مشخصات مقاله | |
ترجمه عنوان مقاله | سیستم تشخیص نفوذ مبتنی بر هوش مصنوعی مقاوم در برابر خطا برای اینترنت اشیا |
عنوان انگلیسی مقاله | Fault-tolerant AI-driven Intrusion Detection System for the Internet of Things |
انتشار | مقاله سال ۲۰۲۱ |
تعداد صفحات مقاله انگلیسی | ۱۶ صفحه |
هزینه | دانلود مقاله انگلیسی رایگان میباشد. |
پایگاه داده | نشریه الزویر |
نوع نگارش مقاله |
مقاله پژوهشی (Research Article) |
مقاله بیس | این مقاله بیس نمیباشد |
نمایه (index) | Scopus – Master Journals List – JCR |
نوع مقاله | ISI |
فرمت مقاله انگلیسی | |
ایمپکت فاکتور(IF) |
۳٫۶۲۲ در سال ۲۰۲۰ |
شاخص H_index | ۳۷ در سال ۲۰۲۱ |
شاخص SJR | ۰٫۶۵۰ در سال ۲۰۲۰ |
شناسه ISSN | ۱۸۷۴-۵۴۸۲ |
شاخص Quartile (چارک) | Q2 در سال ۲۰۲۰ |
فرضیه | ندارد |
مدل مفهومی | ندارد |
پرسشنامه | ندارد |
متغیر | ندارد |
رفرنس | دارد |
رشته های مرتبط | مهندسی کامپیوتر، مهندسی فناوری اطلاعات |
گرایش های مرتبط | اینترنت و شبکه های گسترده، امنیت اطلاعات، شبکه های کامپیتری، هوش مصنوعی |
نوع ارائه مقاله |
ژورنال |
مجله | مجله بین المللی حفاظت از زیرساخت های حیاتی – International Journal of Critical Infrastructure Protection |
دانشگاه | Research Centre on Scientific and Technical Information (CERIST), Algiers, Algeria |
کلمات کلیدی | امنیت RPL ، امنیت اینترنت اشیا، IDS، یادگیری ماشین، یادگیری عمیق، زیرساخت های حیاتی |
کلمات کلیدی انگلیسی | RPL security – IoT security – IDS – Machine Learning – Deep Learning – Critical infrastructure |
شناسه دیجیتال – doi |
https://doi.org/10.1016/j.ijcip.2021.100436 |
کد محصول | E15961 |
وضعیت ترجمه مقاله | ترجمه آماده این مقاله موجود نمیباشد. میتوانید از طریق دکمه پایین سفارش دهید. |
دانلود رایگان مقاله | دانلود رایگان مقاله انگلیسی |
سفارش ترجمه این مقاله | سفارش ترجمه این مقاله |
فهرست مطالب مقاله: |
Abstract Keywords ۱٫ Introduction ۲٫ Background ۳٫ Materials and methods ۴٫ Classifiers evaluation and discussion ۵٫ RF-Based Intrusion Detection System for RPL (RF-IDSR) ۶٫ Related works ۷٫ Conclusion Declaration of Competing Interest Acknowledgements References |
بخشی از متن مقاله: |
Abstract Internet of Things (IoT) has emerged as a key component of all advanced critical infrastructures. However, with the challenging nature of IoT, new security breaches have been introduced, especially against the Routing Protocol for Low-power and Lossy Networks (RPL). Artificial-Intelligence-based technologies can be used to provide insights to deal with IoT’s security issues. In this paper, we describe the initial stages of developing, a new Intrusion Detection System using Machine Learning (ML) to detect routing attacks against RPL. We first simulate the routing attacks and capture the traffic for different topologies. We then process the traffic and generate large 2-class and multi-class datasets. We select a set of significant features for each attack, and we use this set to train different classifiers to make the IDS. The experiments with 5-fold cross-validation demonstrated that decision tree (DT), random forests (RF), and K-Nearest Neighbours (KNN) achieved good results of more than 99% value for accuracy, precision, recall, and F1-score metrics, and RF has achieved the lowest fitting time. On the other hand, Deep Learning (DL) model, MLP, Naïve Bayes (NB), and Logistic Regression (LR) have shown significantly lower performance. ۱٫ Introduction Critical infrastructures (CIs) cover various socio-economic sectors such as healthcare, agriculture, industry, gas and water distribution, transportation, energy, communications, information technology, etc. CIs are continuously changing and adapting to changes in technology. Indeed, Cyber-Physical Systems (CPS) and the Internet of Things (IoT) have emerged as core components in all advanced Cis, such as Industry 4.0 [1,2]. Since CIs are vital to daily human lives, their protection from cyber-attacks by malicious entities that cause significant impacts on the targeted CIs and their services is a serious concern. Consequently, to secure CIs, it is necessary to secure IoT networks [3]. IoT [4] consists of physical objects, usually known as things (devices) that sense, collect, and might process CIs related information. On one side, these objects are resource-constrained as they are powered by batteries and have limited computation and storage capability. On the other side, billions of these devices are interconnected and connected to the Internet under lossy and noisy communication environments such as Wi-Fi, ZigBee, Bluetooth, LoRa, GSM, WiMAX or GPRS. IoT applications have emerged in several aspects. Nevertheless, the IoT’s networks rise challenges in designing efficient and secure routing protocols [5,6]. Several efforts have been made by standardisation entities to specify efficient routing protocols for the IoT. Finally, the IPv6 Routing Protocol for Low Power and Lossy Networks (RPL) [7] was designed and standardised by the IETF ROLL working group to overcome the routing challenges underpinning IoT networks. RPL specification considers limitations in both the energy power and the computational capabilities of such networks |