A server has an already trained decision tree machine learning model and one or more clients have unclassified query(ies) that they wish to classify using the server's model under strict security, privacy, and eff...
详细信息
ISBN:
(纸本)9798350312751
A server has an already trained decision tree machine learning model and one or more clients have unclassified query(ies) that they wish to classify using the server's model under strict security, privacy, and efficiency constraints. To do so, already existing secure building blocks are used, improved, and adjusted to fit this scenario. On top of the proposed building blocks, novel secure and private Decision Tree Evaluation (sDTE) algorithms are proposed. The proposed building blocks show better performances than the related ones in literature in terms of computation and communication costs. Consequently, experimental evaluations over benchmark datasets show that the proposed sDTE algorithms build on top of the proposed blocks, also outperform the state-of-the-art ones in terms of computation and communication costs as well as on security and privacy characteristics. Our theoretical analysis shows that if the whole decision tree can fit in a single ciphertext, which in the proposed sDTE algorithms is almost always the case, then private tree evaluations are done in constant time and do not depend on the tree depth. To the best of the author's knowledge, this is the first scheme in literature with such properties.
In Mobile Edge Computing, the framework of federated learning can enable collaborative learning models across edge nodes, without necessitating the direct exchange of data from edge nodes. It addresses significant cha...
详细信息
In Mobile Edge Computing, the framework of federated learning can enable collaborative learning models across edge nodes, without necessitating the direct exchange of data from edge nodes. It addresses significant challenges encompassing access rights, privacy, security, and the utilization of heterogeneous data sources over mobile edge computing. Edge devices generate and gather data, across the network, in non-IID (independent and identically distributed) manner leading to potential variations in the number of data samples among these edge networks. A method is proposed to work in federated learning under edge computing setting, which involves AI techniques such as data augmentation and class estimation and balancing during training process with minimized computational overhead. This is accomplished through the implementation of data augmentation techniques to refine data distribution. Additionally, we leveraged class estimation and employed linear regression for client-side model training. This strategic approach yields a reduction in computational costs. To validate the effectiveness of the proposed approach, it is applied to two distinct datasets. One dataset pertains to image data (FashionMNIST), while the other comprises numerical and textual data concerning stocks for predictive analysis of stock values. This approach demonstrates commendable performance across both dataset types and approaching more than 92% of accuracy in the paradigm of federated learning.
Over the last decade there has a been widespread usage of Machine Learning (ML) classifiers in cases such accurate disease diagnosis at clinics, credit card fraud detection in banks, cyber-attacks prevention of comput...
详细信息
Over the last decade there has a been widespread usage of Machine Learning (ML) classifiers in cases such accurate disease diagnosis at clinics, credit card fraud detection in banks, cyber-attacks prevention of computer systems in different industries, etc. However, privacy and security concerns and law regulations have been an obstacle to the usage of ML classifiers. To this end, this paper addresses the scenario where a server has a private trained ML model, and one or more clients have private queries that they wish to classify using the server's model. During the process, the server learns nothing, while the clients learn only their final classifications and nothing else. Several ML classification algorithms, such as Deep Neural Networks, Support Vector Machines, Logistic Regression, different flavors of Naive Bayes, etc., can be expressed in terms of linear algebra operations. To this end, initially, as building blocks, several novel secure linear algebra operations are proposed. On top of them novel secure ML classification algorithms are proposed for the aforementioned classifiers under strict security, privacy and efficiency constraints and their security is proven under the semi-honest model. Since the used underlying cryptographic primitives are shown to be resilient to quantum computer attacks, the proposed algorithms are also suitable for the post-quantum world. Furthermore, the proposed algorithms are non-interactive and, based on where the bulk of the operations are done, they have the flexibility to be server or client centric. Theoretical analysis and extensive experimental evaluations over benchmark datasets show that the proposed secure linear algebra operations, hence the secure ML algorithms build on top of them, outperform the state-of-the-art schemes in terms of computation and communication costs as well as on security and privacy characteristics. Moreover, and to the best of the authors' knowledge, for the first time in literature the securit
We provide an overview of privacypreserving association rule mining, which is one of the most popular pattern-discovery methods in the new and rapidly emerging research area of privacypreserving data mining. Various...
详细信息
ISBN:
(纸本)9781424442843
We provide an overview of privacypreserving association rule mining, which is one of the most popular pattern-discovery methods in the new and rapidly emerging research area of privacypreserving data mining. Various proposals and algorithms have been designed for it in recent years. In this paper, we summarize them and survey current existing techniques, and analyze their advantage and disadvantage. We divide the proposals of privacypreserving association rule mining into three categories: heuristic-based techniques, reconstruction-based techniques, cryptography-based techniques. Then we give a simple review of the work accomplished. Finally, we conclude further research directions of privacy preserving algorithms of association rule mining by analyzing the existing work.
暂无评论