prikaz prve stranice dokumenta Neprijateljski napadi na modele za klasifikaciju slike
No public access
undergraduate thesis
Neprijateljski napadi na modele za klasifikaciju slike
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:310143
Sović, Iva
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Sović, I. (2019). Neprijateljski napadi na modele za klasifikaciju slike (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:310143

Sović, Iva. "Neprijateljski napadi na modele za klasifikaciju slike." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:310143

Sović, Iva. "Neprijateljski napadi na modele za klasifikaciju slike." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:310143

Sović, I. (2019). 'Neprijateljski napadi na modele za klasifikaciju slike', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:310143

Sović I. Neprijateljski napadi na modele za klasifikaciju slike [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 December 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:310143

I. Sović, "Neprijateljski napadi na modele za klasifikaciju slike", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:310143

Metadata
TitleNeprijateljski napadi na modele za klasifikaciju slike
Title (english)Adversarial Attacks in Image Classification
AuthorIva Sović
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarin Oršić (član povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad dotiče temu diferencijabilnog programiranja kao novog pogleda na područje neuronskih mreža. Definiraju se neprijateljski napadi i opisuje njihova podjela na usmjerene i neusmjerene napade. Implementirana su tri modela na kojima je testirana dana teoretska podloga: dva potpuno povezana modela (s jednim i dva skrivena sloja) i konvolucijski model. U nastavku je opisano treniranje robusnih modela. Detaljno su opisani FGSM i PGD napadi. Predstavljen je kratak osvrt na programski okvir TensorFlow i skup podataka MNIST koji je korišten za testiranje teoretskih kocepata opisanih u radu. Potpuno povezani modeli (s jednim odnosno dva skrivena sloja) i konvolucijski model prilikom normalnog treniranja postižu točnost od oko 87%, 88% odnosno 97%. Prilikom neprijateljskih napada isti modeli za apsolutnu vrijednost neprijateljske perturbacije od 0.1 postižu točnost od 0.6%, 0.8% odnosno 2.3% kada se radi o PGD napadima. Za FGSM napade i jednaku vrijednost perturbacije točnosti su 3.6%, 1.3% i 27.9%. Treniranjem robusnih modela postignuto je poboljšanje u točnosti prilikom napada na 87% za vrijednost perturbacije 0.3. Dodatno, u radu je prikazana i programska implementacija opisanih napada.
Abstract (english)
This work addresses the topic of differentiable programming as a new shift in perspective on the field of neural networks. The definition of adversarial attacks are presented, as well as their classification into two major groups: targeted and untargeted attacks. In the scope of this work, three different models were implemented and used for testing the theoretical background: two dense fully connected neural networks (with one and two hidden layers, respectively), and one convolutional model. The process of training these models is given, as well as a detailed description of the FGSM and PGD types of attacks. Further, the work presents a brief introduction to the TensorFlow library and the MNIST dataset. During the normal training procedure, the tested models achieved accuracies of 87%, 88% and 97% (respectively), while under adversarial attacks with perturbation of 0.1 the same models achieve accuracies of 0.6%, 0.8% and 2.3% (respectively) for the PGD type, and 3.6%, 1.3% and 27.9% for the FGSM type (respectively). By training the robust model, the accuracy was significantly improved, up to 87% for the perturbation value of 0.3. Additionally, this work also presents the software implementation of the described adversarial attacks.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:310143
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 on2020-01-07 16:57:32