Otkrivanje napada na sustave preporučivanja zasnovane na suradničkom filtriranju

master's thesis

• Title (english): Attack Detection in Collaborative Filtering Recommendation Systems
• Author: Vjeran Grozdanić
• Mentor: Klemo Vladimir (mentor)
• Committee member: Klemo Vladimir (predsjednik povjerenstva)
• Committee member: Marin Šilić (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-02-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu su predstavljeni osnovne grupe sustava preporučivanja s naglaskom na sustave preporučivanja zasnovane na suradničkom filtriranju. Prikazane su ranjivosti takvih sustava preporučivanja te najčešći napadi na takve sustave preporučivanja.
U radu je predstavljen novi pristup otkrivanju napada, uporabom ansambla slučajnih
šuma, gdje je svaki model slučajne šume specijaliziran za odred̄enu skupinu napada

Abstract (english)

In this paper, the basic groups of recommendation systems are presented with a focus on collaborative filtering recommendation systems. The vulnerabilities of such recommendation systems and the most common attacks on such systems are shown. A new approach to attack detection is presented using an ensemble of random forest models, where each random forest model is specialized for a certain group of attacks.

• Keywords: sustavi preporučivanja; suradničko filtriranje; napadi ubacivanjem profila; otkrivanje napada; slučajna šuma
• Keywords (english): recommendation systems; collaborative filtering; shilling attacks; profile injection attack; attack detection
• Language: croatian
• URN:NBN: urn:nbn:hr:168:605169
• 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: 2023-07-13 10:05:32