prikaz prve stranice dokumenta Parametrizacija napadačkog prometa i primjena u zadanim topologijama
No public access
master's thesis
Parametrizacija napadačkog prometa i primjena u zadanim topologijama
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. urn:nbn:hr:168:327298
Pagon, Vilim
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pagon, V. (2024). Parametrizacija napadačkog prometa i primjena u zadanim topologijama (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:327298

Pagon, Vilim. "Parametrizacija napadačkog prometa i primjena u zadanim topologijama." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:327298

Pagon, Vilim. "Parametrizacija napadačkog prometa i primjena u zadanim topologijama." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:327298

Pagon, V. (2024). 'Parametrizacija napadačkog prometa i primjena u zadanim topologijama', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:327298

Pagon V. Parametrizacija napadačkog prometa i primjena u zadanim topologijama [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 December 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:327298

V. Pagon, "Parametrizacija napadačkog prometa i primjena u zadanim topologijama", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:327298

Metadata
TitleParametrizacija napadačkog prometa i primjena u zadanim topologijama
Title (english)Parametrization of attack traffic and application in given topologies
AuthorVilim Pagon
MentorStjepan Groš (mentor)
Committee memberStjepan Groš (predsjednik povjerenstva)
Committee memberAdrian Satja Kurdija (član povjerenstva)
Committee memberLeonardo Jelenković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-07-01, Croatia
Abstract
Ovaj rad istražuje izazove treniranja algoritama strojnog učenja za detekciju mrežnih napada, posebno zbog nedostatka malicioznog prometa u dostupnim skupovima podataka. Većina mrežnog prometa je benigni, a identificiranje malicioznog prometa je izazovno. Tradicionalni pristupi snimanja prometa tijekom penetracijskih testova ili umjetnog generiranja napadačkog prometa često brzo zastarijevaju. U radu su analizirani javno dostupni skupovi podataka poput UNSW-NB15, CSE-CIC-IDS2018 i Kitsune Network Attack dataset, te ručno snimljeni skupovi podataka. Tehnike generiranja napada uključuju filtriranje javno dostupnih podataka i ručno generiranje napada, dok je modifikacija napada ključna za prilagodbu parametrima, skaliranje, promjenu intenziteta i upravljanje s vremenom napada. Razvijeno je programsko rješenje za generiranje napadačkog prometa prema topologijama formata CCS. Opisana je implementacija lokalne baze uzoraka napada, formatiranje CCS topologije, parsiranje scenarija, generiranje napada i kreiranje PCAP datoteka. Prikazani su primjeri korištenja, rezultati i ograničenja rješenja, uz smjerove za daljnje istraživanje.
Abstract (english)
This paper explores the challenges of training machine learning algorithms for detecting network attacks, particularly due to the lack of malicious traffic in available datasets. Most network traffic is benign, and identifying malicious traffic is challenging. Traditional approaches of recording traffic during penetration tests or artificially generating attack traffic often quickly become outdated. This study analyzes publicly available datasets such as UNSW-NB15, CSE-CIC-IDS2018, and Kitsune Network Attack dataset, as well as manually recorded datasets. Attack generation techniques include filtering publicly available data and manually generating attacks, with attack modification being crucial for parameter adjustment, scaling, intensity variation, and timing control of attacks. A software solution was developed to generate attack traffic according to CCS topology formats. The implementation of a local attack sample database, CCS topology formatting, scenario parsing, attack generation, and PCAP file creation are described. Examples of usage, results, and solution limitations are presented, along with directions for further research.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:327298
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2024-10-12 21:44:05