Implementation of real-time learning on homomorphically encrypted visual inputs

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.

Bibliografische gegevens
Hoofdauteurs:	Bhuiyan, Emtiaz MD Tafsir, Rahman, Mushfiqur, Mondal, Sudipta, Warech, Sadman
Andere auteurs:	Hossain, Muhammad Iqbal
Formaat:	Thesis
Taal:	English
Gepubliceerd in:	Brac University 2021
Onderwerpen:	Homomorphic Encryption Privacy preserving Reinforcement Learning Deep Q Learning
Online toegang:	http://hdl.handle.net/10361/14982

id	10361-14982
record_format	dspace
spelling	10361-149822022-01-26T10:21:49Z Implementation of real-time learning on homomorphically encrypted visual inputs Bhuiyan, Emtiaz MD Tafsir Rahman, Mushfiqur Mondal, Sudipta Warech, Sadman Hossain, Muhammad Iqbal Mukta, Jannatun Noor Department of Computer Science and Engineering, Brac University Homomorphic Encryption Privacy preserving Reinforcement Learning Deep Q Learning Reinforcement Learning This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021. Cataloged from PDF version of thesis. Includes bibliographical references (pages 53-56). It’s challenging to provide security for cloud-based services, especially for cloud processing services, due to the fact that typical encryption techniques do not al low for calculation on encrypted data. The formation of Homomorphic Encryption techniques shows significant possibilities of incorporating encrypted computation on cloud infrastructures. This enables owners to outsource computation over confiden tial data to cloud vendors. Control and synthesis tasks of sensitive systems like traffic light control, article recommendation for online users and potentially, robot’s action determination can be delegated to a cloud-based Reinforcement Learning agent. In this study, we designed two Deep Reinforcement Learning agents that work on ciphertexts using Homomorphic Encryption. Both agents take encrypted state images and produce encrypted actions. One learns on plain data but evaluates on encrypted inputs, while the other one operates fully on encrypted space. The performance of both agents is compared against plaintext RL agents with identical parameters. The paper also describes possible architectures for such systems. Emtiaz MD Tafsir Bhuiyan Mushfiqur Rahman Sudipta Mondal Sadman Warech B. Computer Science 2021-09-07T10:03:32Z 2021-09-07T10:03:32Z 2021 2021-06 Thesis ID 16301049 ID 20241040 ID 17301224 ID 16301115 http://hdl.handle.net/10361/14982 en Brac 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. 56 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Homomorphic Encryption Privacy preserving Reinforcement Learning Deep Q Learning Reinforcement Learning
spellingShingle	Homomorphic Encryption Privacy preserving Reinforcement Learning Deep Q Learning Reinforcement Learning Bhuiyan, Emtiaz MD Tafsir Rahman, Mushfiqur Mondal, Sudipta Warech, Sadman Implementation of real-time learning on homomorphically encrypted visual inputs
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.
author2	Hossain, Muhammad Iqbal
author_facet	Hossain, Muhammad Iqbal Bhuiyan, Emtiaz MD Tafsir Rahman, Mushfiqur Mondal, Sudipta Warech, Sadman
format	Thesis
author	Bhuiyan, Emtiaz MD Tafsir Rahman, Mushfiqur Mondal, Sudipta Warech, Sadman
author_sort	Bhuiyan, Emtiaz MD Tafsir
title	Implementation of real-time learning on homomorphically encrypted visual inputs
title_short	Implementation of real-time learning on homomorphically encrypted visual inputs
title_full	Implementation of real-time learning on homomorphically encrypted visual inputs
title_fullStr	Implementation of real-time learning on homomorphically encrypted visual inputs
title_full_unstemmed	Implementation of real-time learning on homomorphically encrypted visual inputs
title_sort	implementation of real-time learning on homomorphically encrypted visual inputs
publisher	Brac University
publishDate	2021
url	http://hdl.handle.net/10361/14982
work_keys_str_mv	AT bhuiyanemtiazmdtafsir implementationofrealtimelearningonhomomorphicallyencryptedvisualinputs AT rahmanmushfiqur implementationofrealtimelearningonhomomorphicallyencryptedvisualinputs AT mondalsudipta implementationofrealtimelearningonhomomorphicallyencryptedvisualinputs AT warechsadman implementationofrealtimelearningonhomomorphicallyencryptedvisualinputs
_version_	1814309497850560512

Implementation of real-time learning on homomorphically encrypted visual inputs

Gelijkaardige items