Sustav za detekciju i klasifikaciju napada u okruženju Interneta stvari

master's thesis

• Title (english): IoT environment intrusion detection and classification system
• Author: Luka Šimunec
• Mentor: Marin Vuković (mentor)
• Committee member: Marin Vuković (predsjednik povjerenstva)
• Committee member: Miljenko Mikuc (član povjerenstva)
• Committee member: Dragan Jevtić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Porastom popularnosti Interneta stvari dolazi do sve većeg iskorištavanja njihovih ranjivosti. Jedan od načina zaštite okruženja od malicioznih pojedinaca je integracija sustava za detekciju napada. Na početku rada opisana je arhitektura okruženja Interneta stvari te su ukratko definirani i klasificirani najučestaliji napadi. Nakon toga su detaljno analizirani postojeći sustavi za detekciju napada. Na temelju istraživanja, predloženi su, implementirani i testirani modeli za detekciju i klasifikaciju napada na mreži bazirani na strojnom učenju. Na kraju je predložena integracija izgrađenih modela u postojeću arhitekturu te je donesen relevantan zaključak.

Abstract (english)

With the growth of IoT popularity, the exploit of their vulnerabilities is also on the rise. One of the ways to protect the environment is to integrate an intrusion detection system. At the beginning of this thesis, IoT architecture has been described and most common attacks have been briefly defined and classified. After that, existing IoT environment intrusion detection systems have been analyzed in detail. Based on research, machine learning models for the detection and classification of IoT attacks have been proposed, implemented, and tested. In the end, an example of the integration of these models into an existing architecture has been given, as well as a relevant conclusion.

• Keywords: Internet stvari; detekcija napada; klasifikacija napada; strojno učenje; neuronska mreža
• Keywords (english): Internet of Things; IoT; intrusion detection; intrusion classification; machine learning; neural network
• Language: croatian
• URN:NBN: urn:nbn:hr:168:043234
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 13:56:16