scholarly journals Privacy Preservation of Social Network Users Against Attribute Inference Attacks via Malicious Data Mining

2019 ◽  
Author(s):  
Khondker Reza ◽  
Md Islam ◽  
Vladimir Estivill-Castro
Keyword(s):  
Data Mining ◽  
Social Network ◽  
Privacy Preservation ◽  
Inference Attacks

Anonymization Techniques for Privacy Preservation in Social Networks: A Review

2021 ◽  
pp. 14-21
Author(s):  
Kalpana Chavhan ◽  
Dr. Praveen S. Challagidad
Keyword(s):  
Data Mining ◽  
Social Networks ◽  
Social Network ◽  
Privacy Preservation ◽  
Information Science ◽  
Original Data ◽  
Published Data ◽  
Sensitive Information ◽  
Social Network Data ◽  
The Social

Any data that user creates or owns is known as the user's data (For example: Name, USN, Phone number, address, email Id). As the number of users in social networks are increasing day by day the data generated by the user's is also increasing. Network providers will publish the data to others for analysis with hope that mining will provide additional functionality to their users or produce useful results that they can share with others. The analysis of social networks is used in modern sociology, geography, economics and information science as well as in various fields. Publicizing the original data of social networks for analysis raises issues of confidentiality, the adversary can search for documented threats such as identity theft, digital harassment and personalized spam. The published data may contain some sensitive information of individuals which must not be disclosed for this reason social network data must be anonymized before it is published. To do the data in nominate the anonymization technique should be applied, to preserve the privacy of data in the social network in a manner that preserves the privacy of the user whose records are being published while maintaining the published dataset rich enough to allow for the exploration of data. In order to address the issue of privacy protection, we first describe the concept of k-anonymity and illustrate different approaches for its enforcement. We then discuss how the privacy requirements characterized by k-anonymity can be violated in data mining and introduce possible approaches to ensure the satisfaction of k-anonymity in data mining also several attacks on dataset are discussed.

scholarly journals Hybrid and Decentralized Privacy Preservation using D-Anonymity and T-Closeness in Social Network

2019 ◽  
Vol 9 (2S) ◽  
pp. 671-675
Keyword(s):  
Data Mining ◽  
Social Network ◽  
General Public ◽  
Privacy Preservation ◽  
Privacy Preserving ◽  
Preservation Solution ◽  
Trade Off ◽  
Data Anonymization ◽  
Data Owner ◽  
The Social

Although Social Network (SN) knowledge is significant assets for data examination, freeing the data to the general public could reason an invasion of privacy. Privacy insurance is taken a lot of seriously than various data mining duties. The privacy problems are dealt with by several algorithms and strategies in the literature. But, perpetually there exists a trade-off between privacy and data.Our objective in this work is to design and develop a privacy-preserving solution for the social network. We have used K-anonymity and T-closeness algorithm and data anonymization. Further, data anonymization is decentralized by giving control of anonymization to the data owner. The solution is implemented on a dummy social network for testing the effectiveness of the privacy preservation solution proposed by us.

The prediction model of personality in social networks by using data mining deep learning algorithm and random walk model

2020 ◽  
pp. 002072092093683
Author(s):  
Yu Zhu
Keyword(s):  
Data Mining ◽  
Deep Learning ◽  
Social Network ◽  
Random Walk ◽  
Prediction Method ◽  
Random Walk Model ◽  
Personality Characteristics ◽  
User Personality ◽  
Network Platform ◽  
Personality Prediction

The objective is to predict and analyze the behaviors of users in the social network platform by using the personality theory and computational technologies, thereby acquiring the personality characteristics of social network users more effectively. First, social network data are analyzed, which finds that the type of text data marks the majority. By using data mining technology, the raw data of numerous social network users can be obtained. Based on the random walk model, the data information of the text status of social network users is analyzed, and a user personality prediction method integrating multi-label learning is proposed. In addition, the online social network platform Weibo is taken as the research object. The blog information of Weibo users is obtained through crawler technology. Then, the users are labeled in accordance with personality characteristics. The Pearson correlation coefficient is used to evaluate the relation between the user personality characteristics and the user behavior characteristics of the Weibo users. The correlation between the network behaviors and personality characteristics of Weibo users is analyzed, and the scientificity of the prediction method is verified by the Big Five Model of Personality. By applying relevant technologies and algorithms of data mining and deep learning, the learning ability of neural networks on data characteristics can be improved. In terms of performance on analyzing text information of social network users, the user personality prediction method of integrated multi-label learning based on the random walk model has a large advantage. For the problem of personality prediction of social network users, through combining data mining technology and deep neural network technology in deep learning, the data processing results of social network user behaviors are more accurate.

Collecting Qualitative Data for Social Network Analysis and Data Mining

2014 ◽  
pp. 124-133
Author(s):  
Nancy L. Leech ◽  
Kathleen M. T. Collins ◽  
Anthony J. Onwuegbuzie
Keyword(s):  
Data Mining ◽  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Qualitative Data

scholarly journals A Fuzzy Logic based Privacy Preservation Clustering method for achieving K- Anonymity using EMD in dLink Model

2016 ◽  
Vol 12 (12) ◽  
pp. 4601-4610 ◽  
Author(s):  
D. Palanikkumar ◽  
S. Priya ◽  
S. Priya
Keyword(s):  
Data Mining ◽  
Privacy Preservation ◽  
Numerical Data ◽  
Fuzzy Membership Function ◽  
Data Mining Technique ◽  
Sensitive Data ◽  
Sensitive Attribute ◽  
Modification Technique ◽  
Earth Mover ◽  
Preservation Technique

Privacy preservation is the data mining technique which is to be applied on the databases without violating the privacy of individuals. The sensitive attribute can be selected from the numerical data and it can be modified by any data modification technique. After modification, the modified data can be released to any agency. If they can apply data mining techniques such as clustering, classification etc for data analysis, the modified data does not affect the result. In privacy preservation technique, the sensitive data is converted into modified data using S-shaped fuzzy membership function. K-means clustering is applied for both original and modified data to get the clusters. t-closeness requires that the distribution of sensitive attribute in any equivalence class is close to the distribution of the attribute in the overall table. Earth Mover Distance (EMD) is used to measure the distance between the two distributions should be no more than a threshold t. Hence privacy is preserved and accuracy of the data is maintained.

Sign in / Sign up

Export Citation Format

Share Document