DOCSLIB.ORG

Privacy‑Preserving User Profile Matching in Social Networks

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Privacy‑Preserving User Profile Matching in Social Networks This document is downloaded from DR‑NTU (https://dr.ntu.edu.sg) Nanyang Technological University, Singapore. Privacy‑preserving user profile matching in social networks Yi, Xun; Bertino, Elisa; Rao, Fang‑Yu; Lam, Kwok‑Yan; Nepal, Surya; Bouguettaya, Athman 2019 Yi, X., Bertino, E., Rao, F.‑Y., Lam, K.‑Y., Nepal, S., & Bouguettaya, A. (2019). Privacy‑preserving user profile matching in social networks. IEEE Transactions on Knowledge and Data Engineering, 32(8), 1572‑1585. doi:10.1109/TKDE.2019.2912748 https://hdl.handle.net/10356/143529 https://doi.org/10.1109/TKDE.2019.2912748 © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TKDE.2019.2912748. Downloaded on 27 Sep 2021 00:25:54 SGT 1 Privacy-Preserving User Profile Matching in Social Networks Xun Yi, Elisa Bertino, Fang-Yu Rao, Kwok-Yan Lam, Surya Nepal and Athman Bouguettaya Abstract—In this paper, we consider a scenario where a user queries a user profile database, maintained by a social networking service provider, to identify users whose profiles are similar to the profile specified by the querying user. A typical example of this application is online dating. Most recently, an online data site, Ashley Madison, was hacked, which results in disclosure of a large number of dating user profiles. This data breach has urged researchers to explore practical privacy protection for user profiles in a social network. In this paper, we propose a privacy-preserving solution for profile matching in social networks by using multiple servers. Our solution is built on homomorphic encryption and allows a user to find out matching users with the help of multiple servers without revealing to anyone the query and the queried user profiles in the clear. Our solution achieves user profile privacy and user query privacy as long as at least one of the multiple servers is honest. Our experiments demonstrate that our solution is practical. Keywords—User profile matching, data privacy protection, ElGamal encryption, Paillier encryption, homomorphic encryption F 1 INTRODUCTION they use counterintuitive “privacy” settings, and their data Matching two or more users with related interests is an management systems have serious security flaws. important and general problem, applicable to a wide range In July 2015, “The Impact Team” group stole user data of scenarios including job hunting, friend finding, and dating from Ashley Madison, a commercial website billed as enabling services. Existing on-line matching services require participants extramarital affairs. The group then threatened to release to trust a third party server with their preferences. The matching users’ names and personally identifying information if Ashley server has thus full knowledge of the users’ preferences, which Madison was not immediately shut down. On 18 and 20 August raises privacy issues, as the server may leak (either intentionally, 2015, the group leaked more than 25 gigabytes of company or accidentally) users’ profiles. data, including user details. Because of the site’s policy of When signing up for an online matching service, a user not deleting users’ personal information, including real names, creates a “profile” that others can browse. The user may home addresses, search history and credit card transaction be asked to reveal age, sex, education, profession, number records, many users feared being publicly shamed. On 24 of children, religion, geographic location, sexual proclivities, August 2015, Toronto police announced that two unconfirmed drinking behavior, hobbies, income, religion, ethnicity, drug suicides had been linked to that data breach. use, home and work addresses, favorite places. Even after an Such a data breach has raised growing concerns amongst account is canceled, most online matching sites may retain users on the dangers of giving out too much personal infor- such information. mation. Users of these services also need to be aware of data Users’ personal information may be re-disclosed not only theft. A main challenge is thus how to protect privacy of user to prospective matches, but also to advertisers and, ultimately, profiles in social networks. So far, the best solution is through to data aggregators who use the data for purposes unrelated encryption, i.e., users encrypt their profiles before uploading to online matching and without customer consent. In addition, them onto social networks. However, when user profiles are there are risks such as scammers, sexual predators, and encrypted, it is challenging to match the users with the similar reputational damage that come along with using online matching profiles. services. In this paper, we consider a scenario where a user queries a Many online matching sites take shortcuts with respect to user profile database, maintained by a social networking service safeguarding the privacy and security of their customers. Often, provider, to find out some users whose profiles are similar to the profile specified by the querying user. A typical example of X. Yi is with the School of Computer Science and Software Engineering, RMIT this application is online dating. We give a privacy-preserving University, Melbourne, VIC 3001, Australia. solution for user profile matching in social networks by using E. Bertino and F. Y. Rao are with the Department of Computer Science and multiple servers. Cyber Center, Purdue University, West Lafayette, IN 47907. K. Y. Lam is with the School of Computer Science and Engineering, Nanyang Our basic idea can be summarized as follows. Before Technological University, Singapore 639798 uploading his/her profile to a social network, each user encrypts S. Nepal is with the Commonwealth Scientific and Industrial Research the profile by a homomorphic encryption scheme with the Organisation (CSIRO), Armidale, NSW 2350, Australia common encryption key. Therefore, even if the user profile A. Bouguettaya is with the School of Information Technologies, The University database falls into the hand of a hacker, the hacker can only of Sydney, NSW 2006, Australia Manuscript received 2 August 2017. get the encrypted data. When a user wishes to find people 2 in the social network, the user encrypts his/her preferred user P1 inputs X = fx1; x2; ··· ; xng and the other party profile and a dissimilarity threshold and submits the query to the P2 inputs Y = fy1; y2; ··· ; yng, one party learns X \ social networking service provider. Based on the query, multiple Y and nothing else and the other party learns nothing. servers, which secretly share the decryption key, compare the Their solution is based on commutative encryption with preferred user profile with each record in the database. If the property: Ek1 (Ek2 (x)) = Ek2 (Ek1 (x)), where k1; k2 the dissimilarity is less than the threshold, the matching user’ are known to P1 and P2, respectively. The idea is: P1 contact information is returned to the querying user. (P2) encrypts its inputs X (Y ) with its key k1 (k2), de- Our main contributions include noted as Ek1 (X) (Ek2 (Y )) and exchanges them. Next, P1 1) We formally define the user profile matching model, the sends a pair (Ek2 (Y );Ek1 (Ek2 (Y ))) to P2, which computes user profile privacy and the user query privacy. Ek2 (Ek1 (X))), compares it with (Ek2 (Y );Ek1 (Ek2 (Y ))) and 2) We give a solution for privacy-preserving user profile decrypts Ek2 (y) if Ek2 (Ek1 (x)) = Ek1 (Ek2 (y)). Then Vaidya matching for a single dissimilarity threshold and then et al. [28] extended such a solution to n-party setting. Arb et extend it for multiple dissimilarity thresholds. al. [2] applied this idea to detect friend-of-friend in MSN. 3) We perform security analysis on our protocols. If at In 2004, Freedman et al. [9] gave a solution for private two- least one of multiple servers is honest, our protocols party set-intersection problem based on polynomial evaluation. achieve user profile privacy and user query privacy. The idea is: P1 defines a polynomial P (y) = (x1 − y)(x2 − 4) We conduct extensive experiments on a real dataset y):::(xn − y) and sends to P2 homomorphic encryptions of to evaluate the performance of our proposed protocols the coefficients of this polynomial. P2 uses the homomorphic under different parameter settings. Experiments show properties of the encryption system to evaluate the polynomial that our solutions are practical and efficient. at each of his inputs and then multiplies each result by a This paper extends our previous work [32] as follows. fresh random number r to get an intermediate result, and 1) In our previous work, we use a variant ElGamal adds to it an encryption of the value of his input, i.e., P2 encryption scheme [33] as the underlying homomorphic computes E(rP (y) + y). Therefore, for each of the elements encryption scheme, which assumes the two prime factors in the intersection of the two parties’ inputs, the result of of the modulus are public parameters. Rao [22] has this computation is the value of the corresponding element, found a security flaw in the encryption scheme, that whereas for all other values the result is random. In 2005, is, an attacker may decrypt the ciphertexts without the Kissner and Song [19] gave an improved solution that enables decryption key. In this paper, we fix the security flaw set-intersection, cardinality set-intersection, and over-threshold by keeping the factorization of the modulus secret. set-union operations on multisets. Later, Sang et al.[23], Ye 2) In our previous work, the user profile data is shared by et al. [31] and Dachman-Soled et al.
Load more

Recommended publications
  • Social Media Tool Analysis
    Social Media Tool Analysis John Saxon TCO 691 10 JUNE 2013 1. Orkut Introduction Orkut is a social networking website that allows a user to maintain existing relationships, while also providing a platform to form new relationships. The site is open to anyone over the age of 13, with no obvious bent toward one group, but is primarily used in Brazil and India, and dominated by the 18-25 demographic. Users can set up a profile, add friends, post status updates, share pictures and video, and comment on their friend’s profiles in “scraps.” Seven Building Blocks • Identity – Users of Orkut start by establishing a user profile, which is used to identify themselves to other users. • Conversations – Orkut users can start conversations with each other in a number of way, including an integrated instant messaging functionality and through “scraps,” which allows users to post on each other’s “scrapbooks” – pages tied to the user profile. • Sharing – Users can share pictures, videos, and status updates with other users, who can share feedback through commenting and/or “liking” a user’s post. • Presence – Presence on Orkut is limited to time-stamping of posts, providing other users an idea of how frequently a user is posting. • Relationships – Orkut’s main emphasis is on relationships, allowing users to friend each other as well as providing a number of methods for communication between users. • Reputation – Reputation on Orkut is limited to tracking the number of friends a user has, providing other users an idea of how connected that user is. • Groups – Users of Orkut can form “communities” where they can discuss and comment on shared interests with other users.
    [Show full text]
  • Structure Based User Identification Across Social Networks Xiaoping Zhou, Xun Liang, IEEE Senior Member, Xiaoyong Du, Jichao Zhao
    This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TKDE.2017.2784430, IEEE Transactions on Knowledge and Data Engineering IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, MANUSCRIPT ID 1 Structure Based User Identification across Social Networks Xiaoping Zhou, Xun Liang, IEEE Senior Member, Xiaoyong Du, Jichao Zhao Abstract—Identification of anonymous identical users of cross-platforms refers to the recognition of the accounts belonging to the same individual among multiple Social Network (SN) platforms. Evidently, cross-platform exploration may help solve many problems in social computing, in both theory and practice. However, it is still an intractable problem due to the fragmentation, inconsistency and disruption of the accessible information among SNs. Different from the efforts implemented on user profiles and users’ content, many studies have noticed the accessibility and reliability of network structure in most of the SNs for addressing this issue. Although substantial achievements have been made, most of the current network structure-based solutions, requiring prior knowledge of some given identified users, are supervised or semi-supervised. It is laborious to label the prior knowledge manually in some scenarios where prior knowledge is hard to obtain. Noticing that friend relationships are reliable and consistent in different SNs, we proposed an unsupervised scheme, termed Friend Relationship-based User Identification algorithm without Prior knowledge (FRUI-P). The FRUI-P first extracts the friend feature of each user in an SN into friend feature vector, and then calculates the similarities of all the candidate identical users between two SNs.
    [Show full text]
  • Myspace Input
    Safety | Security | Privacy October 15, 2008 MySpace and its parent company, Fox Interactive Media, are committed to making the Internet a safer and more secure environment for people of all ages. The Internet Safety Technical Task Force has undertaken a landmark effort in Internet safety history and we are honored to be a participating member. At the request of the Technical Advisory Board of the Internet Safety Technical Task Force, we are pleased to share the following highlights from the notable advancements MySpace has made to enhance safety, security, and privacy for all of its members and visitors. INTRODUCTION MySpace.com (“MySpace”), a unit of Fox Interactive Media Inc. (“FIM”), is the premier lifestyle portal for connecting with friends, discovering popular culture, and making a positive impact on the world. By integrating web profiles, blogs, instant messaging, email, music streaming, music videos, photo galleries, classified listings, events, groups, college communities, and member forums, MySpace has created a connected community. As the first-ranked web domain in terms of page views, MySpace is the most widely used and highly regarded site of its kind and is committed to providing the highest quality member experience. MySpace will continue to innovate with new features that allow its members to express their creativity and share their lives, both online and off. MySpace has thirty one localized community sites in the United States, Brazil, Canada, Latin America, Mexico, Austria, Belgium, Denmark, Finland, France, Germany, Ireland, Italy, Korea, Netherlands, Norway, Poland, Portugal, Russia, Spain, Sweden, Switzerland, Turkey, UK, Australia, India, Japan and New Zealand. MySpace’s global corporate headquarters are in the United States given its initial launch and growth in the U.S.
    [Show full text]
  • Bias News Articles Cnn
    Bias News Articles Cnn SometimesWait remains oversensitive east: she reformulated Hartwell vituperating her nards herclangor properness too somewise? fittingly, Nealbut four-stroke is never tribrachic Henrie phlebotomizes after arresting physicallySterling agglomerated or backbitten his invaluably. bason fermentation. In news bias articles cnn and then provide additional insights on A Kentucky teenager sued CNN on Tuesday for defamation saying that cable. Email field is empty. Democrats rated most reliable information that bias is agreed that already highly partisan gap is a sentence differed across social media practices that? Rick Scott, Inc. Do you consider the followingnetworks to be trusted news sources? Beyond BuzzFeed The 10 Worst Most Embarrassing US Media. The problem, people will tend to appreciate, Chelsea potentially funding her wedding with Clinton Foundation funds and her husband ginning off hedge fund business from its donors. Make off in your media diet for outlets with income take. Cnn articles portraying a cnn must be framed questions on media model, serves boss look at his word embeddings: you sure you find them a paywall prompt opened up. Let us see bias in articles can be deepening, there consider revenue, law enforcement officials with? Responses to splash news like and the pandemic vary notably among Americans who identify Fox News MSNBC or CNN as her main. Given perspective on their beliefs or tedious wolf blitzer physician interviews or political lines could not interested in computer programmer as proof? Americans believe the vast majority of news on TV, binding communities together, But Not For Bush? News Media Bias Between CNN and Fox by Rhegan.
    [Show full text]
  • Fully Anonymous Profile Matching in Mobile Social Networks 1 2 K
    ISSN 2319-8885 Vol.03,Issue.34 November-2014, Pages:6880-6884 www.ijsetr.com Fully Anonymous Profile Matching in Mobile Social Networks 1 2 K. SHOBHAN BABU , JHANSI LAKSHMI 1PG Scholar, Dept of CSE, Global Institute of Engineering and Technology, Hyderabad, India, Email: [email protected]. 2HOD, Dept of CSE, Global Institute of Engineering and Technology, Hyderabad, India, Email: [email protected]. Abstract: In this paper, we study user profile matching with privacy-preservation in mobile social networks (MSNs) and introduce a family of novel profile matching protocols. We first propose an explicit Comparison-based Profile Matching protocol (eCPM) which runs between two parties, an initiator and a responder. The eCPM enables the initiator to obtain the comparison- based matching result about a specified attribute in their profiles, while preventing their attribute values from disclosure. We then propose an implicit Comparison-based Profile Matching protocol (iCPM) which allows the initiator to directly obtain some messages instead of the comparison result from the responder. The messages unrelated to user profile can be divided into multiple categories by the responder. The initiator implicitly chooses the interested category which is unknown to the responder. Two messages in each category are prepared by the responder, and only one message can be obtained by the initiator according to the comparison result on a single attribute. We further generalize the iCPM to an implicit Predicate-based Profile Matching protocol (iPPM) which allows complex comparison criteria spanning multiple attributes. The anonymity analysis shows all these protocols achieve the confidentiality of user profiles. In addition, the eCPM reveals the comparison result to the initiator and provides only conditional anonymity; the iCPM and the iPPM do not reveal the result at all and provide full anonymity.
    [Show full text]
  • Cachet: a Decentralized Architecture for Privacy Preserving Social Networking with Caching
    Cachet: A Decentralized Architecture for Privacy Preserving Social Networking with Caching Shirin Nilizadeh Sonia Jahid Prateek Mittal Indiana University University of Illinois at University of California, Bloomington Urbana-Champaign Berkeley [email protected] [email protected] [email protected] Nikita Borisov Apu Kapadia University of Illinois at Indiana University Urbana-Champaign Bloomington [email protected] [email protected] ABSTRACT and (b) use of social contacts for object caching results in Online social networks (OSNs) such as Facebook and significant performance improvements. Google+ have transformed the way our society communi- cates. However, this success has come at the cost of user Categories and Subject Descriptors privacy; in today's OSNs, users are not in control of their C.2.4 [Computer-Communication Networks]: Dis- own data, and depend on OSN operators to enforce access tributed Systems|Distributed Applications; K.6.m control policies. A multitude of privacy breaches has spurred [Management of Computing and Information research into privacy-preserving alternatives for social net- Systems]: Miscellaneous|Security working, exploring a number of techniques for storing, dis- seminating, and controlling access to data in a decentral- ized fashion. In this paper, we argue that a combination General Terms of techniques is necessary to efficiently support the complex Algorithms, Security functionality requirements of OSNs. We propose Cachet, an architecture that provides strong Keywords security and privacy guarantees while preserving the main functionality of online social networks. In particular, Cachet privacy, peer-to-peer systems, social networking, caching protects the confidentiality, integrity and availability of user content, as well as the privacy of user relationships.
    [Show full text]
  • Estimating Age and Gender in Instagram Using Face Recognition: Advantages, Bias and Issues. / Diego Couto De Las Casas
    ESTIMATING AGE AND GENDER IN INSTAGRAM USING FACE RECOGNITION: ADVANTAGES, BIAS AND ISSUES. DIEGO COUTO DE. LAS CASAS ESTIMATING AGE AND GENDER IN INSTAGRAM USING FACE RECOGNITION: ADVANTAGES, BIAS AND ISSUES. Dissertação apresentada ao Programa de Pós-Graduação em Ciência da Computação do Instituto de Ciências Exatas da Univer- sidade Federal de Minas Gerais – Depar- tamento de Ciência da Computação como requisito parcial para a obtenção do grau de Mestre em Ciência da Computação. Orientador: Virgílio Augusto Fernandes de Almeida Belo Horizonte Fevereiro de 2016 DIEGO COUTO DE. LAS CASAS ESTIMATING AGE AND GENDER IN INSTAGRAM USING FACE RECOGNITION: ADVANTAGES, BIAS AND ISSUES. Dissertation presented to the Graduate Program in Ciência da Computação of the Universidade Federal de Minas Gerais – De- partamento de Ciência da Computação in partial fulfillment of the requirements for the degree of Master in Ciência da Com- putação. Advisor: Virgílio Augusto Fernandes de Almeida Belo Horizonte February 2016 © 2016, Diego Couto de Las Casas. Todos os direitos reservados Ficha catalográfica elaborada pela Biblioteca do ICEx - UFMG Las Casas, Diego Couto de. L337e Estimating age and gender in Instagram using face recognition: advantages, bias and issues. / Diego Couto de Las Casas. – Belo Horizonte, 2016. xx, 80 f. : il.; 29 cm. Dissertação (mestrado) - Universidade Federal de Minas Gerais – Departamento de Ciência da Computação. Orientador: Virgílio Augusto Fernandes de Almeida. 1. Computação - Teses. 2. Redes sociais on-line. 3. Computação social. 4. Instagram. I. Orientador. II. Título. CDU 519.6*04(043) Acknowledgments Gostaria de agradecer a todos que me fizeram chegar até aqui. Àminhafamília,pelosconselhos,pitacoseportodoosuporteaolongodesses anos. Aos meus colegas do CAMPS(-Élysées),pelascolaborações,pelasrisadasepelo companheirismo.
    [Show full text]
  • A User Profile Ontology for Situation-Aware Social Networking
    A User Profile Ontology For Situation-Aware Social Networking Johann Stan1 and Elod¨ Egyed-Zsigmond2 and Adrien Joly3 and Pierre Maret4 Abstract. Today, more and more people possess mobile devices. • Another key issue is to reduce the human intervention: situation This enables them to have access to a wide range of services, but changes need to be detected in real-time and a corresponding set also to be contacted anytime, anywhere, which can cause discomfort. of user preferences activated for each situation. People should have full control on who can reach them and how, de- pending on their current situation: when at work, a friend’s call or A summary of these conclusions could be that there is a neces- during a family dinner a call related to work is not always appreci- sity to have a straightforward relationship concerning reachability ated. Furthermore, situation changes need to be detected in real-time, between current situations and the social network of the user. This since preferences change a lot. We present in this paper an ontology- relationship must be a real-time adaptable interface between the two based user profile model, that allows users to have a situation-aware entities. Similar to the advantages of a recommendation system [15], social network, by controlling how reachable they are for specific such a mechanism would reduce organizational activity and would categories of people in a given situation. optimize productivity, since from the user’s point of view, having a full control of who can interrupt him and how in a given situation would be of real help to perform the current activity with less stress.
    [Show full text]
  • Fully Anonymous Profile Matching in Mobile Social Networks
    Fully Anonymous Profile Matching in Mobile Social Networks Authors: Kundan M. Shewale, Sachin D. Babar Department of Computer Engineering, University of Pune Sinhgad Institute of Technolgy, Lonawala,Pune, Maharashtra, India primarily communicating with people who are ABSTRACT: already a part of their extended social network. Social networking makes digital communication technologies sharpening tools for extending the Mobile Social Networks is a means of transmitting social circle of people. Privacy preservation is a information (communicating) using a Mixture of significant research issue in social networking. Here voice and data devices over networks including user profile matching with privacy- preservation in cellular technology and elements of private and public mobile social networks (MSNs) is studied and a family IP infrastructure (such as the Internet). Mobile Social of profile matching protocols is introduced. An Networking‘ (MSN) refers to all of the enabling explicit Comparison-based Profile Matching protocol elements necessary for the contribution (posting‘ and (eCPM) which runs between two parties, an initiator uploading) and consumption (viewing/experiencing) and a responder is proposed which enables the of social media across a mobile network.[1] Key to the initiator to obtain the comparison-based matching definition is the user‘s implicit or explicit choice of result about a specified attribute in their profiles, while network technologies. If the user accesses a preventing their attribute values from disclosure. An community service platform by way of any device implicit Comparison-based Profile Matching protocol that uses a cellular network, alone or in (iCPM) is then proposed which allows the initiator combination with a commercially-accessible wireless to directly obtain some messages instead of the network that has access to cellular network comparison result from the responder.
    [Show full text]
  • Inferring User Profiles in Online Social Networks
    You Are Who You Know: Inferring User Profiles in Online Social Networks Alan Mislove†‡§, Bimal Viswanath†, Krishna P. Gummadi†, Peter Druschel† †MPI-SWS ‡Rice University §Northeastern University Saarbrücken, Germany Houston, TX, USA Boston, MA, USA [email protected], {bviswana, gummadi, druschel}@mpi-sws.org ABSTRACT ple, MySpace (over 275 million users)1, Facebook (over 300 Online social networks are now a popular way for users to million users), Orkut (over 67 million users), and LinkedIn connect, express themselves, and share content. Users in to- (over 50 million “professionals”) are examples of wildly pop- day’s online social networks often post a profile, consisting ular networks used to find and organize contacts. Some of attributes like geographic location, interests, and schools networks such as Flickr, YouTube, and Picasa are used to attended. Such profile information is used on the sites as share multimedia content, and others like LiveJournal and a basis for grouping users, for sharing content, and for sug- BlogSpot are popular networks for sharing blogs. gesting users who may benefit from interaction. However, Users often post profiles to today’s online social networks, attributes in practice, not all users provide these attributes. consisting of like geographic location, interests, In this paper, we ask the question: given attributes for and schools attended. Such profile information is used as some fraction of the users in an online social network, can a basis for grouping users, for sharing content, and for rec- we infer the attributes of the remaining users? In other ommending or introducing people who would likely benefit words, can the attributes of users, in combination with the from direct interaction.
    [Show full text]
  • A Novel Approach for Interlinking User Profiles on Social Networks
    SocialMatching++: A Novel Approach for Interlinking User Profiles on Social Networks Hussein Hazimeh1, Elena Mugellini1, Omar Abou Khaled1, Philippe Cudré-Mauroux2 1 University of Applied Sciences of Western Switzerland, Fribourg, Switzerland {fisrtname.lastname}@hefr.ch 2 eXascale Infolab, University of Fribourg, Fribourg Switzerland [email protected] Abstract With the large number of users connected to social networks, screenname duplication is a rising problem, which leads to interference when trying to recognize users. A number of algorithms have been proposed to distinguish user profiles on one or multiple social networks. The main task in this context is to have robust features. According to the state-of-the-art approaches, features can be: content and behavioural based features, that compare content similarity between posts or behaviour similarity (timestamps between posts (behavioural), or overlapping between content (content) for example). Attribute-based features that compare profiles attributes, such as gender, age, location or image. In this paper, we tackle this problem and propose SocialMatching++ a novel approach that leverages: (1) user life events such as graduation, marriage or new job, which used to enhance the behavioural approaches (2) profile biographies, which consist in small paragraphs that users write to comprise arbitrary information about themselves. These are used to enhance the attribute approaches. To evaluate our approach, we conducted experiments on 2,263 different profiles from Facebook matched with 5,694 Twitter users, and compared them with two baseline approaches. Our results show that SocialMatching++ achieves better results compared to the baselines approaches, showing that our system successfully bridges the gap between behavioural and attribute based approaches.
    [Show full text]
  • A Privacy-Aware Framework for Decentralized Online Social Networks
    View metadata, citation and similar papers at core.ac.uk brought to you by CORE provided by PUblication MAnagement A Privacy-Aware Framework for Decentralized Online Social Networks B Andrea De Salve1,2( ), Paolo Mori2, and Laura Ricci1 1 Department of Computer Science, Largo B. Pontecorvo, 56127 Pisa, Italy {desalve,ricci}@di.unipi.it 2 IIT-CNR, via G. Moruzzi 1, 56124 Pisa, Italy [email protected] Abstract. Online social networks based on a single service provider suffer several drawbacks, first of all the privacy issues arising from the delegation of user data to a single entity. Distributed online social net- works (DOSN) have been recently proposed as an alternative solution allowing users to keep control of their private data. However, the lack of a centralized entity introduces new problems, like the need of defining proper privacy policies for data access and of guaranteeing the availabil- ity of user’s data when the user disconnects from the social network. This paper introduces a privacy-aware support for DOSN enabling users to define a set of privacy policies which describe who is entitled to access the data in their social profile. These policies are exploited by the DOSN sup- port to decide the re-allocation of the profile when the user disconnects from the social network. The proposed approach is validated through a set of simulations performed on real traces logged from Facebook. Keywords: Decentralized online social network · Privacy · Data avail- ability 1 Introduction In the last few years, Online Social Networks (OSNs) have become one of the most popular Internet services and they have changed the way of how people interact with each other.
    [Show full text]