Razvoj sustava za stvaranje i pohranu simuliranih podataka o mrežnom prometu u svrhu očuvanja kibernetičke sigurnosti

master's thesis

• Title (english): A Solution for Creating and Storing Simulated Network Traffic Data for the Needs of Cybersecurity System Development
• Author: Vedran Kolka
• Mentor: Damir Pintar (mentor)
• Committee member: Damir Pintar (predsjednik povjerenstva)
• Committee member: Mihaela Vranić (član povjerenstva)
• Committee member: Luka Humski (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu su opisani neki od alata za stvaranje skupova podataka sa svrhom očuvanja kibernetičke sigurnosti te su navedeni glavni nedostaci istih. Dana je specifikacija takvog sustava koji ne bi imao te nedostatke te je predložen idejni model.
Predstavljena je teorijska podloga najvažnijih koncepata za ostvarivanje opisanog sustava koji su kontejnerizacija i komunikacija procesa. Nakon toga su opisane korištene tehnologije i arhitektura sustava s opisom svake komponente. Nakon opisa sustava su analizirani skup podataka stvoren razvijenim alatom i stablo odluke naučeno na stvorenom skupu. Analizom je zaključeno da su stvoreni podaci nedovoljno kvalitetni za učenje modela za detekciju upada, ali je potvrđen koncept sustava koji u stvarnom vremenu distribuira stvorene podatke o mrežnom prometu.

Abstract (english)

In this thesis, some of the tools for creating datasets for cybersecurity system development are described along with their main flaws. A specification of a system which would not have these flaws is given and the model of the solution is proposed.
Key concepts for implementing such a system are covered, which were containerization and process communication. After this, the technologies and architecture of the system are described, as well as all of the components. After describing the system, a dataset generated with the implemented tool is analyzed, as well as a decision tree fit on the dataset. The conclusion of the analysis is that the generated data is of quality far too poor to train an intrusion detection system but the proof of concept for a system with real-time distribution of generated data is confirmed.

• Keywords: kibernetička sigurnost; mrežni napadi; streaming u stvarnom vremenu; Kafka; Docker
• Keywords (english): cybersecurity; network attacks; real-time streaming; Kafka; Docker
• Language: croatian
• URN:NBN: urn:nbn:hr:168:077032
• 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: 2023-01-14 09:08:14