Please use this identifier to cite or link to this item:
|Title:||Convolutional neural network biometric cryptosystem for the protection of the blockchain's private key||Authors:||Albakri, Alfaisal||Advisors:||Mokbel, Chafic||Subjects:||Blockchains (Databases)
Transaction systems (Computer systems)
Electronic funds transfers
University of Balamand--Dissertations
Blockchain technology has attracted enormous attention in the previous years as a secure way to protect transactions in different processes. It has been particularly used to define cryptocurrencies. While inherently secure against classical single node attacks, the blockchain cryptocurrencies have recently been subject to attacks by malwares able to capture a single user wallet and its included keys. In this approach, we propose the use of biometric cryptosystems to control the access to the wallets on single machines. After a brief description of the blockchain, the cryptocurrencies and the possible attacks, our method describes the use of convolutional neural network face recognition as a tool to extract biometric features that help in a key binding approach to protect the personal data in the wallet. Experiments have been conducted on three independent face datasets and the results obtained are satisfactory. The equal error rate between false acceptance and false rejection has been as low as 0% when testing on images from the same dataset used for the training of the convolutional neural network. This generalizes well when experimenting on two other independent datasets. These results prove that face cryptosystems can be possibly used to protect the access on sensitive data existing in the wallets of many cryptocurrencies.
Includes bibliographical references (p. 51-57).
|URI:||https://scholarhub.balamand.edu.lb/handle/uob/4016||Rights:||This object is protected by copyright, and is made available here for research and educational purposes. Permission to reuse, publish, or reproduce the object beyond the personal and educational use exceptions must be obtained from the copyright holder||Ezproxy URL:||Link to full text||Type:||Thesis|
|Appears in Collections:||UOB Theses and Projects|
Show full item record
checked on Nov 30, 2023
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.