An Enhanced Approach for Privacy Preserving Data Mining (PPDM)

In many organizations large amount of data are collected. These data are sometimes used by the organizations for data mining tasks. However, the data collected may contain private or sensitive information which should be protected. Privacy protection is an important issue if we release data for the mining or sharing purpose. Privacy preserving data mining techniques allow publishing data for the mining purpose while at the same time preserve the private information of the individuals. Many techniques have been proposed for privacy preservation but they suffer from various types of attacks and information loss. In this paper we proposed an efficient approach for privacy preservation in data mining. Our technique protects the sensitive data with less information loss which increase data usability and also prevent the sensitive data for various types of attack. Data can also be reconstructed using our proposed technique.

Data mining is the extraction of interesting patterns or knowledge from huge amount of data. In recent years, with the explosive development in Internet, data storage and data processing technologies, privacy preservation has been one of the greater concerns in data mining. In recent years, privacy-preserving data mining has been studied extensively, because of the wide proliferation of sensitive information on the Internet. A number of methods and techniques have been developed for privacy preserving data mining. This paper provides a wide survey of different privacy preserving data mining algorithms and analyses the representative techniques for privacy preserving data mining, and points out their merits and demerits. Finally the present problems and directions for future research are discussed.

IJEMR, 2017

Now a day’s information is played major role in decision making in an organization. We are in the world of information processing society. Data is the major valuable resource of any business or organization. There is a huge amount of sensitive data produced by various business operational applications. Sharing information between various sources through authorized channel is an important task. Data Mining is kind knowledge discovery system, through this data can extract from different sources. While sharing information through different channels or extracting information from different external sources, the key factor is protecting data from unauthorized accesses. This paper presents a brief idea about protecting extracted data of data mining system without loss of processing data using Privacy Preserving techniques and its comparison.

The main aim of Data mining techniques are to try to find out helpful patterns from the data that is big in quantity. These ideas or patterns are useful to find out some useful information. The abilities learned through fully knowledge mining approaches may contain confidential information about persons or trade. Upkeep of secrecy is a gigantic aspect of information mining also as a result be taught of attaining some information mining ambitions without dropping the secrecy of the individuals .The assessment of privacy preserving data mining (PPDM) algorithms must don't forget the penalties of those algorithms in mining the outcome along with retaining privacy. Inside the constraints of privateness, a couple of ways have been introduced however nonetheless this branch of exploration is in its early life .The success of privateness preserving data mining procedures is measured in phrases of its efficiency, data utility, degree of uncertainty or resistance to data mining procedures and so on. Nevertheless no privateness maintaining algorithm exists that outperforms all others on all feasible standards. Rather, an algorithm could participate in better than one other on one exact criterion. So, the aim of this paper is to show the current situation of privacy preserving knowledge mining framework and tactics

In organization large amount of data are collected daily and these data are used by the organization for data mining tasks. These data collected may contain sensitive attribute which not disclosed by un-trusted user. Privacy is very important when release the data for sharing purpose or mining. Privacy preserving data mining allow publishing data while same time it protect the sensitive or private data. For privacy preserving there are many technique like k-anonymity, cryptography, blocking based, data Perturbation etc. In this paper, various privacy preserving approaches in data sharing and their merits and demerits are analyzed.

Data mining is the extraction of the important patterns or information from large amount of data, which is used for decision making in future work. But the process of data collection and data dissemination may cause the serious damage for any organization, however may causes the privacy concerns. Sensitive or personal information of individuals, industries and organization must be kept private before it is shared or published. Thus privacy preserving data mining has become an important issue to efficiently hide sensitive information. Many numbers of methods and techniques have been proposed for privacy preserving data mining for hiding sensitive information. In this paper we provides our own overview which has taken from previous paper on privacy preserving data mining.

As people of every walk of life are using Internet for various purposes there is growing evidence of proliferation of sensitive information. Security and privacy of data became an important concern. For this reason privacy preserving data mining (PPDM) has been an active research area. PPDM is a process discovering knowledge from voluminous data while protecting sensitive information. In this paper we explore the present state-of-the-art of secure and privacy preserving data mining algorithms or techniques which will help in real world usage of enterprise applications. The techniques discussed include randomized method, k-Anonymity, l-Diversity, t-Closeness, m-Privacy and other PPDM approaches. This paper also focuses on SQL injection attacks and prevention measures. The paper provides research insights into the areas of secure and privacy preserving data mining techniques or algorithms besides presenting gaps in the research that can be used to plan future research.

2016

With technological revolution, a huge amount of data is being collected and as a consequence the need of mining knowledge from this data is triggered. But, data in its raw form comprises of sensitive information and advances in data mining techniques have increased the privacy breach. However, due to socio-technical transformations, most countries have levied the guidelines and policies for publishing certain data. As a result, a new area known as Privacy Preserving Data Mining (PPDM) has emerged. The goal of PPDM is to extract valuable information from data while retaining privacy of this data. The paper focuses on exploring PPDM in different aspects, such as types of privacy, PPDM scenarios and applications, methods of evaluating PPDM algorithms etc. Also, the paper shows parametric analysis and comparison of different PPDM techniques. The goal of this study is to facilitate better understanding of these PPDM techniques and boost fruitful research in this direction.

Privacy preserving has become crucial in knowledge-based applications. And proper integration of individual privacy is essential for data mining operations. This privacy-based data mining is important for sectors such as healthcare, pharmaceuticals, investigation and security service providers, where the data mining is transformed into cooperative task among individuals. Data mining is successful in many applications, data mining refers special concerns for private data. In data mining, clustering algorithms are most of skilled and frequently used frameworks. The integrated architecture takes a systemic view of the problem of implementing established protocols for data collection, inference control, information sharing and keeping information safety. The goal is to investigating privacy preservation issues was to take a systemic view of the architectural requirements and also design principles and explore possible solutions that would lead to the guidelines for buildup practical privacy-preserving data mining systems. In this paper, we propose the methods which uses formula-based technique for sharing of secret data in privacy-preserving mechanism. The process includes formula-based methodology which enables the information to be partitioned into numerous shares and handled independently at various servers. This paper surveys the most relevant Privacy preserving data mining 'PPDM' techniques from the literature are used to evaluate such techniques and presents the typical applications of PPDM methods in relevant fields. The ongoing current challenges and open issues in PPDM are discussed in the paper.

2015

The Privacy preserving Data mining (PPDM) has been among the important issues of current research that deals with preserving privacy of individual's data over a network. The major area of concern is that non-sensitive data even may deliver sensitive information, including personal information, facts or patterns. In this paper, we present a unique concept of combining different PPDM techniques which provides high level security and integrity to confidential data. This paper mainly highlights the improved results that can be obtained on merging the two different PPDM techniques. One of the latest concept of PPDM called Slicing has also been explained in our paper. It has been observed that slicing preserves better data utility and thus we have tried to merge slicing with one of the best security mechanism that is Cryptography.