Accurate Classification Models for Distributed Mining of Privately Preserved Data

Data maintained at various sectors, needs to be mined to derive useful inferences. Larger part of the data is sensitive and not to be revealed while mining. Current methods perform privacy preservation classification either by randomizing, perturbing or anonymizing the data during mining. These forms of privacy preserving mining work well for data centralized at a single site. Moreover the amount of information hidden during mining is not sufficient. When perturbation approaches are used, data reconstruction is a major challenge. This paper aims at modeling classifiers for data distributed across various sites with respect to the same instances. The homomorphic and probabilistic property of Paillier is used to perform secure product, mean and variance calculations. The secure computations are performed without any intermediate data or the sensitive data at multiple sites being revealed. It is observed that the accuracy of the classifiers modeled is almost equivalent to the non-privacy preserving classifiers. Secure protocols require reduced computation time and communication cost.

Download Full-text

Semantically Secure Classifiers for Privacy Preserving Data Mining

Research Anthology on Privatizing and Securing Data ◽

10.4018/978-1-7998-8954-0.ch049 ◽

2021 ◽

pp. 1066-1095

Author(s):

Sumana M. ◽

Hareesha K. S. ◽

Sampath Kumar

Keyword(s):

Data Mining ◽

Model Building ◽

Computation Time ◽

Privacy Preserving ◽

Sensitive Data ◽

Privacy Preserving Data Mining ◽

Intermediate Data ◽

Secure Protocols ◽

Mean And Variance ◽

Probabilistic Property

Essential predictions are to be made by the parties distributed at multiple locations. However, in the process of building a model, perceptive data is not to be revealed. Maintaining the privacy of such data is a foremost concern. Earlier approaches developed for classification and prediction are proven not to be secure enough and the performance is affected. This chapter focuses on the secure construction of commonly used classifiers. The computations performed during model building are proved to be semantically secure. The homomorphism and probabilistic property of Paillier is used to perform secure product, mean, and variance calculations. The secure computations are performed without any intermediate data or the sensitive data at multiple sites being revealed. It is observed that the accuracy of the classifiers modeled is almost equivalent to the non-privacy preserving classifiers. Secure protocols require reduced computation time and communication cost. It is also proved that proposed privacy preserving classifiers perform significantly better than the base classifiers.

Download Full-text

Semantically Secure Classifiers for Privacy Preserving Data Mining

Security and Privacy Management, Techniques, and Protocols - Advances in Information Security, Privacy, and Ethics ◽

10.4018/978-1-5225-5583-4.ch003 ◽

2018 ◽

pp. 66-95

Author(s):

Sumana M. ◽

Hareesha K. S. ◽

Sampath Kumar

Keyword(s):

Data Mining ◽

Model Building ◽

Computation Time ◽

Privacy Preserving ◽

Sensitive Data ◽

Privacy Preserving Data Mining ◽

Intermediate Data ◽

Secure Protocols ◽

Mean And Variance ◽

Probabilistic Property

Essential predictions are to be made by the parties distributed at multiple locations. However, in the process of building a model, perceptive data is not to be revealed. Maintaining the privacy of such data is a foremost concern. Earlier approaches developed for classification and prediction are proven not to be secure enough and the performance is affected. This chapter focuses on the secure construction of commonly used classifiers. The computations performed during model building are proved to be semantically secure. The homomorphism and probabilistic property of Paillier is used to perform secure product, mean, and variance calculations. The secure computations are performed without any intermediate data or the sensitive data at multiple sites being revealed. It is observed that the accuracy of the classifiers modeled is almost equivalent to the non-privacy preserving classifiers. Secure protocols require reduced computation time and communication cost. It is also proved that proposed privacy preserving classifiers perform significantly better than the base classifiers.

Download Full-text

A noise-based privacy preserving model for Internet of Things

Complex & Intelligent Systems ◽

10.1007/s40747-021-00489-5 ◽

2021 ◽

Author(s):

Shelendra Kumar Jain ◽

Nishtha Kesswani

Keyword(s):

Internet Of Things ◽

Privacy Protection ◽

Privacy Preservation ◽

Data Access ◽

Privacy Preserving ◽

Sensitive Data ◽

Computational Overhead ◽

Data Access Control ◽

Proposed Model ◽

Control Scheme

AbstractWith the ever-increasing number of devices, the Internet of Things facilitates the connection between the devices in the hyper-connected world. As the number of interconnected devices increases, sensitive data disclosure becomes an important issue that needs to be addressed. In order to prevent the disclosure of sensitive data, effective and feasible privacy preservation strategies are necessary. A noise-based privacy-preserving model has been proposed in this article. The components of the noise-based privacy-preserving model include Multilevel Noise Treatment for data collection; user preferences-based data classifier to classify sensitive and non-sensitive data; Noise Removal and Fuzzification Mechanism for data access and user-customized privacy preservation mechanism. Experiments have been conducted to evaluate the performance and feasibility of the proposed model. The results have been compared with existing approaches. The experimental results show an improvement in the proposed noise-based privacy-preserving model in terms of computational overhead. The comparative analysis indicates that the proposed model without the fuzzifier has around 52–77% less computational overhead than the Data access control scheme and 46–70% less computational overhead compared to the Dynamic Privacy Protection model. The proposed model with the fuzzifier has around 48–73% less computational overhead compared to the Data access control scheme and 31–63% less computational overhead compared to the Dynamic Privacy Protection model. Furthermore, the privacy analysis has been done with the relevant approaches. The results indicate that the proposed model can customize privacy as per the users’ preferences and at the same time takes less execution time which reduces the overhead on the resource constraint IoT devices.

Download Full-text

Detection of Sensitive Data Leakage for Privacy Preserving

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6i9.765769 ◽

2018 ◽

Vol 6 (9) ◽

pp. 765-769

Author(s):

R.J. Patil ◽

Y.S. Borse

Keyword(s):

Privacy Preserving ◽

Sensitive Data

Download Full-text

Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study

npj Digital Medicine ◽

10.1038/s41746-021-00431-6 ◽

2021 ◽

Vol 4 (1) ◽

Author(s):

Qi Dou ◽

Tiffany Y. So ◽

Meirui Jiang ◽

Quande Liu ◽

Varut Vardhanabhuti ◽

...

Keyword(s):

Data Privacy ◽

Medical Training ◽

External Validation ◽

Mainland China ◽

Privacy Preserving ◽

Generalization Capability ◽

Major Focus ◽

Sensitive Data ◽

Lung Abnormalities ◽

Medical Image Diagnosis

AbstractData privacy mechanisms are essential for rapidly scaling medical training databases to capture the heterogeneity of patient data distributions toward robust and generalizable machine learning systems. In the current COVID-19 pandemic, a major focus of artificial intelligence (AI) is interpreting chest CT, which can be readily used in the assessment and management of the disease. This paper demonstrates the feasibility of a federated learning method for detecting COVID-19 related CT abnormalities with external validation on patients from a multinational study. We recruited 132 patients from seven multinational different centers, with three internal hospitals from Hong Kong for training and testing, and four external, independent datasets from Mainland China and Germany, for validating model generalizability. We also conducted case studies on longitudinal scans for automated estimation of lesion burden for hospitalized COVID-19 patients. We explore the federated learning algorithms to develop a privacy-preserving AI model for COVID-19 medical image diagnosis with good generalization capability on unseen multinational datasets. Federated learning could provide an effective mechanism during pandemics to rapidly develop clinically useful AI across institutions and countries overcoming the burden of central aggregation of large amounts of sensitive data.

Download Full-text

Privacy-Preserving Deep Neural Network Methods: Computational and Perceptual Methods—An Overview

Electronics ◽

10.3390/electronics10111367 ◽

2021 ◽

Vol 10 (11) ◽

pp. 1367

Author(s):

Raghida El El Saj ◽

Ehsan Sedgh Sedgh Gooya ◽

Ayman Alfalou ◽

Mohamad Khalil

Keyword(s):

Neural Networks ◽

Classification Accuracy ◽

Deep Neural Networks ◽

Privacy Preserving ◽

Sensitive Data ◽

Encrypted Data ◽

High Classification Accuracy ◽

Hide Information ◽

Network Methods ◽

Cloud Environments

Privacy-preserving deep neural networks have become essential and have attracted the attention of many researchers due to the need to maintain the privacy and the confidentiality of personal and sensitive data. The importance of privacy-preserving networks has increased with the widespread use of neural networks as a service in unsecured cloud environments. Different methods have been proposed and developed to solve the privacy-preserving problem using deep neural networks on encrypted data. In this article, we reviewed some of the most relevant and well-known computational and perceptual image encryption methods. These methods as well as their results have been presented, compared, and the conditions of their use, the durability and robustness of some of them against attacks, have been discussed. Some of the mentioned methods have demonstrated an ability to hide information and make it difficult for adversaries to retrieve it while maintaining high classification accuracy. Based on the obtained results, it was suggested to develop and use some of the cited privacy-preserving methods in applications other than classification.

Download Full-text