The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 신경망과 의사결정 트리 모두에서 사용할 수 있는 기술을 포함하여 연합 학습의 개인정보 보호 기술을 살펴봅니다. 먼저 연합 학습에서 정보가 유출될 수 있는 방법을 식별한 후 기존의 많은 PPFL(개인 정보 보호 연합 학습) 시스템을 포괄하는 두 가지 개인 정보 보호 프레임워크를 도입하여 이 문제를 해결하는 방법을 제시합니다. 공개적으로 사용 가능한 금융, 의료 및 사물 인터넷 데이터 세트를 사용한 실험을 통해 개인 정보 보호 연합 학습의 효과와 실제 시나리오에서 매우 정확하고 안전하며 개인 정보를 보호하는 기계 학습 시스템을 개발할 수 있는 잠재력을 보여줍니다. 연구 결과는 연합 학습 시스템의 설계 및 구현에서 개인 정보 보호를 고려하는 것이 중요하다는 점을 강조하고, 효과적이고 실용적인 기계 학습 시스템을 개발하려면 개인 정보 보호 기술이 필수적임을 시사합니다.
Le Trieu PHONG
National Institute of Information and Communications Technology (NICT)
Tran Thi PHUONG
National Institute of Information and Communications Technology (NICT),KDDI Research, Inc.
Lihua WANG
National Institute of Information and Communications Technology (NICT)
Seiichi OZAWA
Kobe University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Le Trieu PHONG, Tran Thi PHUONG, Lihua WANG, Seiichi OZAWA, "Frameworks for Privacy-Preserving Federated Learning" in IEICE TRANSACTIONS on Information,
vol. E107-D, no. 1, pp. 2-12, January 2024, doi: 10.1587/transinf.2023MUI0001.
Abstract: In this paper, we explore privacy-preserving techniques in federated learning, including those can be used with both neural networks and decision trees. We begin by identifying how information can be leaked in federated learning, after which we present methods to address this issue by introducing two privacy-preserving frameworks that encompass many existing privacy-preserving federated learning (PPFL) systems. Through experiments with publicly available financial, medical, and Internet of Things datasets, we demonstrate the effectiveness of privacy-preserving federated learning and its potential to develop highly accurate, secure, and privacy-preserving machine learning systems in real-world scenarios. The findings highlight the importance of considering privacy in the design and implementation of federated learning systems and suggest that privacy-preserving techniques are essential in enabling the development of effective and practical machine learning systems.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023MUI0001/_p
부
@ARTICLE{e107-d_1_2,
author={Le Trieu PHONG, Tran Thi PHUONG, Lihua WANG, Seiichi OZAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Frameworks for Privacy-Preserving Federated Learning},
year={2024},
volume={E107-D},
number={1},
pages={2-12},
abstract={In this paper, we explore privacy-preserving techniques in federated learning, including those can be used with both neural networks and decision trees. We begin by identifying how information can be leaked in federated learning, after which we present methods to address this issue by introducing two privacy-preserving frameworks that encompass many existing privacy-preserving federated learning (PPFL) systems. Through experiments with publicly available financial, medical, and Internet of Things datasets, we demonstrate the effectiveness of privacy-preserving federated learning and its potential to develop highly accurate, secure, and privacy-preserving machine learning systems in real-world scenarios. The findings highlight the importance of considering privacy in the design and implementation of federated learning systems and suggest that privacy-preserving techniques are essential in enabling the development of effective and practical machine learning systems.},
keywords={},
doi={10.1587/transinf.2023MUI0001},
ISSN={1745-1361},
month={January},}
부
TY - JOUR
TI - Frameworks for Privacy-Preserving Federated Learning
T2 - IEICE TRANSACTIONS on Information
SP - 2
EP - 12
AU - Le Trieu PHONG
AU - Tran Thi PHUONG
AU - Lihua WANG
AU - Seiichi OZAWA
PY - 2024
DO - 10.1587/transinf.2023MUI0001
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E107-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2024
AB - In this paper, we explore privacy-preserving techniques in federated learning, including those can be used with both neural networks and decision trees. We begin by identifying how information can be leaked in federated learning, after which we present methods to address this issue by introducing two privacy-preserving frameworks that encompass many existing privacy-preserving federated learning (PPFL) systems. Through experiments with publicly available financial, medical, and Internet of Things datasets, we demonstrate the effectiveness of privacy-preserving federated learning and its potential to develop highly accurate, secure, and privacy-preserving machine learning systems in real-world scenarios. The findings highlight the importance of considering privacy in the design and implementation of federated learning systems and suggest that privacy-preserving techniques are essential in enabling the development of effective and practical machine learning systems.
ER -