On Data Distortion for Privacy Preserving Data Mining

Kabir, Saif Mohammad Asif; Youssef, Ayman; Elhakeem, A.K.

doi:10.1109/ccece.2007.83

Cited by 12 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However as, like any perturbation approach, such changes could affect some important information (i.e., lose data utility), obtaining a balance between data protection and utility is still a significant challenge [7], [32]. Various studies for maintaining the privacy of data-driven devices in different applications, such as that of Kabir et al [33], use the Non-negative Matrix Factorisation (NMF) and sparseness constraint to hide sensitive information. This constraint provides a sparse data representation in which a predefined threshold is set to control the level of data distortion.…”

Section: ) Signal Distortionmentioning

confidence: 99%

Privacy-Preserving Schemes for Safeguarding Heterogeneous Data Sources in Cyber-Physical Systems

et al. 2021

View full text Add to dashboard Cite

Cyber-Physical Systems (CPSs) as in power, water, gas systems and smart grids produce heterogeneous and huge amount of data from various devices and networks, therefore it is essential to develop efficient privacy-preserving techniques for safeguarding system data (telemetry and transactions) from cyber attacks. In order to protect CPSs from prospect cyber-threats, it is essential to discover system components vulnerabilities to prohibit Advanced Persistent Threats (APTs) and keep their generated data secure using privacy-preserving techniques. This paper introduces a comprehensive review of the current privacy-preserving techniques for protecting CPS systems and their data from cyber attacks. Concepts of Privacy preservation and CPSs are discussed, demonstrating CPSs' components and the way these systems could be exploited by either cyber and physical hacking scenarios. Then, classification of privacy preservation according to the way they would be protected, including perturbation, authentication, machine learning (ML), cryptography and blockchain, are explained to illustrate how they would be employed for data privacy preservation. Finally, we show existing challenges, solutions and future research directions of privacy preservation in CPSs.

show abstract

Section: ) Signal Distortionmentioning

confidence: 99%

Privacy-Preserving Schemes for Safeguarding Heterogeneous Data Sources in Cyber-Physical Systems

et al. 2021

View full text Add to dashboard Cite

show abstract

“…As a result, we choose to develop ways to perturb the objective function and then we can easily apply the Laplace mechanism to preserve differential privacy. Let us first start with a simple approach which directly adds Laplace noise to the parameters (w, α) [13], as described in Algorithm 1.…”

Section: Output Function Perturbation Approach (Ofpa)mentioning

confidence: 99%

Privacy-Preserving Multiparty Learning for Logistic Regression

2018

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

In recent years, machine learning techniques are widely used in numerous applications, such as weather forecast, financial data analysis, spam filtering, and medical prediction. In the meantime, massive data generated from multiple sources further improve the performance of machine learning tools. However, data sharing from multiple sources brings privacy issues for those sources since sensitive information may be leaked in this process. In this paper, we propose a framework enabling multiple parties to collaboratively and accurately train a learning model over distributed datasets while guaranteeing the privacy of data sources. Specifically, we consider logistic regression model for data training and propose two approaches for perturbing the objective function to preserve ǫ-differential privacy. The proposed solutions are tested on real datasets, including Bank Marketing and Credit Card Default prediction. Experimental results demonstrate that the proposed multiparty learning framework is highly efficient and accurate.

show abstract

“…The most possible of using multiplicative random projection matrices for privacy preserving distributed data mining for computing statistical aggregates like the inner product matrix, correlation coefficient matrix, and Euclidean distance matrix from distributed privacy sensitive data is explored. The scope of perturbation-based PPDM to Multilevel Trust (MLT-PPDM) is expanded in [9] which are robust against diversity attacks with respect to the privacy goal. In [12] a kind of privacy preserving classification mining method based on the random perturbation matrix is proposed which is suitable to the data of character type, Boolean type, classified type and digital type.…”

Section: Perturbation Algorithmsmentioning

confidence: 99%

Survey on Privacy Preserving Data Mining Techniques using Recent Algorithms

Rajesh¹,

Sujatha²,

Selvakumar³

2016

IJCA

View full text Add to dashboard Cite

The privacy preserving data mining is playing crucial role act as rising technology to perform various data mining operations on private data and to pass on data in a secured way to protect sensitive data. Many types of technique such as randomization, secured sum algorithms and k-anonymity have been suggested in order to execute privacy preserving data mining. In this survey paper, on current researches made on privacy preserving data mining technique with fuzzy logic, neural network learning, secured sum and various encryption algorithm is presented. This will enable to grasp the various challenges faced in privacy preserving data mining and also help us to find best suitable technique for various data environment.

show abstract

On Data Distortion for Privacy Preserving Data Mining

Abstract: Because of the increasing ability to trace and collect large amount of personal information, privacy preserving in data mining applications has become an important concern. Data perturbation is one of the well known techniques for privacy preserving data mining.

Cited by 12 publications

References 6 publications

Privacy-Preserving Schemes for Safeguarding Heterogeneous Data Sources in Cyber-Physical Systems

Privacy-Preserving Schemes for Safeguarding Heterogeneous Data Sources in Cyber-Physical Systems

Privacy-Preserving Multiparty Learning for Logistic Regression

Survey on Privacy Preserving Data Mining Techniques using Recent Algorithms

Contact Info

Product

Resources

About