| アイテムタイプ |
学術雑誌論文 / Journal Article(1) |
| 公開日 |
2025-12-19 |
| タイトル |
|
|
タイトル |
Secure Federated Matrix Factorization via Device to Device Model Shuffling |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Matrix factorization |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
federated learning |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
location recommendation |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
model shuffling |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
distributed system |
| 資源タイプ |
|
|
資源タイプ |
journal article |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
笹田, 大翔
Hossain, Md Delwar
妙中, 雄三
Rahman, Md. Mahbubur
門林, 雄基
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Location-Based Recommendation Systems (LBRS) use device location data to suggest nearby hotels, restaurants, and points of interest. Since directly collecting location data from users can raise privacy concerns, there is growing interest in building recommendation systems based on Federated Learning (FL). Under FL, parameters of recommendation model learned on each user’s device are collected on a single server to build aggregated model. While FL does not raise privacy concerns about data collection since it does not collect user data directly, it may construct unfair models that repeatedly recommend specific locations. Although there are training methods to achieve fair recommendations that prevent such bias, they require more training epochs than usual. In FL, a malicious server can infer the original location data by continuously tracking a specific user’s parameter updates, and the inference accuracy increases proportionally with the number of training epochs. This means that achieving fair location recommendations in FL puts the original data at risk. In this paper, we design a novel parameter aggregation method to build fair and secure FL recommendation models. In the proposed aggregation method, users exchange parameters with each other before model aggregation to prevent malicious servers from inferring the original data. Even if a server (adversary) continuously tracks a specific user’s device, it cannot get parameters from the same user, thus preventing inference of the original location data. An experiment result demonstrated that the proposed method can reduce training time while maintaining the same accuracy as homomorphic encryption approach. |
| 書誌情報 |
en : IEEE Access
巻 13,
p. 124180-124196,
ページ数 17,
発行日 2025-07-15
|
| 出版者 |
|
|
出版者 |
IEEE |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
2169-3536 |
| 出版者版DOI |
|
|
関連タイプ |
isIdenticalTo |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1109/ACCESS.2025.3588497 |
| 出版者版URI |
|
|
関連タイプ |
isIdenticalTo |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://ieeexplore.ieee.org/abstract/document/11079566 |
| 権利 |
|
|
権利情報Resource |
https://creativecommons.org/licenses/by/4.0/ |
|
権利情報 |
© 2025 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ |
| 著者版フラグ |
|
|
出版タイプ |
VoR |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP22J23910 |
|
|
研究課題番号URI |
https://kaken.nii.ac.jp/ja/grant/KAKENHI-PROJECT-22KJ2294/ |
|
|
研究課題名 |
時空間データの特性に適応する実践的プライバシ保護技術に関する研究 |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP24K03045 |
|
|
研究課題番号URI |
https://kaken.nii.ac.jp/ja/grant/KAKENHI-PROJECT-24K03045/ |
|
|
研究課題名 |
データセントリックな信頼志向データ流通管理の研究 |
| 助成情報 |
|
|
|
助成機関名 |
Daiichi-Sankyo |
|
|
研究課題名 |
‘‘Habataku’’ Support Program for the Next Generation of Researchers |
| 助成情報 |
|
|
|
助成機関名 |
Nara Institute Science and Technology |
|
|
研究課題名 |
Senju Monju Project |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP24K02916 |
|
|
研究課題番号URI |
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-24K02916/ |
|
|
研究課題名 |
高信頼システム間連携のための仮想/現実空間連動ブロックチェーン基盤の研究開発 |
fulltext (7.9 MB)
