A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated Learning
With the widespread use of smartphones and wearable devices, Mobile Crowdsourcing (MCS) has become a powerful method for gathering and processing data from various users. MCS offers several advantages, including improved mobility, scalability, cost-effectiveness, and the utilization of collective hu...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10770208/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846128524517179392 |
|---|---|
| author | Mohamad Wazzeh Hakima Ould-Slimane Chamseddine Talhi Azzam Mourad Mohsen Guizani |
| author_facet | Mohamad Wazzeh Hakima Ould-Slimane Chamseddine Talhi Azzam Mourad Mohsen Guizani |
| author_sort | Mohamad Wazzeh |
| collection | DOAJ |
| description | With the widespread use of smartphones and wearable devices, Mobile Crowdsourcing (MCS) has become a powerful method for gathering and processing data from various users. MCS offers several advantages, including improved mobility, scalability, cost-effectiveness, and the utilization of collective human intelligence. However, ensuring the authenticity of users throughout the data collection process remains a challenge. Current authentication methods, such as traditional PIN codes, two-factor authentication, and biometric authentication, often struggle to provide continuous verification while adequately protecting user privacy. This paper addresses this issue by proposing a new continuous authentication approach based on Federated Learning. This approach combines continuous identity verification with privacy preservation benefits, allowing for the ongoing validation of user authenticity during data collection while improving authentication accuracy. We also discuss the non-Independently and Identically Distributed issue in Federated Learning and employ transfer learning techniques based on feature extraction to enhance the performance of the authentication models. We conducted extensive experiments using various datasets to evaluate the effectiveness of our proposed method. The results of this study demonstrate its potential to enhance the security and privacy of MCS systems. |
| format | Article |
| id | doaj-art-31b3e3e0c4dc4c75bc0cfea495268998 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-31b3e3e0c4dc4c75bc0cfea4952689982024-12-11T00:04:50ZengIEEEIEEE Access2169-35362024-01-011217823717825010.1109/ACCESS.2024.350769510770208A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated LearningMohamad Wazzeh0https://orcid.org/0009-0002-8710-3434Hakima Ould-Slimane1https://orcid.org/0000-0002-2694-6959Chamseddine Talhi2https://orcid.org/0000-0003-2264-8265Azzam Mourad3https://orcid.org/0000-0001-9434-5322Mohsen Guizani4https://orcid.org/0000-0002-8972-8094Department of Software and IT Engineering, École de Technologie Supérieure (ÉTS), Montreal, QC, CanadaDepartment of Mathematics and Computer Science, Université du Québec à Trois-Rivières (UQTR), Trois-Rivières, QC, CanadaDepartment of Software and IT Engineering, École de Technologie Supérieure (ÉTS), Montreal, QC, CanadaDepartment of Computer Science, KU 6G Research Center, Khalifa University, Abu Dhabi, United Arab EmiratesMachine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab EmiratesWith the widespread use of smartphones and wearable devices, Mobile Crowdsourcing (MCS) has become a powerful method for gathering and processing data from various users. MCS offers several advantages, including improved mobility, scalability, cost-effectiveness, and the utilization of collective human intelligence. However, ensuring the authenticity of users throughout the data collection process remains a challenge. Current authentication methods, such as traditional PIN codes, two-factor authentication, and biometric authentication, often struggle to provide continuous verification while adequately protecting user privacy. This paper addresses this issue by proposing a new continuous authentication approach based on Federated Learning. This approach combines continuous identity verification with privacy preservation benefits, allowing for the ongoing validation of user authenticity during data collection while improving authentication accuracy. We also discuss the non-Independently and Identically Distributed issue in Federated Learning and employ transfer learning techniques based on feature extraction to enhance the performance of the authentication models. We conducted extensive experiments using various datasets to evaluate the effectiveness of our proposed method. The results of this study demonstrate its potential to enhance the security and privacy of MCS systems.https://ieeexplore.ieee.org/document/10770208/Continuous authenticationfederated learningmobile crowdsourcingprivacy-preservingtransfer learningunique label |
| spellingShingle | Mohamad Wazzeh Hakima Ould-Slimane Chamseddine Talhi Azzam Mourad Mohsen Guizani A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated Learning IEEE Access Continuous authentication federated learning mobile crowdsourcing privacy-preserving transfer learning unique label |
| title | A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated Learning |
| title_full | A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated Learning |
| title_fullStr | A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated Learning |
| title_full_unstemmed | A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated Learning |
| title_short | A Continuous Authentication Approach for Mobile Crowdsourcing Based on Federated Learning |
| title_sort | continuous authentication approach for mobile crowdsourcing based on federated learning |
| topic | Continuous authentication federated learning mobile crowdsourcing privacy-preserving transfer learning unique label |
| url | https://ieeexplore.ieee.org/document/10770208/ |
| work_keys_str_mv | AT mohamadwazzeh acontinuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT hakimaouldslimane acontinuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT chamseddinetalhi acontinuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT azzammourad acontinuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT mohsenguizani acontinuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT mohamadwazzeh continuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT hakimaouldslimane continuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT chamseddinetalhi continuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT azzammourad continuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning AT mohsenguizani continuousauthenticationapproachformobilecrowdsourcingbasedonfederatedlearning |