existing approaches, the proposed method reduced memory consumption by 29%, offering a scalable solution for IoT security.
[1] M. Hasan, M. Islam, and I. Islam, "Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches," Internet of Things, vol. 7Article ID: 100059, Jan. 2019.
[2] H. Mazarei, M. Dadvar, and M. H. Atabakzadeh, "Distributed denial of service attacks detection in Internet of Things using the majority voting approach," J. Commun. Eng., vol. 13, no. 49, pp.23-48, Jun. 2023.
[3] S. Sharifi and S. Gheisari, "Design of anomaly-bbased intrusion detection system using support vector machine and grasshopper optimization algorithm in IoT," J. Commun. Eng., vol. 12, no. 46, pp. 42-58, May 2023.
[4] M. Eghbali, M. R. Mollakhalili Meybodi, and M. H. Atabakzadeh, "Detection of DDoS attacks in SDN switches with deep learning and swarm intelligence approach," J. South. Commun. Eng., vol. 13, no. 49, pp. 23-48, Apr. 2024.
[5] B. M. Pampapathi, M. Guptha, and M. S. Hema, "Towards an effective deep learning-based intrusion detection system in the Internet of Things," Telecommun. Informatics, vol. 7Article ID: 100009, Mar. 2022.
[6] F. Pishdad and R. Ebrahimi Atani, "Prevention and detection of botnet attacks in IoT using ensemble learning methods," Monadi: J. Cyberspace Secur., vol. 13, no. 2, pp. 45-55, Feb. 2024.
[7] M. Naji, H. Zougagh, Y. Saadi, H. Garmani, and Y. Oukissou, "Attack and anomaly detection in IoT sensors using machine learning approaches," in Proc. 23rd Int. Conf. on Intelligent Systems Design and Applications, pp. 331-340, Held Online, 11-13 Dec. 2023.
[8] K. Mithran and C. Gopi, "Anomaly detection in IoT sensor networks using machine learning," in Proc. 22nd Int. Conf. on Intelligent Systems Design and Applications, pp. 331-340, Held Online, 12-14 Dec. 2022.
[9] R. Thamaraiselvi and S. A. Selva Mary, "Attack and anomaly detection in IoT networks using machine learning," Int. J. Comput. Sci. Mob. Comput., vol. 9, no. 10, pp. 95-103, Nov. 2020.
[10] A. Shaikh and G. Negalur, "Attack and anomaly detection in IoT sites using machine learning techniques," Int. J. Res. Appl. Sci. Eng. Technol., vol. 10, no. 7, Article ID: 3029, Aug. 2022.
[11] A. A. Obaidli, D. Mansour, S. M. Abdulhamid, N. B. Halima, and A. Al-Ghushami, "Machine learning approach to anomaly detection attacks classification in IoT devices," in Proc. 1st Int. Conf. Adv. Innovations Smart Cities, 6 pp., Jeddah, Saudi Arabia. 23-25 Jan. 2023.
[12] C. Cyrus, IoT Ccyberattacks escalate in 2021, according to Kaspersky, IoT World Today, www.iotworldtoday.com/security/iotcyberattacks-escalate-in-2021-according-to-kaspersky, Sept. 2021.
[13] R. Al Attar, M. alkasassbeh, M. Al-Dala’ien, and M. Alohaly, Detecting Anomalies in IoT Devices: A Machine Learning-Based Solution, arXiv preprint arXiv:2404.0499, Oct. 2024.
[14] V. Prakash, O. Odedina, A. Kumar, L. Garg, and S. Bawa, "A secure framework for the Internet of Things anomalies using machine learning," Discover Internet of Things, vol. 4, Article ID: 33, 2024.
[15] I. Alrashdi, et al., "AD-IoT: Anomaly detection of IoT cyberattacks in smart city," in Proc. IEEE 9th Annual Computing and Communication Workshop Conf., pp. 305-310, Las Vegas, Nevada, USA, 7-9 Jan. 2019.
[16] P. K. Yadav and A. C. Kumar, "Analysis of machine learning model for anomaly and attack detection in IoT devices," in Proc. 4th Int. Conf. on Inventive Research in. Computing Applications, pp. 387-392, Coimbatore, India, 21-23 Sept. 2022.
[17] M. Khan and M. Alkhathami, "Anomaly detection in IoT-based healthcare: machine learning for enhanced security," Scientific Reports, vol. 14, no. 1, Article ID: 5872, Mar. 2024.
[18] T. P. Jayesh et al., "A Hybrid Machine Learning Approach to Anomaly Detection in Industrial IoT," in Proc. 3rd Int. Conf. on Advances in Computing, Communication, Embedded and Secure Systems, 4 pp., Kalady, India, 18-20 May 2023.
[19] E. Altulaihan, M. A. Almaiah, and A. Aljughaiman, "Anomaly detection IDS for detecting DoS attacks in IoT networks based on machine learning algorithms," Sensors, vol. 24, no. 2, Article ID: 713, Jun. 2024.
[20] B. B. Gupta, et al., "A novel hybrid convolutional neural network- and gated recurrent unit-based paradigm for IoT network traffic attack detection in smart cities," Sensors, vol. 23, no. 21, Article ID: 8686, Sept. 2023.
[21] A. A. Diro and N. Chilamkurti, "Distributed attack detection scheme using deep learning approach for Internet of Things," Future Gener. Comput. Syst., vol. 82, pp. 761–768, Dec. 2018.
[22] I. T. Al-Halboosi, B. M. Elbagoury, S. El-Regaily, and E.-S. M. El-Horbaty, "A hybrid-transformer-based cyber-attack detection in IoT networks," Int. J. Interact. Mob. Technol., vol. 18, no. 14, pp. 90-102, May 2024.
[23] H. Kamal and M. Mashaly, "Enhanced hybrid deep learning models-based anomaly detection method for two-stage binary and multi-class classification of attacks in intrusion detection systems," Algorithms, vol. 18, no. 2, Article ID: 69, Jul. 2025.
[24] M. O. Pahl and F. X. Aubet, "All eyes on you: Distributed multi- dimensional IoT microservice anomaly detection," in Proc. Int. Conf. on Network and Service Management, pp. 72-80, Rome, Italy, 5-9 Nov. 2018.