prikaz prve stranice dokumenta Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki
No public access
master's thesis
Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:370421
Stanić, Mateo
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Stanić, M. (2023). Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:370421

Stanić, Mateo. "Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:370421

Stanić, Mateo. "Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:370421

Stanić, M. (2023). 'Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:370421

Stanić M. Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:370421

M. Stanić, "Napadi na neuronske mreže korištenjem dubokih prikrivenih značajki", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:370421

Metadata
TitleNapadi na neuronske mreže korištenjem dubokih prikrivenih značajki
Title (english)Deep Hidden Feature Backdoor Attacks Upon Neural Networks
AuthorMateo Stanić
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-03, Croatia
Abstract
U ovom radu razmatramo napad umetanja stražnjih vrata u modelima dubokog učenja. Cilj napada je da za „otrovane“ primjerke model daje ciljnu klasu dok za čiste uzorke funkcionira kao normalan klasifikacijski model. Popratni cilj napada u ovom radu je također ostvariti kvalitetan okidač za stvaranje otrovanih primjeraka te korištenjem naučenih značajki međuslojeva ostvariti veću „nevidljivost“ od standardnih napada. Opisana je teorijska podloga te implementacija u programskim okruženjima. Napadi su testirani na dva modela i dva poznata skupa podataka i uspoređeni s ostalim vrstama napada. Razmotrili smo ograničenja napada i implementacije te donijeli zaključke o uspješnosti izvedenog napada.
Abstract (english)
In this paper, we consider backdoor attacks in deep learning models. The aim of the attack is that for "poisoned" samples the model predicts the target class, while for clean samples it functions as a normal classification model. The goal of the attack in this work is also to achieve a high-quality trigger for the creation of poisoned samples and to achieve greater "invisibility" than standard attacks by using the learned features of the intermediate layers. The theoretical background along with its implementation in programming environments is described in detail. The attacks were tested on two models and two known datasets and compared with other types of attacks. We considered the limitations of the attack and its implementation, and reached conclusions about the success of the attack.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:370421
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 on2023-10-11 10:30:55