HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework

Abstract Protecting user privacy is essential in machine learning research, especially in the context of data collection. Federated learning (FL), which trains models across decentralized devices without sharing raw data, has emerged as a promising solution. However, FL is still vulnerable to securi...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammad Moshawrab, Mehdi Adda, Abdenour Bouzouane, Hussein Ibrahim, Ali Raad
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Cybersecurity
Subjects:
Online Access:https://doi.org/10.1186/s42400-024-00341-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849691311159902208
author Mohammad Moshawrab
Mehdi Adda
Abdenour Bouzouane
Hussein Ibrahim
Ali Raad
author_facet Mohammad Moshawrab
Mehdi Adda
Abdenour Bouzouane
Hussein Ibrahim
Ali Raad
author_sort Mohammad Moshawrab
collection DOAJ
description Abstract Protecting user privacy is essential in machine learning research, especially in the context of data collection. Federated learning (FL), which trains models across decentralized devices without sharing raw data, has emerged as a promising solution. However, FL is still vulnerable to security threats, including inference attacks, which have been underexplored in comparison to poisoning and backdoor attacks that have received more attention in existing research. To address these vulnerabilities, this paper proposes a novel aggregation framework called homomorphic and polymorphic federated learning aggregation of parameters (HP_FLAP). HP_FLAP integrates both homomorphic and polymorphic encryption to enhance the security and privacy of FL. Homomorphic encryption allows the server to perform aggregation on encrypted parameters without decrypting them, ensuring that sensitive information is protected during the aggregation process. Polymorphic encryption further strengthens security by using different encryption keys for each set of parameters, mitigating the risk of system-wide compromise in case a key is leaked. This dual encryption approach effectively counters inference attacks while maintaining robust protections against other security threats. The framework is evaluated using multiple models, including logistic regression, Gaussian Naive Bayes, Stochastic Gradient Descent, and Multi-Layer Perceptron, demonstrating HP_FLAP’s ability to enhance both security and privacy in FL environments.
format Article
id doaj-art-09952e6fd3c34a6da9d5c420f5dae3df
institution DOAJ
issn 2523-3246
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Cybersecurity
spelling doaj-art-09952e6fd3c34a6da9d5c420f5dae3df2025-08-20T03:21:03ZengSpringerOpenCybersecurity2523-32462025-06-018112410.1186/s42400-024-00341-6HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters frameworkMohammad Moshawrab0Mehdi Adda1Abdenour Bouzouane2Hussein Ibrahim3Ali Raad4Mathematics, Informatics and Engineering Department, University of Quebec at RimouskiMathematics, Informatics and Engineering Department, University of Quebec at RimouskiMathematics and Informatics Department, University of Quebec at ChicoutimiInstitut Technologique de Maintenance IndustrielleFaculty of Science and Arts, Islamic University of Lebanon, WardaniyehAbstract Protecting user privacy is essential in machine learning research, especially in the context of data collection. Federated learning (FL), which trains models across decentralized devices without sharing raw data, has emerged as a promising solution. However, FL is still vulnerable to security threats, including inference attacks, which have been underexplored in comparison to poisoning and backdoor attacks that have received more attention in existing research. To address these vulnerabilities, this paper proposes a novel aggregation framework called homomorphic and polymorphic federated learning aggregation of parameters (HP_FLAP). HP_FLAP integrates both homomorphic and polymorphic encryption to enhance the security and privacy of FL. Homomorphic encryption allows the server to perform aggregation on encrypted parameters without decrypting them, ensuring that sensitive information is protected during the aggregation process. Polymorphic encryption further strengthens security by using different encryption keys for each set of parameters, mitigating the risk of system-wide compromise in case a key is leaked. This dual encryption approach effectively counters inference attacks while maintaining robust protections against other security threats. The framework is evaluated using multiple models, including logistic regression, Gaussian Naive Bayes, Stochastic Gradient Descent, and Multi-Layer Perceptron, demonstrating HP_FLAP’s ability to enhance both security and privacy in FL environments.https://doi.org/10.1186/s42400-024-00341-6Federated machine learningAggregation algorithmsPolymorphic encryptionHomomorphic encryptionSecurityPrivacy
spellingShingle Mohammad Moshawrab
Mehdi Adda
Abdenour Bouzouane
Hussein Ibrahim
Ali Raad
HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework
Cybersecurity
Federated machine learning
Aggregation algorithms
Polymorphic encryption
Homomorphic encryption
Security
Privacy
title HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework
title_full HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework
title_fullStr HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework
title_full_unstemmed HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework
title_short HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework
title_sort hp flap homomorphic and polymorphic federated learning aggregation of parameters framework
topic Federated machine learning
Aggregation algorithms
Polymorphic encryption
Homomorphic encryption
Security
Privacy
url https://doi.org/10.1186/s42400-024-00341-6
work_keys_str_mv AT mohammadmoshawrab hpflaphomomorphicandpolymorphicfederatedlearningaggregationofparametersframework
AT mehdiadda hpflaphomomorphicandpolymorphicfederatedlearningaggregationofparametersframework
AT abdenourbouzouane hpflaphomomorphicandpolymorphicfederatedlearningaggregationofparametersframework
AT husseinibrahim hpflaphomomorphicandpolymorphicfederatedlearningaggregationofparametersframework
AT aliraad hpflaphomomorphicandpolymorphicfederatedlearningaggregationofparametersframework