scholarly journals Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks

2020 ◽  
Vol 34 (07) ◽  
pp. 11304-11311
Author(s):  
Chetan Kumar ◽  
Riazat Ryan ◽  
Ming Shao
Keyword(s):  
Social Networks ◽  
Information Leakage ◽  
Personal Data ◽  
Huge Amount ◽  
Sensitive Data ◽  
Social Good ◽  
Face Images ◽  
Adversarial Attack ◽  
Graph Neural Networks ◽  
Family Privacy

Social media has been widely used among billions of people with dramatical participation of new users every day. Among them, social networks maintain the basic social characters and host huge amount of personal data. While protecting user sensitive data is obvious and demanding, information leakage due to adversarial attacks is somehow unavoidable, yet hard to detect. For example, implicit social relation such as family information may be simply exposed by network structure and hosted face images through off-the-shelf graph neural networks (GNN), which will be empirically proved in this paper. To address this issue, in this paper, we propose a novel adversarial attack algorithm for social good. First, we start from conventional visual family understanding problem, and demonstrate that familial information can easily be exposed to attackers by connecting sneak shots to social networks. Second, to protect family privacy on social networks, we propose a novel adversarial attack algorithm that produces both adversarial features and graph under a given budget. Specifically, both features on the node and edges between nodes will be perturbed gradually such that the probe images and its family information can not be identified correctly through conventional GNN. Extensive experiments on a popular visual social dataset have demonstrated that our defense strategy can significantly mitigate the impacts of family information leakage.

Privacy Information Leakage Prevention in Cognitive Social Mining Applications

2019 ◽  
pp. 188-212
Author(s):  
Suriya Murugan ◽  
Anandakumar H.
Keyword(s):  
Social Networks ◽  
Social Relations ◽  
Private Information ◽  
Online Social Networks ◽  
Information Leakage ◽  
User Profile ◽  
User Privacy ◽  
Sensitive Data ◽  
Data Set ◽  
Secure Information

Online social networks, such as Facebook are increasingly used by many users and these networks allow people to publish and share their data to their friends. The problem is user privacy information can be inferred via social relations. This chapter makes a study and performs research on managing those confidential information leakages which is a challenging issue in social networks. It is possible to use learning methods on user released data to predict private information. Since the main goal is to distribute social network data while preventing sensitive data disclosure, it can be achieved through sanitization techniques. Then the effectiveness of those techniques is explored, and the methods of collective inference are used to discover sensitive attributes of the user profile data set. Hence, sanitization methods can be used efficiently to decrease the accuracy of both local and relational classifiers and allow secure information sharing by maintaining user privacy.

Privacy Information Leakage Prevention in Cognitive Social Mining Applications

2021 ◽  
pp. 2110-2134
Author(s):  
Suriya Murugan ◽  
Anandakumar H.
Keyword(s):  
Social Networks ◽  
Social Relations ◽  
Private Information ◽  
Online Social Networks ◽  
Information Leakage ◽  
User Profile ◽  
User Privacy ◽  
Sensitive Data ◽  
Data Set ◽  
Secure Information

Online social networks, such as Facebook are increasingly used by many users and these networks allow people to publish and share their data to their friends. The problem is user privacy information can be inferred via social relations. This chapter makes a study and performs research on managing those confidential information leakages which is a challenging issue in social networks. It is possible to use learning methods on user released data to predict private information. Since the main goal is to distribute social network data while preventing sensitive data disclosure, it can be achieved through sanitization techniques. Then the effectiveness of those techniques is explored, and the methods of collective inference are used to discover sensitive attributes of the user profile data set. Hence, sanitization methods can be used efficiently to decrease the accuracy of both local and relational classifiers and allow secure information sharing by maintaining user privacy.

scholarly journals Privacy and Security Issues in Online Social Networks

2018 ◽  
Vol 10 (12) ◽  
pp. 114 ◽  
Author(s):  
Shaukat Ali ◽  
Naveed Islam ◽  
Azhar Rauf ◽  
Ikram Din ◽  
Mohsen Guizani ◽  
...  
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Virtual Communities ◽  
Service Providers ◽  
Security And Privacy ◽  
Security Issue ◽  
Sensitive Data ◽  
Privacy And Security ◽  
Security Issues ◽  
Social Sphere

The advent of online social networks (OSN) has transformed a common passive reader into a content contributor. It has allowed users to share information and exchange opinions, and also express themselves in online virtual communities to interact with other users of similar interests. However, OSN have turned the social sphere of users into the commercial sphere. This should create a privacy and security issue for OSN users. OSN service providers collect the private and sensitive data of their customers that can be misused by data collectors, third parties, or by unauthorized users. In this paper, common security and privacy issues are explained along with recommendations to OSN users to protect themselves from these issues whenever they use social media.

scholarly journals A Survey: Data Leakage Detection Techniques

2018 ◽  
Vol 8 (4) ◽  
pp. 2247
Author(s):  
K. S. Wagh
Keyword(s):  
Credit Card ◽  
Information Leakage ◽  
Leakage Detection ◽  
Sensitive Data ◽  
Detection Techniques ◽  
Personal Credit ◽  
Customer Information ◽  
Other Information ◽  
Effective System ◽  
Credit Card Data

Data is an important property of various organizations and it is intellectual property of organization. Every organization includes sensitive data as customer information, financial data, data of patient, personal credit card data and other information based on the kinds of management, institute or industry. For the areas like this, leakage of information is the crucial problem that the organization has to face, that poses high cost if information leakage is done. All the more definitely, information leakage is characterize as the intentional exposure of individual or any sort of information to unapproved outsiders. When the important information is goes to unapproved hands or moves towards unauthorized destination. This will prompts the direct and indirect loss of particular industry in terms of cost and time. The information leakage is outcomes in vulnerability or its modification. So information can be protected by the outsider leakages. To solve this issue there must be an efficient and effective system to avoid and protect authorized information. From not so long many methods have been implemented to solve same type of problems that are analyzed here in this survey.  This paper analyzes little latest techniques and proposed novel Sampling algorithm based data leakage detection techniques.

scholarly journals Responsible Research on Social Networks

2018 ◽  
pp. 558-576
Author(s):  
Jon Crowcroft ◽  
Hamed Haddadi ◽  
Tristan Henderson
Keyword(s):  
Social Networks ◽  
Interpersonal Communication ◽  
Private Information ◽  
Online Social Networks ◽  
Personal Data ◽  
Legal Requirements ◽  
Pros And Cons ◽  
Conducting Research ◽  
Responsible Research ◽  
Responsible Manner

Researchers have found online social networks a goldmine for research into various aspects of social behavior and interpersonal communication. For example, observing social interaction between individuals and their engagement in conversations, or performing sentiment analysis on these communications, is often carried out for research in a number of disciplines such as health, sociology, or politics. Such studies introduce many challenges for conducting research in a responsible manner. Data may be repurposed or cross-correlated in ways that participants may not have anticipated or desired, private information may be collected, or legal requirements may not be met. This chapter explores some of the challenges and dilemmas faced by industry, academia, regulators, privacy advocates, and ultimately the individuals using these services. It discusses the pros and cons of the collection, analysis, and archiving of personal data for digital research. The chapter concludes by discussing theoretical and practical approaches that target these dilemmas.

Access Control Models for Online Social Networks

2014 ◽  
pp. 451-484
Author(s):  
Rula Sayaf ◽  
Dave Clarke
Keyword(s):  
Social Networks ◽  
Access Control ◽  
Online Social Networks ◽  
Personal Data ◽  
Security And Privacy ◽  
Open Problems ◽  
Access Control Models ◽  
Control Models ◽  
Underlying Mechanisms ◽  
High Level

Access control is one of the crucial aspects in information systems security. Authorizing access to resources is a fundamental process to limit potential privacy violations and protect users. The nature of personal data in online social networks (OSNs) requires a high-level of security and privacy protection. Recently, OSN-specific access control models (ACMs) have been proposed to address the particular structure, functionality and the underlying privacy issues of OSNs. In this survey chapter, the essential aspects of access control and review the fundamental classical ACMs are introduced. The specific OSNs features and review the main categories of OSN-specific ACMs are highlighted. Within each category, the most prominent ACMs and their underlying mechanisms that contribute enhancing privacy of OSNs are surveyed. Toward the end, more advanced issues of access control in OSNs are discussed. Throughout the discussion, different models and highlight open problems are contrasted. Based on these problems, the chapter is concluded by proposing requirements for future ACMs.

Internet Identity and the Right to be Forgotten

2015 ◽  
pp. 32-46
Author(s):  
Valentina Amenta ◽  
Adriana Lazzaroni ◽  
Laura Abba
Keyword(s):  
Social Networks ◽  
Human Rights ◽  
Personal Identity ◽  
Personal Data ◽  
Digital Identity ◽  
Right To Be Forgotten ◽  
The Subject ◽  
The Right ◽  
Regulatory Trends

In this chapter, the analysis will focus on the concept of digital identity which is evolving and changing, based on the experiences that every individual lives. The chapter further highlights how the digital identity includes the fundamental human rights such as the right to a name, the right of reply, the right to protection of personal data and the right to an image. In translating the right to personal identity to our digitalized era, with its massive use of social networks, we have added to the related decalogue of rights the right to oblivion, equally called right to be forgotten. Given the complexity of the subject, the chapter develops an analysis of the actual international regulatory trends.

Maturity in Health Organization Information Systems

2019 ◽  
pp. 294-314
Author(s):  
Alberto Carneiro
Keyword(s):  
Information Systems ◽  
Personal Data ◽  
Security Assessment ◽  
Sensitive Data ◽  
Practical Utilization ◽  
Maturity Models ◽  
Systems Security ◽  
It Managers ◽  
Improvement Measures ◽  
Health Organization

Adapting maturity models to healthcare organization's needs is an issue that researchers and technicians should consider and a valuable instrument for IT managers because these models allow the assessment of a present situation as well as the identification of useful improvement measures. This paper discusses the practical utilization of maturity models, including different manners of exploring model's usefulness. For a more complete understanding of maturity models, the selection of criteria and processes of measurement, called metrics, is briefly reviewed in terms of indicators and daily procedures. Some issues of management information systems security are briefly addressed, along with a note on measuring security assessment. Finally some considerations are presented about the need for privacy of personal data to ensure the strategies to be pursued to sensitive data in order to establish a level of effective privacy which is included in the concerns of security of information systems.

Sign in / Sign up

Export Citation Format

Share Document