In this paper, we study a distributed privacy-preserving learning problem in social networks with general topology. The agents can communicate with each other over the network, which may result in privacy disclosure, since the trustworthiness of the agents cannot be guaranteed. Given a set of options which yield unknown stochastic rewards, each agent is required to learn the best one, aiming at maximizing the resulting expected average cumulative reward. To serve the above goal, we propose a four-staged distributed algorithm which efficiently exploits the collaboration among the agents while preserving the local privacy for each of them. In particular, our algorithm proceeds iteratively, and in every round, each agent i) randomly perturbs its adoption for the privacy-preserving purpose, ii) disseminates the perturbed adoption over the social network in a nearly uniform manner through random walking, iii) selects an option by referring to the perturbed suggestions received from its peers, and iv) decides whether or not to adopt the selected option as preference according to its latest reward feedback. Through solid theoretical analysis, we quantify the trade-off among the number of agents (or communication overhead), privacy preserving and learning utility. We also perform extensive simulations to verify the efficacy of our proposed social learning algorithm.
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；School of Cyber Science and Technology, Beihang University（北京航空航天大学网络空间安全学院）；Sony AI（索尼人工智能）；Salesforce（赛富时）；Zhejiang University（浙江大学）；Macquarie University（麦考瑞大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
Integrating multiple online social networks (OSNs) has important implications for many downstream social mining tasks, such as user preference modelling, recommendation, and link prediction. However, it is unfortunately accompanied by growing privacy concerns about leaking sensitive user information. How to fully utilize the data from different online social networks while preserving user privacy remains largely unsolved. To this end, we propose a Cross-network Social User Embedding framework, namely DP-CroSUE, to learn the comprehensive representations of users in a privacy-preserving way. We…
Differential privacy is effective in sharing information and preserving privacy with a strong guarantee. As social network analysis has been extensively adopted in many applications, it opens a new arena for the application of differential privacy. In this article, we provide a comprehensive survey connecting the basic principles of differential privacy and applications in social network analysis. We present a concise review of the foundations of differential privacy and the major variants and discuss how differential privacy is applied to social network analysis, including privacy attacks in …
The increasing popularity of social media has attracted a huge number of people to participate in numerous activities on a daily basis. This results in tremendous amounts of rich user-generated data. This data provides opportunities for researchers and service providers to study and better understand users' behaviors and further improve the quality of the personalized services. Publishing user-generated data risks exposing individuals' privacy. Users privacy in social media is an emerging task and has attracted increasing attention in recent years. These works study privacy issues in social me…
Online users generate tremendous amounts of data. To better serve users, it is required to share the user-related data among researchers, advertisers and application developers. Publishing such data would raise more concerns on user privacy. To encourage data sharing and mitigate user privacy concerns, a number of anonymization and de-anonymization algorithms have been developed to help protect privacy of users. This paper reviews my doctoral research on online users privacy specifically in social media. In particular, I propose a new adversarial attack specialized for social media data. I fur…
The increasing popularity of online social network brings huge privacy threat for the end users. While existing work focus on inferring sensitive attributes from the social network such as age, location and gender, little has been done on how to protect the users' privacy by preventing the malicious inference. In this paper we investigated the privacy vulnerability of the existing social network and designed a privacy-preserving framework. We evaluated the framework's privacy and usefulness guarantees, demonstrated its effectiveness on classification and the defense against the privacy attack.
Widespread usage of complex interconnected social networks such as Facebook, Twitter and LinkedIn in modern internet era has also unfortunately opened the door for privacy violation of users of such networks by malicious entities. In this article we investigate, both theoretically and empirically, privacy violation measures of large networks under active attacks that was recently introduced in (Information Sciences, 328, 403-417, 2016). Our theoretical result indicates that the network manager responsible for prevention of privacy violation must be very careful in designing the network if its …
Despite the several advantages commonly attributed to social networks such as easiness and immediacy to communicate with acquaintances and friends, significant privacy threats provoked by unexperienced or even irresponsible users recklessly publishing sensitive material are also noticeable. Yet, a different, but equally hazardous privacy risk might arise from social networks profiling the online activity of their users based on the timestamp of the interactions between the former and the latter. In order to thwart this last type of commonly neglected attacks, this paper presents a novel, smart…
A growing body of research leverages social network based trust relationships to improve the functionality of the system. However, these systems expose users' trust relationships, which is considered sensitive information in today's society, to an adversary. In this work, we make the following contributions. First, we propose an algorithm that perturbs the structure of a social graph in order to provide link privacy, at the cost of slight reduction in the utility of the social graph. Second we define general metrics for characterizing the utility and privacy of perturbed graphs. Third, we eval…
Theories of privacy and how it relates to the use of Information Communication Technology (ICT) have been a topic of research for decades. However, little attention has been paid to the perception of privacy from the perspective of technology users in the Middle East. In this paper, we delve into interpretations of privacy from the approach of Arab Gulf citizens. We consider how privacy is practiced and understood in technology-mediated environments among this population, paying particular attention to the role of Islam and cultural traditions in constructing norms around privacy. We then offe…
Online Social Networks (OSNs) have come to play an increasingly important role in our social lives, and their inherent privacy problems have become a major concern for users. Can we assist consumers in their privacy decision-making practices, for example by predicting their preferences and giving them personalized advice? To this end, we introduce PPM: a Privacy Prediction Model, rooted in psychological principles, which can be used to give users personalized advice regarding their privacy decision-making practices. Using this model, we study psychological variables that are known to affect us…
Social networks such as Facebook (FB) and Instagram are known for tracking user online behaviour for commercial gain. To this day, there is practically no other way of achieving privacy in said platforms other than renouncing their use. However, many users are reluctant in doing so because of convenience or social and professional reasons. In this work, we propose a means of balancing convenience and privacy on FB through obfuscation. We have created MetaPriv, a tool based on simulating user interaction with FB. MetaPriv allows users to add noise interactions to their account so as to lead FB'…
The increasing participation of people in online activities in recent years like content publishing, and having different kinds of relationships and interactions, along with the emergence of online social networks and people's extensive tendency toward them, have resulted in generation and availability of a huge amount of valuable information that has never been available before, and have introduced some new, attractive, varied, and useful research areas to researchers. In this paper we try to review some of the accomplished research on information of SNSs (Social Network Sites), and introduce…
The Social Web is a set of social relations that link people through World Wide Web. This Social Web encompasses how the websites and software are designed and developed to support social relations. The new paradigms, tools and web services introduced by Social Web are widely accepted by internet users. The main drawbacks of these tools are it acts as independent data silos; hence interoperability among applications is a complex issue. This paper focuses on this issue and how best we can use semantic web technologies to achieve interoperability among applications.
This paper argues that data of strategic individuals with heterogeneous privacy valuations in a distributed online social network (e.g., Facebook) will be under-priced, if traded in a monopoly buyer setting, and will lead to diminishing utilitarian welfare. This result, for a certain family of online community data trading problems, is in stark contrast to a popular information economics intuition that increased amounts of end-user data signals in a data market improves its efficiency. Our proposed theory paves the way for a future (counter-intuitive) analysis of data trading oligopoly markets…
Complex decision-making problems such as the privacy policy selection when sharing content in online social networks can significantly benefit from artificial intelligence systems. With the use of Computational Argumentation, it is possible to persuade human users to modify their initial decisions to avoid potential privacy threats and violations. In this paper, we present a study performed over 186 teenage users aimed at analysing their behaviour when we try to persuade them to modify the publication of sensitive content in Online Social Networks (OSN) with different arguments. The results of…
In recent years, Online Social Networks (OSNs) have become immensely popular as social interaction services among worldwide Internet users. OSNs facilitate Third-party applications (TPAs) which provide many additional functionalities to users. While providing the extended services TPAs access the users data which would raise serious concerns to user privacy. This is due to the lack of user data protection mechanisms by OSN and none of the present OSN platforms offers satisfactory protection mechanisms to users private data. In this paper, we propose an access control framework called InfoRest …
Existing constructs for privacy concerns and behaviors do not adequately model deviations between user attitudes and behaviors. Although a number of studies have examined supposed deviations from rationality by online users, true explanations for these behaviors may lie in factors not previously addressed in privacy concern constructs. In particular, privacy attitudes and behavioral changes over time have not been examined within the context of an empirical study. This paper presents the results of an Agile, sprint-based longitudinal study of Social Media users conducted over a two year period…
Protecting personal information privacy has become a controversial issue among online social network providers and users. Most social network providers have developed several techniques to decrease threats and risks to the users privacy. These risks include the misuse of personal information which may lead to illegal acts such as identity theft. This study aims to measure the awareness of users on protecting their personal information privacy, as well as the suitability of the privacy systems which they use to modify privacy settings. Survey results show high percentage of the use of smart pho…
I study two privacy-preserving social network graphs to dis- close the types of relationships of connecting edges and provide flexible multigrained access control. To create such graphs, my schemes employ the concept of secretaries and types of relationships. It is significantly more efficient than those that using expensive cryptographic primitives. I also show how these schemes can be used for multigrained access control with various options. In addition, I describe how much these schemes are resilient to infer the types of connecting edges.
Online Social Networks (OSN) are a permanent presence in today's personal and professional lives of a huge segment of the population, with direct consequences to offline activities. Built on a foundation of trust-users connect to other users with common interests or overlapping personal trajectories-online social networks and the associated applications extract an unprecedented volume of personal information. Unsurprisingly, serious privacy and security risks emerged, positioning themselves along two main types of attacks: attacks that exploit the implicit trust embedded in declared social rel…
Ensuring privacy of users of social networks is probably an unsolvable conundrum. At the same time, an informed use of the existing privacy options by the social network participants may alleviate - or even prevent - some of the more drastic privacy-averse incidents. Unfortunately, recent surveys show that an average user is either not aware of these options or does not use them, probably due to their perceived complexity. It is therefore reasonable to believe that tools assisting users with two tasks: 1) understanding their social net behavior in terms of their privacy settings and broad priv…
Preserving privacy of users is a key requirement of web-scale analytics and reporting applications, and has witnessed a renewed focus in light of recent data breaches and new regulations such as GDPR. We focus on the problem of computing robust, reliable analytics in a privacy-preserving manner, while satisfying product requirements. We present PriPeARL, a framework for privacy-preserving analytics and reporting, inspired by differential privacy. We describe the overall design and architecture, and the key modeling components, focusing on the unique challenges associated with privacy, coverage…
Online social networks are becoming a major growth point of the internet, as individuals, companies and governments constantly desire to interact with one another, the ability of the internet to deliver this networking capabilities grows stronger. In this paper, we looked at the structure and components of the member profile and the challenges of privacy issues faced by individuals and governments that participate in social networking. We also looked at how it can be used to distort national security, how it became the new weapons of mass mobilization and also how social networks have became t…
Many proximity-based mobile social networks are developed to facilitate connections between any two people, or to help a user to find people with matched profile within a certain distance. A challenging task in these applications is to protect the privacy the participants' profiles and personal interests. In this paper, we design novel mechanisms, when given a preference-profile submitted by a user, that search a person with matching-profile in decentralized multi-hop mobile social networks. Our mechanisms are privacy-preserving: no participants' profile and the submitted preference-profile ar…
Social media users generate tremendous amounts of data. To better serve users, it is required to share the user-related data among researchers, advertisers and application developers. Publishing such data would raise more concerns on user privacy. To encourage data sharing and mitigate user privacy concerns, a number of anonymization and de-anonymization algorithms have been developed to help protect privacy of social media users. In this work, we propose a new adversarial attack specialized for social media data. We further provide a principled way to assess effectiveness of anonymizing diffe…
With the recent surge of social networks like Facebook, new forms of recommendations have become possible - personalized recommendations of ads, content, and even new friend and product connections based on one's social interactions. Since recommendations may use sensitive social information, it is speculated that these recommendations are associated with privacy risks. The main contribution of this work is in formalizing these expected trade-offs between the accuracy and privacy of personalized social recommendations. In this paper, we study whether "social recommendations", or recommendation…
With the advent of social media, different companies often promote competing products simultaneously for word-of-mouth diffusion and adoption by users in social networks. For such scenarios of competitive diffusion, prior studies show that the weaker product will soon become extinct (i.e., "winner takes all"). It is intriguing to observe that in practice, however, competing products, such as iPhone and Android phone, often coexist in the market. This discrepancy may result from many factors such as the phenomenon that a user in the real world may not spread its use of a product due to dissatis…
In this paper, we formalize the notion of distributed sensitive social networks (DSSNs), which encompasses networks like enmity networks, financial transaction networks, supply chain networks and sexual relationship networks. Compared to the well studied traditional social networks, DSSNs are often more challenging to study, given the privacy concerns of the individuals on whom the network is knit. In the current work, we envision the use of secure multiparty tools and techniques for performing privacy preserving social network analysis over DSSNs. As a step towards realizing this, we design e…
Social relationships are a natural basis on which humans make trust decisions. Online Social Networks (OSNs) are increasingly often used to let users base trust decisions on the existence and the strength of social relationships. While most OSNs allow users to discover the length of the social path to other users, they do so in a centralized way, thus requiring them to rely on the service provider and reveal their interest in each other. This paper presents Social PaL, a system supporting the privacy-preserving discovery of arbitrary-length social paths between any two social network users. We…
Users disclose ever-increasing amounts of personal data on Social Network Service platforms (SNS). Unless SNSs' policies are privacy friendly, this leaves them vulnerable to privacy risks because they ignore the privacy policies. Designers and regulators have pushed for shorter, simpler and more prominent privacy policies, however the evidence that transparent policies increase informed consent is lacking. To answer this question, we conducted an online experiment with 214 regular Facebook users asked to join a fictitious SNS. We experimentally manipulated the privacy-friendliness of SNS's pol…
Considerable concerns exist over privacy on social networks, and huge debates persist about how to extend the artifacts users need to effectively protect their rights to privacy. While many interesting ideas have been proposed, no single approach appears to be comprehensive enough to be the front runner. In this paper, we propose a comprehensive and novel reference conceptual model for privacy in constantly evolving social networks and establish its novelty by briefly contrasting it with contemporary research. We also present the contours of a possible query language that we can develop with d…
Privacy scoring aims at measuring the privacy violation risk of a user over an online social network (OSN). Existing work in the field rely on possibly biased or emotional survey data and focus only on personel purpose OSNs like Facebook. In contrast to existing work, in this thesis, we work with real-world OSN data collected from LinkedIn, the most popular professional-purpose OSN (ProOSN). Towards this end, we developed an extensive crawler to collect all relevant profile data of 5,389 LinkedIn users, modelled these data using both relational and graph databases and quantitatively analyzed a…
This paper has been withdrawn by the author due to a crucial sign error in equation 1. With the advance of online social networks, there has been extensive research on how to spread influence in online social networks, and many algorithms and models have been proposed. However, many fundamental problems have also been overlooked. Among those, the most important problems are the incentive aspect and the privacy aspect (eg, nodes' relationships) of the influence propagation in online social networks. Bearing these defects in mind, and incorporating the powerful tool from differential privacy, we…
Social Coding Platforms (SCPs) like GitHub have become central to modern software engineering thanks to their collaborative and version-control features. Like in mainstream Online Social Networks (OSNs) such as Facebook, users of SCPs are subjected to privacy attacks and threats given the high amounts of personal and project-related data available in their profiles and software repositories. However, unlike in OSNs, the privacy concerns and practices of SCP users have not been extensively explored nor documented in the current literature. In this work, we present the preliminary results of an …
The number of people on social networks has grown exponentially. Users share very large volumes of personal informations and content every days. This content could be tagged with geo-spatial and temporal coordinates that may be considered sensitive for some users. While there is clearly a demand for users to share this information with each other, there is also substantial demand for greater control over the conditions under which their information is shared. Content published in a geo-aware social networks (GeoSN) often involves multiple users and it is often accessible to multiple users, wit…
Online social networks are being increasingly used for analyzing various societal phenomena such as epidemiology, information dissemination, marketing and sentiment flow. Popular analysis techniques such as clustering and influential node analysis, require the computation of eigenvectors of the real graph's adjacency matrix. Recent de-anonymization attacks on Netflix and AOL datasets show that an open access to such graphs pose privacy threats. Among the various privacy preserving models, Differential privacy provides the strongest privacy guarantees. In this paper we propose a privacy preserv…
A multitude of privacy breaches, both accidental and malicious, have prompted users to distrust centralized providers of online social networks (OSNs) and investigate decentralized solutions. We examine the design of a fully decentralized (peer-to-peer) OSN, with a special focus on privacy and security. In particular, we wish to protect the confidentiality, integrity, and availability of user content and the privacy of user relationships. We propose DECENT, an architecture for OSNs that uses a distributed hash table to store user data, and features cryptographic protections for confidentiality…
Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e.g., citation or social networks. However, sensitive personal information, such as documents with people's profiles or relationships as edges, are prone to privacy leaks, as the trained model might reveal the original input. Although differential privacy (DP) offers a well-founded privacy-preserving framework, GCNs pose theoretical and practical challenges due to their training specifics. We address these challenges by adapting differentially-private gradien…
