Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition
Wearable devices and smartphones that are used to monitor the activity and the state of the driver collect a lot of sensitive data such as audio, video, location and even health data. The analysis and processing of such data require observing the strict legal requirements for personal data security...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/8/2983 |
| _version_ | 1797434203217854464 |
|---|---|
| author | Evgenia Novikova Dmitry Fomichov Ivan Kholod Evgeny Filippov |
| author_facet | Evgenia Novikova Dmitry Fomichov Ivan Kholod Evgeny Filippov |
| author_sort | Evgenia Novikova |
| collection | DOAJ |
| description | Wearable devices and smartphones that are used to monitor the activity and the state of the driver collect a lot of sensitive data such as audio, video, location and even health data. The analysis and processing of such data require observing the strict legal requirements for personal data security and privacy. The federated learning (FL) computation paradigm has been proposed as a privacy-preserving computational model that allows securing the privacy of the data owner. However, it still has no formal proof of privacy guarantees, and recent research showed that the attacks targeted both the model integrity and privacy of the data owners could be performed at all stages of the FL process. This paper focuses on the analysis of the privacy-preserving techniques adopted for FL and presents a comparative review and analysis of their implementations in the open-source FL frameworks. The authors evaluated their impact on the overall training process in terms of global model accuracy, training time and network traffic generated during the training process in order to assess their applicability to driver’s state and behaviour monitoring. As the usage scenario, the authors considered the case of the driver’s activity monitoring using the data from smartphone sensors. The experiments showed that the current implementation of the privacy-preserving techniques in open-source FL frameworks limits the practical application of FL to cross-silo settings. |
| first_indexed | 2024-03-09T10:28:53Z |
| format | Article |
| id | doaj.art-1d6efe23e7ca43bc83056e128092d091 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T10:28:53Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1d6efe23e7ca43bc83056e128092d0912023-12-01T21:23:19ZengMDPI AGSensors1424-82202022-04-01228298310.3390/s22082983Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity RecognitionEvgenia Novikova0Dmitry Fomichov1Ivan Kholod2Evgeny Filippov3Faculty of Computer Science and Technology, Saint Petersburg Electrotechnical University “LETI”, Saint Petersburg 197376, RussiaFaculty of Computer Science and Technology, Saint Petersburg Electrotechnical University “LETI”, Saint Petersburg 197376, RussiaFaculty of Computer Science and Technology, Saint Petersburg Electrotechnical University “LETI”, Saint Petersburg 197376, RussiaSmartilizer Rus LLC, Saint Petersburg 197376, RussiaWearable devices and smartphones that are used to monitor the activity and the state of the driver collect a lot of sensitive data such as audio, video, location and even health data. The analysis and processing of such data require observing the strict legal requirements for personal data security and privacy. The federated learning (FL) computation paradigm has been proposed as a privacy-preserving computational model that allows securing the privacy of the data owner. However, it still has no formal proof of privacy guarantees, and recent research showed that the attacks targeted both the model integrity and privacy of the data owners could be performed at all stages of the FL process. This paper focuses on the analysis of the privacy-preserving techniques adopted for FL and presents a comparative review and analysis of their implementations in the open-source FL frameworks. The authors evaluated their impact on the overall training process in terms of global model accuracy, training time and network traffic generated during the training process in order to assess their applicability to driver’s state and behaviour monitoring. As the usage scenario, the authors considered the case of the driver’s activity monitoring using the data from smartphone sensors. The experiments showed that the current implementation of the privacy-preserving techniques in open-source FL frameworks limits the practical application of FL to cross-silo settings.https://www.mdpi.com/1424-8220/22/8/2983privacyfederated learningdriver activity monitoringopen-source federated learning frameworksdifferential privacyhomomorphic encryption |
| spellingShingle | Evgenia Novikova Dmitry Fomichov Ivan Kholod Evgeny Filippov Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition Sensors privacy federated learning driver activity monitoring open-source federated learning frameworks differential privacy homomorphic encryption |
| title | Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition |
| title_full | Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition |
| title_fullStr | Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition |
| title_full_unstemmed | Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition |
| title_short | Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition |
| title_sort | analysis of privacy enhancing technologies in open source federated learning frameworks for driver activity recognition |
| topic | privacy federated learning driver activity monitoring open-source federated learning frameworks differential privacy homomorphic encryption |
| url | https://www.mdpi.com/1424-8220/22/8/2983 |
| work_keys_str_mv | AT evgenianovikova analysisofprivacyenhancingtechnologiesinopensourcefederatedlearningframeworksfordriveractivityrecognition AT dmitryfomichov analysisofprivacyenhancingtechnologiesinopensourcefederatedlearningframeworksfordriveractivityrecognition AT ivankholod analysisofprivacyenhancingtechnologiesinopensourcefederatedlearningframeworksfordriveractivityrecognition AT evgenyfilippov analysisofprivacyenhancingtechnologiesinopensourcefederatedlearningframeworksfordriveractivityrecognition |