prikaz prve stranice dokumenta Akustična kriptoanaliza tipkovnica
  Download
PDF 8.1 MB
master's thesis
Akustična kriptoanaliza tipkovnica
2023. urn:nbn:hr:190:619221
Breš, Barbara
University of Rijeka
Faculty of Engineering

Cite this document

Breš, B. (2023). Akustična kriptoanaliza tipkovnica (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:619221

Breš, Barbara. "Akustična kriptoanaliza tipkovnica." Master's thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:619221

Breš, Barbara. "Akustična kriptoanaliza tipkovnica." Master's thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:619221

Breš, B. (2023). 'Akustična kriptoanaliza tipkovnica', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 05 May 2024, https://urn.nsk.hr/urn:nbn:hr:190:619221

Breš B. Akustična kriptoanaliza tipkovnica [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2023 [cited 2024 May 05] Available at: https://urn.nsk.hr/urn:nbn:hr:190:619221

B. Breš, "Akustična kriptoanaliza tipkovnica", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:190:619221

Please login to the repository to save this object to your list.
Metadata
TitleAkustična kriptoanaliza tipkovnica
Title (english)Acoustic Cryptanalysis
AuthorBarbara Breš
MentorJonatan Lerga (mentor)
Committee memberRenato Filjar (predsjednik povjerenstva)
Committee memberZoran Čarija (član povjerenstva)
Committee memberJonatan Lerga (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2023, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu predstavljena je teorija i povijest akustične kriptoanalize kao i praktičan primjer primjene akustične kriptoanalize kroz kod pisan u Pythonu. Korištenjem Mel-frekvencijskih kepstrum koeficijenata za izvlačenje značajki iz snimki tipkanja te linearne neuronske mreže, model je uspio s oko 97\% točnosti predvidjeti tipkani znak iz označenih podataka dvije različite tipkovnice. S visokom točnosti najbolji model je uspio rekonstruirati natipkani tekst iz neoznačenih podataka tipkanih na obje tipkovnice.
Abstract (english)
In this paper, the theory and history of acoustic cryptanalysis is presented, as well as a practical example of the application of acoustic cryptanalysis through code written in Python. Using Mel-frequency cepstral coefficients to extract features from typing recordings and a linear neural network, the model was able to predict the typed character from the labeled data of two different keyboards with about 97\% accuracy. With high accuracy, the best model was able to reconstruct typed text from unlabeled data typed on both keyboards.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:619221
Study programmeTitle: Computer Engineering
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 conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2023-09-12 18:27:58