prikaz prve stranice dokumenta Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika
No public access
master's thesis
Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:649893
Smoljan, Dorian
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Smoljan, D. (2023). Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:649893

Smoljan, Dorian. "Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:649893

Smoljan, Dorian. "Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:649893

Smoljan, D. (2023). 'Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 17 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:649893

Smoljan D. Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 June 17] Available at: https://urn.nsk.hr/urn:nbn:hr:168:649893

D. Smoljan, "Ispitivanje sigurnosti dubokih neuronskih mreža za analizu slika", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:649893

Metadata
TitleIspitivanje sigurnosti dubokih neuronskih mreža za analizu slika
Title (english)Investigation of Security of Deep Neural Networks for Image Analysis
AuthorDorian Smoljan
MentorMarko Subašić (mentor)
Committee memberMarko Subašić (predsjednik povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
Committee memberKrešimir Križanović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-13, Croatia
Abstract
Cilj ovog rada je bio istražiti potencijalne napade i obrane na neuronske mreže za analizu slika s naglaskom na ugrađivanja stražnjih vrata u mrežu (eng. backdoor) korištenjem trovanja podataka. U tu svrhu je predstavljen niz metoda napada, te odgovarajućih obrana, te su uspoređene njihove mogućnosti i ograničenja. Dvije odabrane metode napada, statičko uzorkovanje i blending su implementirane i testirane na više različitih skupova podataka za klasifikaciju slika. Kao obrana od implementiranih metoda napada, testirane su dvije metode obrane, STRIP i Neural Cleanse. Uspoređena je učinkovitost napada te obrane, te je zaključeno da je STRIP učinkovit za većinu ali ne sve metode napada, dok se Neural Cleanse pokazala kao učinkovita metoda za sve razmatrane vrste napada. Konačno, pokazano je da se model može djelomično oporaviti koristeći rekonstruirane okidače dobivene metodom Neural Cleanse i ponovnim treniranjem.
Abstract (english)
This work aimed to explore potential attacks on neural networks for image analysis, focusing on backdoor attacks using data poisoning and suitable defense methods. A wide array of attack and defense methods was presented, and their capabilities and limitations were compared. Two selected attack methods, static sampling and blending were implemented and tested on multiple image classification datasets. Two defense methods against those attacks, STRIP and Neural Cleanse were evaluated. The efficiency of attacks and defense was compared, and it was concluded that STRIP is effective for most, but not all attack methods, and Neural Cleanse showed good performance against all attacks. Finally, it was shown that the backdoored models can be partially restored using retraining with triggers reconstructed by Neural Cleanse.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:649893
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 10:28:37