prikaz prve stranice dokumenta Neprijateljski napadi na modele za klasifikaciju slike
No public access
master's thesis
Neprijateljski napadi na modele za klasifikaciju slike
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:519031
Vukić, Krešimir
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Vukić, K. (2019). Neprijateljski napadi na modele za klasifikaciju slike (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:519031

Vukić, Krešimir. "Neprijateljski napadi na modele za klasifikaciju slike." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:519031

Vukić, Krešimir. "Neprijateljski napadi na modele za klasifikaciju slike." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:519031

Vukić, K. (2019). 'Neprijateljski napadi na modele za klasifikaciju slike', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 24 August 2024, https://urn.nsk.hr/urn:nbn:hr:168:519031

Vukić K. Neprijateljski napadi na modele za klasifikaciju slike [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 August 24] Available at: https://urn.nsk.hr/urn:nbn:hr:168:519031

K. Vukić, "Neprijateljski napadi na modele za klasifikaciju slike", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:519031

Metadata
TitleNeprijateljski napadi na modele za klasifikaciju slike
Title (english)Adversarial attacks on image classification models
AuthorKrešimir Vukić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberStjepan Groš (član povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-15, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Nadzirani diskriminativni modeli sastavni su dio mnogih sustava računalnog vida. No, poznato je da su ranjivi neprijateljskim primjerima što je neprihvatljivo za osjetljive produkcijske sustave. Upravo iz toga proizlazi važnost poznavanja njihove funkcionalnosti, razloga postojanja i mogućih obrana. U ovoj tezi opisana je nekolicina postojećh neprijateljskih napada i primjenjivih obrana. Napadi FGSM i PGD te obrana treniranja sa neprijateljskim primjerima su implementirani i testirani na MNIST i SVHN podatkovnim skupovima. Također, istražen je utjecaj različitih perturbacijskih normi na utjecaj klasifikacije.
Abstract (english)
Strongly supervised discriminative models are the principal ingredient in many computer vision applications. However, discriminative models are known for being vulnerable to adversarial examples which is unacceptable for production systems. Hence, the techniques for constructing adversarial examples and building defenses against them are a very important research topic. This thesis consists of brief descriptions of existing adversarial attacks and applicable defenses. FGSM and PGD attacks, as well as defense through adversarial training, are developed and tested on the MNIST and SVHN data sets. Also, the influence of the perturbation norm on the efficiency of the attacks is briefly described.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:519031
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 on2020-01-07 23:02:58