prikaz prve stranice dokumenta Otpornost modela dubokog učenja na suparničke napade
No public access
master's thesis
Otpornost modela dubokog učenja na suparničke napade
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:664117
Gjenero, Mario
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Gjenero, M. (2023). Otpornost modela dubokog učenja na suparničke napade (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:664117

Gjenero, Mario. "Otpornost modela dubokog učenja na suparničke napade." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:664117

Gjenero, Mario. "Otpornost modela dubokog učenja na suparničke napade." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:664117

Gjenero, M. (2023). 'Otpornost modela dubokog učenja na suparničke napade', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 17 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:664117

Gjenero M. Otpornost modela dubokog učenja na suparničke napade [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 November 17] Available at: https://urn.nsk.hr/urn:nbn:hr:168:664117

M. Gjenero, "Otpornost modela dubokog učenja na suparničke napade", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:664117

Metadata
TitleOtpornost modela dubokog učenja na suparničke napade
Title (english)Resistance of deep learning models to adversarial attacks
AuthorMario Gjenero
MentorSonja Grgić (mentor)
Committee memberSonja Grgić (član povjerenstva)
Committee memberMarko Bosiljevac (član povjerenstva)
Committee memberDario Bojanjac (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-11, Croatia
Abstract
Ovaj rad istražuje suparničke napade na duboke neuronske mreže korištene za probleme računalnog vida. Suparnički napadi mijenjaju ulazne podatke kako bi model strojnog učenja donio pogrešne zaključke. Karakteristika ovih napada je da su promjene na ulaznim podacima gotovo neprimjetne ljudima dok značajno utječu na model. Uvodni dio rada detaljno objašnjava duboke neuronske mreže, njihov rad te osjetljivost na suparničke napade. Kasnije u radu, detaljno su objašnjeni različiti načini kreiranja suparničkih napada, uključujući algoritme korištene za njihovo generiranje. Opisane su i metode obrana kojima štitimo duboke neuronske mreže, kako bi postale robusnije. Provedeni su eksperimenti kojima je utvrđena učinkovitost suparničkih napada i obrana od njih, a rad je zaključen objašnjenjem dobivenih rezultata.
Abstract (english)
This thesis investigates adversarial attacks on deep neural networks used for computer vision problems. Adversarial attacks modify input data in order to cause the machine learning model to make incorrect conclusions. The characteristic of these attacks is that the changes made to the input data are nearly imperceptible to humans, while significantly impacting machine learning model. The introduction of the thesis provides a detailed explanation of deep neural networks, their functioning and their vulnerability to adversarial attacks. Later in the thesis, various methods of creating adversarial attacks are explained in detail, including the specific algorithms used for generating them. Defense methods are described in order to protect deep neural networks and make them more robust. Various experiments have been conducted to evaluate the effectiveness of adversarial attacks and defenses against them, and the thesis is concluded by interpreting the obtained results
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:664117
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 on2023-10-11 08:53:40