Mostakim, MoinJoy, Tanvir AhmedAhmed, Sultan Gias UddinAhmed, Mir AbrarIslam, Sazzad ULNima, Menuka Tasnim2021-09-022021-09-0220212021-06ID 17101039ID 16301151ID 17101197ID 17101457ID 17101414http://hdl.handle.net/10361/14962Cataloged from PDF version of thesis.Includes bibliographical references (pages 49-51).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.The fast-growing cryptocurrency system is changing the financial world with its ensured blockchain technology. It’s specific use in expounding cryptocurrencies is highly acknowledged in the modern world, although the acceptance is growing in several other domains such as the Internet of Things (IoT), Artificial Intelligence, Fintech, and many other fields. Proof of Work (POW), which contains a digital ledger of transactions, plays a vital role in blockchain security. In addition, Blockchain uses a changeable public key which ensures an extra layer of privacy by containing individual user identity. Although, malwares has been planted to encapsulate the single user identity and the keys included in it. Focusing on Blockchain’s significant features, possible vulnerabilities in the system and cryptography, we will emphasize the deep learning process to generate hybrid public key in the blockchain system which will be binding with the face recognition features delivering to a compact & secured cryptosystem leading towards protection of sensitive data. After successfully generating the public & private key, we were able to implement those keys in blockchain system creating a person’s wallet and verifying the signatures. Our success rate in generating keys was close to 100% which were implemented in blockchain.51 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.BlockchainDeep LearningPublic Key CryptographyHybrid Public KeyFacial RecognitionDeep LearningThesis