Otkrivanje prijevara usmjerenih na sustave za prepoznavanje lica

master's thesis

• Title (english): Detection of spoofing attacks on the facial recognition system
• Author: Matija Zlovolić
• Mentor: Mirjana Domazet-Lošo (mentor)
• Committee member: Mirjana Domazet-Lošo (predsjednik povjerenstva)
• Committee member: Marina Bagić Babac (član povjerenstva)
• Committee member: Marko Horvat (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru ovoga diplomskog rada istražen je problem prijevara (engl. spoofing) usmjerenih na sustave za prepoznavanje ljudskih lica te metode otkrivanja takvih prijevara. U kontekstu biometrijskih sustava, napad lažiranjem (engl. spoofing attack) je pokušaj prevare sustava za prepoznavanje ljudskih lica pomoću npr. fotografije ili video zapisom druge osobe. U sklopu rada implementiran je program baziran na algoritmima strojnog učenja za otkrivanje prijevara usmjerene na sustave za prepoznavanje lica u programskom jeziku Python. Rezultati implementacije su obrazloženi i uspoređeni s rezultatima drugih metoda.

Abstract (english)

This graduate thesis focuses on the research of classification tasks for human face anti-spoofing. A spoofing attack is an identity impersonation with the attempt to fool biometric systems. Identity impersonation attacks like the presentation attack, replay attack, and mask attack, can create partial or whole modifications to the face. Machine learning algorithms are used to develop a system for the classification task using the programming language Python. Results from the implemented system are then compared to the results of different methods.

• Keywords: Napad lažiranjem usmjeren na sustave za prepoznavanje lica; Strojno učenje; Duboko učenje; Generativne suparničke mreže
• Keywords (english): Spoofing attack; Machine learning; Deep learning; Generative adversarial networks
• Language: croatian
• URN:NBN: urn:nbn:hr:168:174765
• 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 14:18:33