prikaz prve stranice dokumenta Generativne suparničke mreže za izradu neprijateljskih uzoraka
No public access
master's thesis
Generativne suparničke mreže za izradu neprijateljskih uzoraka
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:307052
Dujmović, Bruna
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Dujmović, B. (2022). Generativne suparničke mreže za izradu neprijateljskih uzoraka (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:307052

Dujmović, Bruna. "Generativne suparničke mreže za izradu neprijateljskih uzoraka." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:307052

Dujmović, Bruna. "Generativne suparničke mreže za izradu neprijateljskih uzoraka." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:307052

Dujmović, B. (2022). 'Generativne suparničke mreže za izradu neprijateljskih uzoraka', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 17 May 2024, https://urn.nsk.hr/urn:nbn:hr:168:307052

Dujmović B. Generativne suparničke mreže za izradu neprijateljskih uzoraka [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 May 17] Available at: https://urn.nsk.hr/urn:nbn:hr:168:307052

B. Dujmović, "Generativne suparničke mreže za izradu neprijateljskih uzoraka", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:307052

Metadata
TitleGenerativne suparničke mreže za izradu neprijateljskih uzoraka
Title (english)Generative adversarial networks for generating adversarial examples
AuthorBruna Dujmović
MentorDomagoj Jakobović (mentor)
Committee memberDomagoj Jakobović (predsjednik povjerenstva)
Committee memberMarko Đurasević (član povjerenstva)
Committee memberSiniša Šegvić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-06-28, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Suvremeni klasifikacijski modeli, unatoč zavidnim rezultatima na nizu skupova podataka, i dalje znaju biti podložni napadima neprijateljskim uzorcima. Jedan od načina oblikovanja tih ciljano izmijenjenih uzoraka oslanja se na generativne suparničke mreže. Dodavanjem klasifikatora koji se želi napasti u osnovnu GAN arhitekturu, tzv. AdvGAN sposoban je proizvesti uspješne slikovne i zvučne neprijateljske uzorke uvjetovane odgovarajućim originalnim uzorcima. Uz izvornu AdvGAN inačicu, prozvanu image-to-perturbation odnosno audio-to-perturbation AdvGAN-om, razvijena je i noise-to-perturbation inačica koja proizvodi neprijateljske uzorke iz vektora nasumično generiranog šuma. Pokazalo se kako razvijeni AdvGAN-ovi djeluju prilikom izrade uzoraka za MNIST te Speech Commands skupove podataka.
Abstract (english)
Modern classification models, despite the enviable results they achieve on a number of datasets, can still be vulnerable to attacks using adversarial examples. One way of generating these intentionally modified examples relies on generative adversarial networks. By incorporating the targeted classifier into the basic GAN architecture, the so-called AdvGAN is capable of producing successful image and audio adversarial examples conditioned on their unmodified counterparts. In addition to the original AdvGAN version, dubbed "image-to-perturbation" or "audio-to-perturbation" AdvGAN, a "noise-to-perturbation" version has been developed that produces adversarial examples out of random noise vectors. This thesis shows how the developed AdvGANs perform when creating examples for the MNIST and Speech Commands datasets.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:307052
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 on2023-01-13 14:51:29