Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/150757
Title: | Detección y mitigación de ataques de denegación de servicio en redes IoT usando Inteligencia Artificial (IA) y técnicas de aprendizaje automático (ML) |
Author: | López Capó, Josep |
Tutor: | Pérez López, Fernando |
Abstract: | The Internet of Things (IoT) emerges as the network of smart devices that arise in response to the need to integrate new services (transportation, healthcare, infrastructure, etc.) into virtually every aspect of our lives. Consequently, this rapid proliferation of the internet has offered new opportunities to attacking users. The most common, due to its simplicity, way to affect a network is through a denial of service attack. This attack consists, essentially, in flooding a network with malicious traffic, hindering or nullifying the offered service. Therefore, the implementation of effective defense mechanisms is established as a basic necessity in every internet network. In this work, machine learning (ML) techniques using artificial intelligence (AI) are employed to implement an Intrusion Detection System (IDS) to detect and mitigate alleged Denial of Service Attacks, as well as to discuss the evolution of the results. This thesis aims to evaluate two machine learning models for the detection of DIS-Flood Denial of Service Attacks in a simulated IoT environment. Support Vector Machine (SVM) and Random Forest (RF) classifiers are used on the IoTR – DS dataset [Resources 9]. The accuracy rate obtained for SVM is 98.6%, while for Random Forest it is 99.4%. The precision rate was 98.2% in SVM and 99.2% in RF. Sensitivity was 98.7% in SVM compared to 99.6% in RF. The results show that Random Forest outperformed Support Vector Machine in all the aforementioned metrics, presenting itself as the most suitable option for implementation in attack detection. |
Keywords: | denial of service attacks IoT IDS support vector machine confusion matrix random forest learning model cybercriminal machine learning artificial intelligence |
Document type: | info:eu-repo/semantics/bachelorThesis |
Issue Date: | Jun-2024 |
Publication license: | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
Appears in Collections: | Trabajos finales de carrera, trabajos de investigación, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
joseplopcapTFC0624.pdf | Memoria del TFG | 2,61 MB | Adobe PDF | View/Open |
Share:
This item is licensed under aCreative Commons License