prikaz prve stranice dokumenta Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka
No public access
master's thesis
Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:970317
Herkov, Antun
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Herkov, A. (2023). Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:970317

Herkov, Antun. "Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:970317

Herkov, Antun. "Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:970317

Herkov, A. (2023). 'Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 18 February 2025, https://urn.nsk.hr/urn:nbn:hr:168:970317

Herkov A. Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2025 February 18] Available at: https://urn.nsk.hr/urn:nbn:hr:168:970317

A. Herkov, "Metode za obranu od napada na neuronske mreže pomoću augmentacije podataka", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:970317

Metadata
TitleMetode za obranu od napada na neuronske mreže pomoću augmentacije podataka
Title (english)Methods for Defense Against Backdoor Attacks Upon Neural Networks Using Data Augmentation
AuthorAntun Herkov
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
Dan je pregled sigurnosnih opasnosti koji prijete modelima dubokog učenja uz fokus na utjecaj primjene augmentacije podataka na sigurnost, metrike i performanse modela dubokog učenja. Formalno su opisani backdoor napadi na modele te je dan pregled obrambenih metoda. Za provedbu eksperimenata, razvijena je programska implementacija procesa učenja inficiranih modela te provođenja obrane u obliku augmentacije podataka točno definiranim strategijama transformacija slika u Keras i PyTorch frameworcima te je pokazan utjecaj augmentacije podataka na osiguravanje modela od umetnutoga backdoora.
Abstract (english)
An overview of security threats to deep learning models is given, with a focus on the impact of applying data augmentation on the security, metrics, and performance of deep learning models. Backdoor attacks on models are formally described and an overview of defense methods is given. To carry out the experiments, a software implementation of the process of training infected models and a defense method in the form of data augmentation with precisely defined image transformation policies was developed in Keras and PyTorch frameworks, and the impact of data augmentation on the model security from an inserted backdoor was demonstrated.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:970317
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 09:01:35