prikaz prve stranice dokumenta Napadi na neuronske mreže umetanjem stražnjih vrata
No public access
master's thesis
Napadi na neuronske mreže umetanjem stražnjih vrata
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. urn:nbn:hr:168:322075
Milić, Jura
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Milić, J. (2024). Napadi na neuronske mreže umetanjem stražnjih vrata (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:322075

Milić, Jura. "Napadi na neuronske mreže umetanjem stražnjih vrata." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:322075

Milić, Jura. "Napadi na neuronske mreže umetanjem stražnjih vrata." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:322075

Milić, J. (2024). 'Napadi na neuronske mreže umetanjem stražnjih vrata', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:322075

Milić J. Napadi na neuronske mreže umetanjem stražnjih vrata [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 November 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:322075

J. Milić, "Napadi na neuronske mreže umetanjem stražnjih vrata", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:322075

Metadata
TitleNapadi na neuronske mreže umetanjem stražnjih vrata
Title (english)Backdoor attacks on deep neural networks
AuthorJura Milić
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 country2024-07-15, Croatia
Abstract
U posljednjim godinama, umjetna inteligencija napravila je velike korake u raznim domenama uključujući i detekciju objekata, što je dovelo do ključnih dijelova u svakodnevnim slučajevima poput samovozećih automobila i sigurnosnih sustava. No, robustnost i sigurnost tih modela su postali veliki razlog za brigu, pogotovo s dočekom sofisticiranih vektora napada poput backdoor napada. Ovaj rad će istražiti implementaciju backdoor napada na modele detekcije objekata, s naglaskom na Faster R-CNN modele, koji su vrlo iskorišteni u tom polju. Uspoređujemo trenutnu situaciju u umjetnoj inteligenciji s već dobro razvijenom sigurnosti u kriptografiji, čime naglašavamo potrebu za rigoroznim obranama protiv takvih napada. Istraživanje će ući u detalje četiri tipa backdoor napada: OGA (napad dodavanja objekta), RMA (napad krive klasifikacije unutar regije), GMA (napad krive klasifikacije na globalnoj razini), te ODA (napad micanja objekta). Generiranjem otrovanih skupova podataka i treniranjem Faster R-CNN modela na tim skupovima podataka, analizirat ćemo utjecaj tih napada. Učinkovitost tih napada je evauluirana korištenjem metrika poput srednje prosječne preciznosti (mAP) i stopom uspješnosti napada (ASR), čime naglašavamo osjetljivost modela detekcije objekata na backdoor napade.
Abstract (english)
In the last few years, artificial intelligence has made great strides in various domains including object detection which led to key components in every-day applications like self driving cars and security systems. But, the robustness and security of these models have become a cause for concern, especially with the arrival of sophisticated attack vectors like backdoor attacks. In this work, we examine an implementation of a backdoor attack on object detection models with emphasis on Faster R-CNN models which have been thoroughly used and researched in the field. We compare the current state of artificial intelligence with cryptography, emphasizing the need for rigorous defenses against such attacks. The research of this work will go into details on four different types of backdoor attacks: OGA (object generation attack), RMA (regional misclassification attack), GMA (global misclassification attack), and ODA (object dissapearance attack). Generating posioned datasets and training a Faster R-CNN model on these datasets, we will analyze the impact of such attacks. The efficiency of these attacks will be evaluated using metrics such as mAP (mean average precision) and ASR (attack success rate). These metrics will emphasize the vulnerability of object detection models to backdoor attacks.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:322075
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 on2024-10-12 21:37:21