Sustav za detekciju napada u okruženjima Interneta stvari

undergraduate thesis

• Title (english): Intrusion detection system in Internet of things environment
• Author: Zdravko Petričušić
• Mentor: Marin Vuković (mentor)
• Committee member: Marin Vuković (predsjednik povjerenstva)
• Committee member: Renato Šoić (član povjerenstva)
• Committee member: Karlo Slovenec (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad je opisao koncept okruženja Interneta stvari i važnosti kibernetičke sigurnosti u modernom svijetu. Dan je pregled osnovnih elemenata umjetne inteligencije u kontekstu neuronskih mreža koje su zatim korištene kako bi se pokušao izgraditi osnovni element nadzornog alata koji bi detektirao kibernetičke napade u IoT mrežama. Rad je obradio tri pristupa ovakvom alatu, jedan koristeći isključivo analizu metrika dostupnih na rubnim uređajima, te dva različita pristupa s gledišta umjetne inteligencije kojima se isti alat pokušao realizirati uz pomoć analize mrežnog prometa rubnih uređaja. Posljednja poglavlja ovog rada prilažu rezultate i prijedloge za buduća istraživanja.

Abstract (english)

This paper describes the concept of an IoT network and the importance of cybersecurity in the modern world. An overview of basic elements used in the field of artificial intelligence was given. Specifically, an overview of neural networks which were then used as a foundation upon which a cyberattack detection system would be built in order to detect such hazards in an IoT network. The paper presents three approaches to creating such software, one of which exclusively analyses the telemetry data collected on the edge devices themselves, whilst the other two employ different artificial intelligence strategies in order to build software which would analyze the network traffic in the IoT edge layer. The final chapters present the final results and provide suggestions for future research.

• Keywords: Internet stvari; IoT; kibernetička sigurnost; Internet; neuronske mreže; umjetna inteligencija; SIEM; mrežni promet; analiza podataka; hiperparametar
• Keywords (english): Internet of Things; IoT; cybersecurity; Internet; neural networks; artificial intelligence; SIEM; network traffic; data analysis; hyperparameter
• Language: croatian
• URN:NBN: urn:nbn:hr:168:309642
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-15 11:02:46