IDS for Industrial Applications: A Federated Learning Approach with Active Personalization
Internet of Things (IoT) is a concept adopted in nearly every aspect of human life, leading to an explosive utilization of intelligent devices. Notably, such solutions are especially integrated in the industrial sector, to allow the remote monitoring and control of critical infrastructure. Such glob...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/20/6743 |
| _version_ | 1797513190775455744 |
|---|---|
| author | Vasiliki Kelli Vasileios Argyriou Thomas Lagkas George Fragulis Elisavet Grigoriou Panagiotis Sarigiannidis |
| author_facet | Vasiliki Kelli Vasileios Argyriou Thomas Lagkas George Fragulis Elisavet Grigoriou Panagiotis Sarigiannidis |
| author_sort | Vasiliki Kelli |
| collection | DOAJ |
| description | Internet of Things (IoT) is a concept adopted in nearly every aspect of human life, leading to an explosive utilization of intelligent devices. Notably, such solutions are especially integrated in the industrial sector, to allow the remote monitoring and control of critical infrastructure. Such global integration of IoT solutions has led to an expanded attack surface against IoT-enabled infrastructures. Artificial intelligence and machine learning have demonstrated their ability to resolve issues that would have been impossible or difficult to address otherwise; thus, such solutions are closely associated with securing IoT. Classical collaborative and distributed machine learning approaches are known to compromise sensitive information. In our paper, we demonstrate the creation of a network flow-based Intrusion Detection System (IDS) aiming to protecting critical infrastructures, stemming from the pairing of two machine learning techniques, namely, federated learning and active learning. The former is utilized for privately training models in federation, while the latter is a semi-supervised approach applied for global model adaptation to each of the participant’s traffic. Experimental results indicate that global models perform significantly better for each participant, when locally personalized with just a few active learning queries. Specifically, we demonstrate how the accuracy increase can reach 7.07% in only 10 queries. |
| first_indexed | 2024-03-10T06:13:11Z |
| format | Article |
| id | doaj.art-4b705b10225a47b9a66d2645d1579fd0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T06:13:11Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4b705b10225a47b9a66d2645d1579fd02023-11-22T19:56:44ZengMDPI AGSensors1424-82202021-10-012120674310.3390/s21206743IDS for Industrial Applications: A Federated Learning Approach with Active PersonalizationVasiliki Kelli0Vasileios Argyriou1Thomas Lagkas2George Fragulis3Elisavet Grigoriou4Panagiotis Sarigiannidis5Department of Electrical and Computer Engineering, University of Western Macedonia, 501 31 Kozani, GreeceDepartment of Networks and Digital Media, Kingston University, London KT1 1LQ, UKDepartment of Computer Science, Kavala Campus, International Hellenic University, 654 04 Kavala, GreeceDepartment of Electrical and Computer Engineering, University of Western Macedonia, 501 31 Kozani, GreeceSidroco Holdings Ltd., Nicosia 1077, CyprusDepartment of Electrical and Computer Engineering, University of Western Macedonia, 501 31 Kozani, GreeceInternet of Things (IoT) is a concept adopted in nearly every aspect of human life, leading to an explosive utilization of intelligent devices. Notably, such solutions are especially integrated in the industrial sector, to allow the remote monitoring and control of critical infrastructure. Such global integration of IoT solutions has led to an expanded attack surface against IoT-enabled infrastructures. Artificial intelligence and machine learning have demonstrated their ability to resolve issues that would have been impossible or difficult to address otherwise; thus, such solutions are closely associated with securing IoT. Classical collaborative and distributed machine learning approaches are known to compromise sensitive information. In our paper, we demonstrate the creation of a network flow-based Intrusion Detection System (IDS) aiming to protecting critical infrastructures, stemming from the pairing of two machine learning techniques, namely, federated learning and active learning. The former is utilized for privately training models in federation, while the latter is a semi-supervised approach applied for global model adaptation to each of the participant’s traffic. Experimental results indicate that global models perform significantly better for each participant, when locally personalized with just a few active learning queries. Specifically, we demonstrate how the accuracy increase can reach 7.07% in only 10 queries.https://www.mdpi.com/1424-8220/21/20/6743IoTIDScritical infrastructurefederated learningmachine learningactive learning |
| spellingShingle | Vasiliki Kelli Vasileios Argyriou Thomas Lagkas George Fragulis Elisavet Grigoriou Panagiotis Sarigiannidis IDS for Industrial Applications: A Federated Learning Approach with Active Personalization Sensors IoT IDS critical infrastructure federated learning machine learning active learning |
| title | IDS for Industrial Applications: A Federated Learning Approach with Active Personalization |
| title_full | IDS for Industrial Applications: A Federated Learning Approach with Active Personalization |
| title_fullStr | IDS for Industrial Applications: A Federated Learning Approach with Active Personalization |
| title_full_unstemmed | IDS for Industrial Applications: A Federated Learning Approach with Active Personalization |
| title_short | IDS for Industrial Applications: A Federated Learning Approach with Active Personalization |
| title_sort | ids for industrial applications a federated learning approach with active personalization |
| topic | IoT IDS critical infrastructure federated learning machine learning active learning |
| url | https://www.mdpi.com/1424-8220/21/20/6743 |
| work_keys_str_mv | AT vasilikikelli idsforindustrialapplicationsafederatedlearningapproachwithactivepersonalization AT vasileiosargyriou idsforindustrialapplicationsafederatedlearningapproachwithactivepersonalization AT thomaslagkas idsforindustrialapplicationsafederatedlearningapproachwithactivepersonalization AT georgefragulis idsforindustrialapplicationsafederatedlearningapproachwithactivepersonalization AT elisavetgrigoriou idsforindustrialapplicationsafederatedlearningapproachwithactivepersonalization AT panagiotissarigiannidis idsforindustrialapplicationsafederatedlearningapproachwithactivepersonalization |