Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification

Thesis (M.S.) -- Computer Science, January 2024.

Saved in:
Bibliographic Details
Main Author: Abbass, Ali (author)
Format: masterThesis
Published: 2024
Subjects:
Online Access:http://hdl.handle.net/10725/15956
https://doi.org/10.26756/th.2023.685
http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.php
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513471809323008
author Abbass, Ali
author_facet Abbass, Ali
author_role author
dc.creator.none.fl_str_mv Abbass, Ali
dc.date.none.fl_str_mv 2024-08-05T07:48:07Z
2024-08-05T07:48:07Z
2024
2024-01-15
dc.identifier.none.fl_str_mv http://hdl.handle.net/10725/15956
https://doi.org/10.26756/th.2023.685
http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.php
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Lebanese American University
dc.rights.*.fl_str_mv info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Deep learning (Machine learning) -- Case studies
Computer security -- Case studies
Data encryption (Computer science)
Lebanese American University -- Dissertations
Dissertations, Academic
dc.title.none.fl_str_mv Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
dc.type.none.fl_str_mv Thesis
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/masterThesis
description Thesis (M.S.) -- Computer Science, January 2024.
eu_rights_str_mv openAccess
format masterThesis
id LAURepo_b107497f45a268dccbcde88882f72d0f
language_invalid_str_mv en
network_acronym_str LAURepo
network_name_str Lebanese American University repository
oai_identifier_str oai:laur.lau.edu.lb:10725/15956
publishDate 2024
publisher.none.fl_str_mv Lebanese American University
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image ClassificationAbbass, AliDeep learning (Machine learning) -- Case studiesComputer security -- Case studiesData encryption (Computer science)Lebanese American University -- DissertationsDissertations, AcademicThesis (M.S.) -- Computer Science, January 2024.The field of deep learning is facing some complex challenges when it comes to balancing sensitive data with privacy and security. With the emergence of quantum computers, encryption vulnerabilities have become a major concern. However, there is a promising solution in the form of fully homomorphic encryption (FHE) that enables encryption without decryption, creating a secure environment. To further enhance the security of deep learning models, we can employ techniques like conditional GANs. We are excited to present a novel PPDL approach for image classification that integrates FHE with adversarial learning to improve resilience. However, it is essential to note such an approach comes with a high computational cost and longer runtime. Nonetheless, it is a small price to pay for the extra layer of security it provides. . Our Research combined fully homomorphic encryption and adversarial machine learning to develop a reliable and accurate model. We protected sensitive information with CKKS encryption. The custom dataset, created with Conditional GANS, showed a 94% accuracy rate when tested with a CNN model. However, when we encrypted the model and dataset using CKKS, the accuracy dropped slightly to 92%. Our findings hold promise for future research and we are excited to share them with you.1 online resource (xi, 60 leaves): ill. (some col.)Includes bibliographical references (leaves 52-60)Lebanese American University2024-08-05T07:48:07Z2024-08-05T07:48:07Z20242024-01-15Thesisinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesishttp://hdl.handle.net/10725/15956https://doi.org/10.26756/th.2023.685http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.phpeninfo:eu-repo/semantics/openAccessoai:laur.lau.edu.lb:10725/159562024-12-06T06:24:41Z
spellingShingle Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
Abbass, Ali
Deep learning (Machine learning) -- Case studies
Computer security -- Case studies
Data encryption (Computer science)
Lebanese American University -- Dissertations
Dissertations, Academic
status_str publishedVersion
title Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
title_full Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
title_fullStr Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
title_full_unstemmed Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
title_short Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
title_sort Secure and Robust Deep Learning Using Homomorphic Encryption and Adversarial Approach for Image Classification
topic Deep learning (Machine learning) -- Case studies
Computer security -- Case studies
Data encryption (Computer science)
Lebanese American University -- Dissertations
Dissertations, Academic
url http://hdl.handle.net/10725/15956
https://doi.org/10.26756/th.2023.685
http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.php