Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study
Attaullah H, Sanaullah S, Jungeblut T (2024)
Applied Sciences 14(19): 9047.
Zeitschriftenaufsatz
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Attaullah, Hasina;
Sanaullah, Sanaullah;
Jungeblut, ThorstenUniBi
Abstract / Bemerkung
The era of digitization and IoT devices is marked by the constant storage of massive amounts of data. The growing adoption of smart home environments, which use sensors and devices to monitor and control various aspects of daily life, underscores the need for effective privacy and security measures. HE is a technology that enables computations on encrypted data, preserving confidentiality. As a result, researchers have developed methodologies to protect user information, and HE is one of the technologies that make it possible to perform computations directly on encrypted data and produce results using this encrypted information. Thus, this research study compares the performance of three ML models, XGBoost, Random Forest, and Decision Classifier, on a real-world smart home dataset using both with and without FHE. Practical results demonstrate that the Decision Classifier showed remarkable results, maintaining high accuracy with FHE and even surpassing its plaintext performance, suggesting that encryption can enhance model accuracy under certain conditions. Additionally, Random Forest showed efficiency in terms of execution time and low prediction errors with FHE, making it a strong candidate for encrypted data processing in smart homes. These findings highlight the potential of FHE to set new privacy standards, advancing secure and privacy-preserving technologies in smart environments.
Stichworte
fully homomorphic encryption;
machine learning;
smart homes;
IoT;
neuronal models;
privacy-preserving
Erscheinungsjahr
2024
Zeitschriftentitel
Applied Sciences
Band
14
Ausgabe
19
Art.-Nr.
9047
eISSN
2076-3417
Page URI
https://pub.uni-bielefeld.de/record/2993890
Zitieren
Attaullah H, Sanaullah S, Jungeblut T. Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study. Applied Sciences. 2024;14(19): 9047.
Attaullah, H., Sanaullah, S., & Jungeblut, T. (2024). Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study. Applied Sciences, 14(19), 9047. https://doi.org/10.3390/app14199047
Attaullah, Hasina, Sanaullah, Sanaullah, and Jungeblut, Thorsten. 2024. “Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study”. Applied Sciences 14 (19): 9047.
Attaullah, H., Sanaullah, S., and Jungeblut, T. (2024). Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study. Applied Sciences 14:9047.
Attaullah, H., Sanaullah, S., & Jungeblut, T., 2024. Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study. Applied Sciences, 14(19): 9047.
H. Attaullah, S. Sanaullah, and T. Jungeblut, “Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study”, Applied Sciences, vol. 14, 2024, : 9047.
Attaullah, H., Sanaullah, S., Jungeblut, T.: Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study. Applied Sciences. 14, : 9047 (2024).
Attaullah, Hasina, Sanaullah, Sanaullah, and Jungeblut, Thorsten. “Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study”. Applied Sciences 14.19 (2024): 9047.
Export
Markieren/ Markierung löschen
Markierte Publikationen
Web of Science
Dieser Datensatz im Web of Science®Suchen in