Sustav za detekciju i klasifikaciju napada na web-aplikacije

master's thesis

• Title (english): Web-application intrusion detection and classification system
• Author: Karlo Slovenec
• Mentor: Marin Vuković (mentor)
• Committee member: Marin Vuković (predsjednik povjerenstva)
• Committee member: Dragan Jevtić (član povjerenstva)
• Committee member: Miljenko Mikuc (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu razmotreni su sustavi za detekciju kibernetičkih napada i metode koje se koriste prilikom detekcije. Predložen je novi sustav koji za detekciju koristi neuronske mreže. Sustav je lako prilagodljiv, brz i ima zadovoljavajuću stopu detekcije uz dovoljno niski udio lažno pozitivnih rezultata. Kao takav može se primjenjivati za detekciju i prevenciju napada na web-aplikacije. Napravljene su i inačice sustava koje mogu služiti kao analizatori dnevničkih zapisa cijelog sustava ili pojedinog korisnika.

Abstract (english)

In this thesis Intrusion detection systems and methods they use for detection and classification are reviewed. New system based on neural networks is suggested. System is fast, easy to configure and applicable to new applications and detects satisfiable amount of attacks while having low amount of false positive results. As such, system is applicable as system for detection and prevention of attacks on web-applications. Since given system has good results, two additional versions of system were made, one as log analyzer and one as individual user analyzer.

• Keywords: Sustavi za detekciju i prevenciju napada; sustavi za prevenciju napada na web-aplikacije; neuronske mreže; neuronske mreže s povratnim vezama; Apache Web Server
• Keywords (english): Intrusion detection and prevention systems; Web application firewall; neural networks; recurrent neural networks; Apache Web Server
• Language: croatian
• URN:NBN: urn:nbn:hr:168:119834
• 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: 2020-01-07 22:03:40