Training Machine Learning Models for Behavior Estimation from Smartwatch with Local Differential Privacy

• Item type: Symposium(1)
• 公開日: 2024-10-15
• タイトル / 言語: en
• タイトル: Training Machine Learning Models for Behavior Estimation from Smartwatch with Local Differential Privacy
• タイトル / 言語: en
• タイトル: Training Machine Learning Models for Behavior Estimation from Smartwatch with Local Differential Privacy
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: Local Differential Privacy, Machine Learning, Smartwatches
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: Meiji University
• 著者所属: Meiji University
• 著者所属(英): en
• 著者所属(英): Meiji University
• 著者所属(英): en
• 著者所属(英): Meiji University
• 著者名: Andres, Hernandez-Matamoros; Hiroaki, Kikuchi
• 著者名(英): Andres, Hernandez-Matamoros; Hiroaki, Kikuchi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: The increasing use of smartwatches for continuous health monitoring necessitates robust and privacy-preserving approaches. To protect user privacy, local differential privacy (LDP) approaches that estimate Joint Probability Distributions (JPD) from noisy datasets have been proposed: Lopub, Locop, BR, and Castell. This paper focuses on training a machine learning model to recognize activity (exercise). Training using JPD helps prevent adversaries from performing training data extraction attacks to recover individual training data, allowing the model to be safely shared with new users, who can run the model locally to predict their activity. We compare our results with the PrivBayes model (Central Differential Privacy) as a benchmark. Through comprehensive experiments on different smartwatch datasets, we demonstrate that the Castell approach significantly outperforms Lopub, Locop, and BR in terms of accuracy. This finding underscores Castell’s potential as a superior choice for privacy-preserving activity detection in wearable devices, balancing the trade-off between data privacy and model performance. Our results highlight the importance of selecting appropriate LDP mechanisms to enhance the reliability and privacy of machine learning models in real-world health monitoring applications.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: The increasing use of smartwatches for continuous health monitoring necessitates robust and privacy-preserving approaches. To protect user privacy, local differential privacy (LDP) approaches that estimate Joint Probability Distributions (JPD) from noisy datasets have been proposed: Lopub, Locop, BR, and Castell. This paper focuses on training a machine learning model to recognize activity (exercise). Training using JPD helps prevent adversaries from performing training data extraction attacks to recover individual training data, allowing the model to be safely shared with new users, who can run the model locally to predict their activity. We compare our results with the PrivBayes model (Central Differential Privacy) as a benchmark. Through comprehensive experiments on different smartwatch datasets, we demonstrate that the Castell approach significantly outperforms Lopub, Locop, and BR in terms of accuracy. This finding underscores Castell’s potential as a superior choice for privacy-preserving activity detection in wearable devices, balancing the trade-off between data privacy and model performance. Our results highlight the importance of selecting appropriate LDP mechanisms to enhance the reliability and privacy of machine learning models in real-world health monitoring applications.
• 書誌情報: コンピュータセキュリティシンポジウム2024論文集; p. 266-273, 発行日 2024-10-15
• 出版者 / 言語: ja
• 出版者: 情報処理学会