prikaz prve stranice dokumenta Algoritmi za brzo učenje na neprijateljskim primjerima
No public access
undergraduate thesis
Algoritmi za brzo učenje na neprijateljskim primjerima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:753638
Jambrović, Dominik
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Jambrović, D. (2023). Algoritmi za brzo učenje na neprijateljskim primjerima (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:753638

Jambrović, Dominik. "Algoritmi za brzo učenje na neprijateljskim primjerima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:753638

Jambrović, Dominik. "Algoritmi za brzo učenje na neprijateljskim primjerima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:753638

Jambrović, D. (2023). 'Algoritmi za brzo učenje na neprijateljskim primjerima', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 29 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:753638

Jambrović D. Algoritmi za brzo učenje na neprijateljskim primjerima [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 June 29] Available at: https://urn.nsk.hr/urn:nbn:hr:168:753638

D. Jambrović, "Algoritmi za brzo učenje na neprijateljskim primjerima", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:753638

Metadata
TitleAlgoritmi za brzo učenje na neprijateljskim primjerima
Title (english)Algorithms for fast adversarial learning
AuthorDominik Jambrović
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
Committee memberDavid Dukić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Učenje s neprijateljskim primjerima važno je za postizanje sigurnih modela. Proučavamo osnovne načine učenja s neprijateljskim primjerima (FGSM, PGD). Uočavamo i istražujemo probleme prisutne pri korištenju PGD načina učenja na kompleksnijim modelima. Razmatramo predložene nadogradnje na osnovne načine učenja s neprijateljskim primjerima (FreeAdv, FastAdv, FastAdv+, FastAdvW) i evaluiramo performanse naučenih modela. Evaluacija pokazuje da najbolje performanse postižu modeli učeni FastAdv+ i FastAdvW načinima učenja. Razmatramo mogućnost korištenja robusnih modela za detekciju zatrovanih podataka.
Abstract (english)
Adversarial learning is important for achieving secure models. We study the basic adversarial learning methods (FGSM, PGD). We observe and investigate the problems present when using the PGD learning method on more complex models. We consider proposed upgrades to the basic adversarial learning method (FreeAdv, FastAdv, FastAdv+, FastAdvW) and evaluate the performance of the trained models. The evaluation shows that the best performance is achieved by models trained using the FastAdv+ and FastAdvW learning methods. We consider the possibility of using robust models for the detection of poisoned data.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:753638
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-07-13 10:08:24