检索结果-内蒙古大学图书馆

privacy-preserving machine learning in Cloud-Edge-End Collaborative Environments

IEEE INTERNET OF THINGS JOURNAL 2025年第1期12卷 419-434页

作者： Yang, Wenbo Wang, Hao Li, Zhi Niu, Ziyu Wu, Lei Wei, Xiaochao Su, Ye Susilo, Willy Shandong Normal Univ Sch Informat Sci & Engn Jinan 250014 Peoples R China Univ Wollongong Sch Comp & Informat Technol Wollongong NSW 2522 Australia

We propose a privacy-preserving machine learning scheme based on the cloud-edge-end architecture to address issues like weak computing power of Internet of Things (IoT) terminals, poor communication quality, and heavy cloud server burdens in traditional frameworks. Edge servers aggregate and forward terminal data, relieving terminals of heavy communication tasks and undertaking part of the computing tasks, which reduces the burden on cloud servers and improves system response speed. For privacy protection, we flexibly use homomorphic encryption and secret sharing techniques, and dynamically add differential privacy noise to resist member inference attacks. Task allocation is coordinated between different layers to optimize computing overhead. Shallow model training is performed on edge servers using homomorphic encryption, while deep model training is conducted on cloud servers using secret sharing. To achieve the conversion from homomorphic ciphertext to secret sharing shares, we design a distributed decryption protocol. Experimental results show our scheme reduces computation overhead by 20%-30% compared to existing privacy-preserving machine learning schemes based on the cloud-edge-end framework, while maintaining privacy protection throughout all stages.

关键词： Servers Cloud computing machine learning Internet of Things Training Homomorphic encryption Computational modeling Cloud-edge-end differential privacy fully homomorphic encryption privacy-preserving machine learning secret sharing

来源：评论

学校读者我要写书评

暂无评论

privacy-preserving machine learning (PPML) Inference for Clinically Actionable Models

引用

IEEE ACCESS 2025年 13卷 37431-37456页

作者： Balaban, Baris Magara, Seyma Selcan Yilgor, Caglar Yucekul, Altug Obeid, Ibrahim Pizones, Javier Kleinstueck, Frank Perez-Grueso, Francisco Javier Sanchez Pellise, Ferran Alanay, Ahmet Savas, Erkay Bagci, Cetin Sezerman, Osman Ugur European Spine Study Group, European Spine Study Acibadem Mehmet Ali Aydinlar Univ Inst Hlth Sci Dept Biostat & Bioinformat TR-34638 Istanbul Turkiye Sabanci Univ Dept Comp Sci & Engn TR-34956 Istanbul Turkiye Univ Tubingen Dept Comp Sci D-72074 Tubingen Germany Acibadem Univ Dept Orthoped & Traumatol Sch Med TR-34750 Istanbul Turkiye Elsan Jean Villar Private Hosp Clin Dos F-33520 Bordeaux France Hosp Univ La Paz Spine Surg Unit Madrid 28046 Spain Schulthess Klin Spine Ctr Div Dept Orthoped & Neurosurg CH-8008 Zurich Switzerland Hosp Univ Vall Hebron Spine Surg Unit Barcelona 08035 Spain Bilmed Comp & Software Co TR-34742 Istanbul Turkiye

machine learning (ML) refers to algorithms (often models) that are learned directly from data, germane to past experience. As algorithms have constantly been evolving with the exponential increase of computing power and vastly generated data, privacy of algorithms as well as of data becomes extremely important due to regulations and IP rights. Therefore, it is vital to address privacy and security concerns of both data and model together with other performance metrics when commercializing machine learning models. Our aim is to show that privacy-preserving machine learning inference methods can safeguard the intellectual property of models and prevent plaintext models from disclosing information about the sensitive data employed in training these ML models. Additionally, these methods protect the confidentiality of model users' sensitive patient data. We accomplish this by performing a security analysis to determine an appropriate query limit for each user, using the European Spine Study Group's (ESSG) adult spinal deformity dataset. We implement a privacy-preserving tree-based machine learning inference and run two security scenarios (scenario A and scenario B) containing four parts with progressively increasing the number of synthetic data points, which are used to enhance the accuracy of the attacker's substitute model. A target model is generated with particular operation site(s) in each scenario, and substitute models are built with nine-time threefold cross-validation using the XGBoost algorithm with the remaining sites' data to assess the security of the target model. First, we create box plots of the test sets' accuracy, sensitivity, precision, and F-score metrics to compare the substitute models' performance with the target model. Second, we compare the gain values of the target and substitute models' features. Third, we provide an in-depth analysis to check the inclusion of target model split points in substitute models with a heatmap. Finally, we compare t

关键词： Data models Computational modeling machine learning machine learning algorithms Cryptography Accuracy Analytical models Inference algorithms Homomorphic encryption Data privacy Homomorphic Encryption privacy-preserving machine learning XGBoost

来源：评论

学校读者我要写书评

暂无评论

privacy-preserving machine learning With Fully Homomorphic Encryption for Deep Neural Network

引用

IEEE ACCESS 2022年 10卷 30039-30054页

作者： Lee, Joon-Woo Kang, Hyungchul Lee, Yongwoo Choi, Woosuk Eom, Jieun Deryabin, Maxim Lee, Eunsang Lee, Junghyun Yoo, Donghoon Kim, Young-Sik No, Jong-Seon Seoul Natl Univ Dept Elect & Comp Engn INMC Seoul 08826 South Korea Samsung Adv Inst Technol Suwon 16678 South Korea Chosun Univ Dept Informat & Commun Engn Gwangju 61452 South Korea

Fully homomorphic encryption (FHE) is a prospective tool for privacy-preserving machine learning (PPML). Several PPML models have been proposed based on various FHE schemes and approaches. Although FHE schemes are suitable as tools for implementing PPML models, previous PPML models based on FHE, such as CryptoNet, SEALion, and CryptoDL, are limited to simple and nonstandard types of machine learning models;they have not proven to be efficient and accurate with more practical and advanced datasets. Previous PPML schemes replaced non-arithmetic activation functions with simple arithmetic functions instead of adopting approximation methods and did not use bootstrapping, which enables continuous homomorphic evaluations. Thus, they could neither use standard activation functions nor employ large numbers of layers. In this work, we first implement the standard ResNet-20 model with the RNS-CKKS FHE with bootstrapping and verify the implemented model with the CIFAR-10 dataset and plaintext model parameters. Instead of replacing the non-arithmetic functions with simple arithmetic functions, we use state-of-the-art approximation methods to evaluate these non-arithmetic functions, such as ReLU and Softmax, with sufficient precision. Further, for the first time, we use the bootstrapping technique of the RNS-CKKS scheme in the proposed model, which enables us to evaluate an arbitrary deep learning model on encrypted data. We numerically verify that the proposed model with the CIFAR-10 dataset shows 98.43% identical results to the original ResNet-20 model with non-encrypted data. The classification accuracy of the proposed model is 92.43%+/- 2.65%, which is quite close to that of the original ResNet-20 CNN model (91.89%). It takes approximately 3 h for inference on a dual Intel Xeon Platinum 8280 CPU (112 cores) with 172 GB of memory. We believe that this opens the possibility of applying FHE to an advanced deep PPML model.

关键词： Cryptography Data models Standards Homomorphic encryption Deep learning Computational modeling Numerical models privacy-preserving machine learning ResNet-20 RNS-CKKS FHE scheme SEAL library software implementation

来源：评论

学校读者我要写书评

暂无评论

IDPriU: A two-party ID-private data union protocol for privacy-preserving machine learning

引用

JOURNAL OF INFORMATION SECURITY AND APPLICATIONS 2025年 88卷

作者： Yan, Jianping Wei, Lifei Qian, Xiansong Zhang, Lei Shanghai Maritime Univ Coll Informat Engn Shanghai 201306 Peoples R China Shanghai Ocean Univ Coll Informat Technol Shanghai 201306 Peoples R China

Due to significant data security concerns in machine learning, such as the data silo problem, there has been a growing trend towards the development of privacy-preserving machine learning applications. The initial step in training data across silos involves establishing secure data joins, specifically private data joins, to ensure the consistency and accuracy of the dataset. While the majority of current research focuses on the inner join of private data, this paper specifically addresses the privacy-preserving full join of private data and develops two-party unbalanced private data full join protocols utilizing secure multi-party computation tools. Notably, our paper introduces the novel component of Private Match-and-Connect (PMC), which performs a union operation on the ID and feature values, and ensure the secret sharing of the resulting union set. Each participant receives only a portion of the secret share, thereby guaranteeing data security during the pre-processing phase. Furthermore, we propose the two-party ID-private data union protocol (IDPriU), which facilitates secure and accurate matching of feature value shares and ID shares and also enables the data alignment. Our protocol represents a significant advancement in the field of privacy-preserving data preprocessing in machine learning and privacy-preserving federated queries. It extends the concept that private data joins are limited to inner connections, offering a novel approach by Private Set Union (PSU). We have experimentally implemented our protocol and obtained favorable results in terms of both runtime and communication overhead.

关键词： Private data union privacy-preserving machine learning Data security Data preprocessing Private set union

来源：评论

学校读者我要写书评

暂无评论

Approximate homomorphic encryption based privacy-preserving machine learning: a survey

引用

ARTIFICIAL INTELLIGENCE REVIEW 2025年第3期58卷 1-49页

作者： Yuan, Jiangjun Liu, Weinan Shi, Jiawen Li, Qingqing Hangzhou Vocat & Tech Coll Business & Tourism Inst Hangzhou 310018 Zhejiang Peoples R China Hangzhou City Univ Supercomp Ctr Hangzhou 310000 Zhejiang Peoples R China

machine learning (ML) is rapidly advancing, enabling various applications that improve people's work and daily lives. However, this technical progress brings privacy concerns, leading to the emergence of privacy-preserving machine learning (PPML) as a popular research topic. In this work, we investigate the privacy protection topic in ML, and showcase the advantages of Homomorphic Encryption (HE) among different privacy-preserving techniques. Additionally, this work presents an introduction of approximate HE, emphasizing its advantages and providing the detail of some representative schemes. Moreover, we systematically review the related works about approximate HE based PPML schemes from the four technical applications and three advanced applications, along with their application scenarios, models and datasets. Finally, we suggest some potential future directions to guide readers in extending the research of PPML.

关键词： privacy-preserving machine learning machine learning Homomorphic encryption privacy

来源：评论

学校读者我要写书评

暂无评论

Efficient Dropout-Resilient Aggregation for privacy-preserving machine learning

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023年 18卷 1839-1854页

作者： Liu, Ziyao Guo, Jiale Lam, Kwok-Yan Zhao, Jun Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore

machine learning (ML) has been widely recognized as an enabler of the global trend of digital transformation. With the increasing adoption of data-hungry machine learning algorithms, personal data privacy has emerged as one of the key concerns that could hinder the success of digital transformation. As such, privacy-preserving machine learning (PPML) has received much attention of the machine learning community, from academic researchers to industry practitioners to government regulators. However, organizations are faced with the dilemma that, on the one hand, they are encouraged to share data to enhance ML performance, but on the other hand, they could potentially be breaching the relevant data privacy regulations. Practical PPML typically allows multiple participants to individually train their ML models, which are then aggregated to construct a global model in a privacy-preserving manner, e.g., based on multi-party computation or homomorphic encryption. Nevertheless, in most important applications of large-scale PPML, e.g., by aggregating clients' gradients to update a global model for federated learning, such as consumer behavior modeling of mobile application services, some participants are inevitably resource-constrained mobile devices, which may drop out of the PPML system due to their mobility nature (Yang et al., 2019). Therefore, the resilience of privacy-preserving aggregation has become an important problem to be tackled because of its real-world application potential and impacts. In this paper, we propose a scalable privacy- preserving aggregation scheme that can tolerate dropout by participants at any time, and is secure against both semi-honest and active malicious adversaries by setting proper system parameters. By replacing communication-intensive building blocks with a seed homomorphic pseudorandom generator, and relying on the additive homomorphic property of Shamir secret sharing scheme, our scheme outperforms state-of-the-art schemes by up to 6.

关键词： Secure aggregation privacy-preserving machine learning dropout-resilience HPRG

来源：评论

学校读者我要写书评

暂无评论

GuardML: Efficient privacy-preserving machine learning Services Through Hybrid Homomorphic Encryption 24

GuardML: Efficient Privacy-Preserving Machine Learning Servi...

引用

39th Annual ACM Symposium on Applied Computing (SAC)

作者： Frimpong, Eugene Nguyen, Khoa Budzys, Mindaugas Khan, Tanveer Michalas, Antonis Tampere Univ Tampere Finland

ISBN: (纸本)9798400702433

machine learning (ML) has emerged as one of data science's most transformative and influential domains. However, the widespread adoption of ML introduces privacy-related concerns owing to the increasing number of malicious attacks targeting ML models. To address these concerns, privacy-preserving machine learning (PPML) methods have been introduced to safeguard the privacy and security of ML models. One such approach is the use of Homomorphic Encryption (HE). However, the significant drawbacks and inefficiencies of traditional HE render it impractical for highly scalable scenarios. Fortunately, a modern cryptographic scheme, Hybrid Homomorphic Encryption (HHE), has recently emerged, combining the strengths of symmetric cryptography and HE to surmount these challenges. Our work seeks to introduce HHE to ML by designing a PPML scheme tailored for end devices. We leverage HHE as the fundamental building block to enable secure learning of classification outcomes over encrypted data, all while preserving the privacy of the input data and ML model. We demonstrate the real-world applicability of our construction by developing and evaluating an HHE-based PPML application for classifying heart disease based on sensitive ECG data. Notably, our evaluations revealed a slight reduction in accuracy compared to inference on plaintext data. Additionally, both the analyst and end devices experience minimal communication and computation costs, underscoring the practical viability of our approach. The successful integration of HHE into PPML provides a glimpse into a more secure and privacy-conscious future for machine learning on relatively constrained end devices.

关键词： Hybrid Homomorphic Encryption machine learning as a Service privacy-preserving machine learning

来源：评论

学校读者我要写书评

暂无评论

Client-Aided privacy-preserving machine learning 14th

Client-Aided Privacy-Preserving Machine Learning

引用

14th International Conference on Security and Cryptography for Networks (SCN)

作者： Miao, Peihan Shi, Xinyi Wu, Chao Xu, Ruofan Brown Univ Providence RI 02912 USA Univ Calif Riverside Riverside CA USA Univ Illinois Urbana IL USA

ISBN: (纸本)9783031710698;9783031710704

privacy-preserving machine learning (PPML) enables multiple distrusting parties to jointly train ML models on their private data without revealing any information beyond the final trained models. In this work, we study the client-aided two-server setting where two non-colluding servers jointly train an ML model on the data held by a large number of clients. By involving the clients in the training process, we develop efficient protocols for training algorithms including linear regression, logistic regression, and neural networks. In particular, we introduce novel approaches to securely computing inner product, sign check, activation functions (e.g., ReLU, logistic function), and division on secret shared values, leveraging lightweight computation on the client side. We present constructions that are secure against semi-honest clients and further enhance them to achieve security against malicious clients. We believe these new client-aided techniques may be of independent interest. We implement our protocols and compare them with the two-server PPML protocols presented in SecureML (Mohassel and Zhang, S&P'17) across various settings and ABY2.0 (Patra et al., Usenix Security'21) theoretically. We demonstrate that with the assistance of untrusted clients in the training process, we can significantly improve both the communication and computational efficiency by orders of magnitude. Our protocols compare favorably in all the training algorithms on both LAN and WAN networks.

关键词： privacy-preserving machine learning Secure Multi-Party Computation Client-Aided Protocols

来源：评论

学校读者我要写书评

暂无评论

A Pervasive, Efficient and Private Future: Realizing privacy-preserving machine learning Through Hybrid Homomorphic Encryption 22

A Pervasive, Efficient and Private Future: Realizing Privacy...

引用

2024 IEEE Conference on Dependable, Autonomic and Secure Computing

作者： Khoa Nguyen Budzys, Mindaugas Frimpong, Eugene Khan, Tanveer Michalas, Antonis Tampere Univ Dept Comp Sci Tampere Finland RISE Res Inst Sweden Gothenburg Sweden

ISBN: (纸本)9798331522735;9798331522728

machine learning (ML) has become one of the most impactful fields of data science in recent years. However, a significant concern with ML is its privacy risks due to rising attacks against ML models. privacy-preserving machine learning (PPML) methods have been proposed to mitigate the privacy and security risks of ML models. A popular approach to achieving PPML uses Homomorphic Encryption (HE). However, the highly publicized inefficiencies of HE make it unsuitable for highly scalable scenarios with resource-constrained devices. Hence, Hybrid Homomorphic Encryption (HHE) - a modern encryption scheme that combines symmetric cryptography with HE - has recently been introduced to overcome these challenges. HHE potentially provides a foundation to build new efficient and privacy-preserving services that transfer expensive HE operations to the cloud. This work introduces HHE to the ML field by proposing resource-friendly PPML protocols for edge devices. More precisely, we utilize HHE as the primary building block of our PPML protocols. We assess the performance of our protocols by first extensively evaluating each party's communication and computational cost on a dummy dataset and show the efficiency of our protocols by comparing them with similar protocols implemented using plain BFV. Subsequently, we demonstrate the real-world applicability of our construction by building an actual PPML application that uses HHE as its foundation to classify heart disease based on sensitive ECG data.

关键词： Hybrid Homomorphic Encryption machine learning as a Service privacy-preserving machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Parameters of Pipelined Multi-party Computation for privacy-preserving machine learning Applications 59

Optimizing the Parameters of Pipelined Multi-party Computati...

引用

59th Annual IEEE International Conference on Communications (IEEE ICC)

作者： Hernandez, Richard Bautista, Oscar G. Akkaya, Kemal Florida Int Univ Adv Wireless & Secur Lab Miami FL 33199 USA

ISBN: (纸本)9781728190549

Cloud Service Providers (CSPs) have recently significantly improved, allowing for outsourcing machine learning (ML) training and inference. However, due to the data privacy needs in most of the ML applications, several privacy-preserving technologies, such as Multi-party Computation (MPC), have been proposed to protect the data privacy. MPC offers splitting and exchanging of data among multiple parties, typically managed on cloud environments. Although MPC performs better than other alternatives, it still lags behind regular clear-text ML processing in terms of performance. To reduce the execution time of privacy-preserving ML (PPML) via MPC, parallelization of computation and communication among the parties (i.e., pipelined MPC), can be employed. However, the complex nature of these systems makes it challenging to select an optimal network and node configuration for executing a pipelined MPC. To address these challenges, in this paper, we propose a Multi-Objective Optimization (MOO) model focusing on achieving optimal configuration to minimize the MPC execution time along with its costs. We formulate an optimization model and propose two distinct approaches to solve it. Our evaluation clearly demonstrates a reduction in execution time and cost with respect to regular MPC execution. The evaluation results also provide valuable insights into the impact of latency and bandwidth considerations on our system's performance, contributing to PPML optimization.

关键词： secure multi-party computation privacy-preserving machine learning MPC on the cloud network parameter optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：