prikaz prve stranice dokumenta Obrane klasifikacijskih modela od napada trovanjem podataka
No public access
undergraduate thesis
Obrane klasifikacijskih modela od napada trovanjem podataka
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:580034
Glavinić, Luka
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Glavinić, L. (2023). Obrane klasifikacijskih modela od napada trovanjem podataka (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:580034

Glavinić, Luka. "Obrane klasifikacijskih modela od napada trovanjem podataka." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:580034

Glavinić, Luka. "Obrane klasifikacijskih modela od napada trovanjem podataka." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:580034

Glavinić, L. (2023). 'Obrane klasifikacijskih modela od napada trovanjem podataka', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 16 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:580034

Glavinić L. Obrane klasifikacijskih modela od napada trovanjem podataka [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 July 16] Available at: https://urn.nsk.hr/urn:nbn:hr:168:580034

L. Glavinić, "Obrane klasifikacijskih modela od napada trovanjem podataka", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:580034

Metadata
TitleObrane klasifikacijskih modela od napada trovanjem podataka
Title (english)Defence of classification models from data-poisoning attacks
AuthorLuka Glavinić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
Committee memberZorana Doždor (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
U ovom radu je proučena funkcionalnost rezidualnog konvolucijskog modela ResNet-18. Objašnjene su namjene i vrste napada otrovanim podacima ovakvog modela. Detaljno objašnjene dvije metode za obranu od ovakvih napada i modula koje one koriste pri svom radu, a to su sigurno treniranje, kojim se trenira ekstraktor značajki i klasifikator i uklanjanje otrovanja iz modela. Na kraju su pokazani eksperimenti i diskutirani rezultati eksperimenata.
Abstract (english)
In this paper, the functionality of the residual convolutional model ResNet-18 was studied. The purposes and types of poisoned data attacks of this model are explained. Two methods for defense against such attacks and the modules they use in their work are explained in detail: safe training, which trains the feature extractor and classifier and removes poisoning from the model. At the end, the experiments were shown and the results of the experiments were discussed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:580034
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 10:03:55