7,982 Hits in 5.1 sec

An Automated Social Graph De-anonymization Technique

Kumar Sharad, George Danezis
2014 Proceedings of the 13th Workshop on Privacy in the Electronic Society - WPES '14  
Degrees of the 1-hop sub-graph of 1-hop nodes is preserved. Can be used as a stable signature. A piecemeal approach towards de-anonymization does not scale.  ...  Recover full communication graph. Gap: Lack of an attack does not imply security. An Ad-hoc Attack Transformation into egonets preserves an important variant.  ... 
doi:10.1145/2665943.2665960 dblp:conf/wpes/SharadD14 fatcat:aufwemfvdnfcpey272xpptp2am

An Automated Social Graph De-anonymization Technique [article]

Kumar Sharad, George Danezis
2014 arXiv   pre-print
We present a generic and automated approach to re-identifying nodes in anonymized social networks which enables novel anonymization techniques to be quickly evaluated.  ...  It uses machine learning (decision forests) to matching pairs of nodes in disparate anonymized sub-graphs.  ...  Our work uses these techniques for the first time in an adversarial de-anonymization setting: whereas previous de-anonymization techniques considered graphs that were organically noisy but structurally  ... 
arXiv:1408.1276v2 fatcat:dcwft434jrfwfjte2wv6mya7k4

Privacy-Preserving WebID Analytics on the Decentralized Policy-Aware Social Web

Yuh Jong Hu
2014 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)  
Graph-parallel analytics for discovering various social network's degree centralities, and data-parallel analytics for data anonymizing and output perturbation.  ...  foaf : knows [ a foaf : Person; / * De − identification * / foaf : name "Ya − Ling Huang"; rdfs : seeAlso / * enhanced microdata protection techniques * / < http : //  ...  Part I An Ontology for Data Releasing Policy (DRP)  ... 
doi:10.1109/wi-iat.2014.140 dblp:conf/webi/Hu14 fatcat:b7ayeoho2vf4vlptjpx2rvk2im

On anonymizing social network graphs

Anne V.D.M. Kayem, Azhar Deshai, Stuart Hammer
2012 2012 Information Security for South Africa  
Previous work has focused on two major approaches to anonymizing data namely, clustering and graph modifications.  ...  The proliferation of social networks as a means of seamless communication between multiple parties across vast geographical distances has driven an increased interest from government organizations and  ...  that provoke de-anonymizations in anonymized social network graphs.  ... 
doi:10.1109/issa.2012.6320456 dblp:conf/issa/KayemDH12 fatcat:qmtx2mrpejaktbwpasrigtwyky

Understanding structure-based social network de-anonymization techniques via empirical analysis

Jian Mao, Wenqian Tian, Jingbo Jiang, Zhaoyuan He, Zhihong Zhou, Jianwei Liu
2018 EURASIP Journal on Wireless Communications and Networking  
However, de-anonymization techniques are actively studied to identify weaknesses in current social network data-publishing mechanisms.  ...  Anonymization techniques are widely adopted to protect users' privacy during social data publishing and sharing.  ...  De-anonymization mechanisms Attack model Generally, de-anonymization is to reidentify an anonymized social graph by using an auxiliary graph, which means to establish a mapping μ between two graphs.  ... 
doi:10.1186/s13638-018-1291-2 fatcat:r3h5b4yaonczdjtqljwr3bzzty

Achieving Anonymity against Major Face Recognition Algorithms [chapter]

Benedikt Driessen, Markus Dürmuth
2013 Lecture Notes in Computer Science  
An ever-increasing number of personal photos is stored online. This trend can be problematic, because face recognition software can undermine user privacy in unexpected ways.  ...  We show that we are able to achieve strong de-identification while maintaining reasonable image quality.  ...  of social networks: First, automated extraction of the social graph, i.e, friendship relations; second, automated tagging of people in images.  ... 
doi:10.1007/978-3-642-40779-6_2 fatcat:uisnrbryxffmvicap7kbcjrxxa

Link Prediction by De-anonymization: How We Won the Kaggle Social Network Challenge [article]

Arvind Narayanan, Elaine Shi, Benjamin I. P. Rubinstein
2011 arXiv   pre-print
We introduce a new simulated annealing-based weighted graph matching algorithm for the seeding step of de-anonymization.  ...  on the de-anonymized portion of the test set, and combining probabilistic predictions from de-anonymization and link prediction.  ...  Releasing useful social network graph data that is resilient to de-anonymization remains an open question. II.  ... 
arXiv:1102.4374v1 fatcat:hmzcsy7tcza3rgfvakueqcwwja

Privacy and security in online social networks: A survey

Imrul Kayes, Adriana Iamnitchi
2017 Online Social Networks and Media  
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  ...  This article provides an overview of the privacy and security issues that emerged so far in OSNs.  ...  De-anonymization Attacks In de-anonymization attacks, an attacker uses external background knowledge and published social data to de-anonymize/identify users in the social graph, and thus learn sensitive  ... 
doi:10.1016/j.osnem.2017.09.001 fatcat:xme5wwkyfbhnpgoiwgadknageq

On the Hardness of Graph Anonymization

Charu C. Aggarwal, Yao Li, Philip S. Yu
2011 2011 IEEE 11th International Conference on Data Mining  
Our experimental results also show that the true anonymization level of graphs is much lower than is implied by measures such as k-anonymity.  ...  In this paper, we examine the problem of node re-identification from anonymized graphs. Typical graphs encountered in real applications are massive and sparse.  ...  CONCLUSIONS In this paper, we examined the problem of massive graph anonymization and proposed a technique for mounting reidentification attacks on the nodes.  ... 
doi:10.1109/icdm.2011.112 dblp:conf/icdm/AggarwalLY11 fatcat:jerehfwlyfdyrp473gue5p3jma

A survey of graph-modification techniques for privacy-preserving on networks

Jordi Casas-Roma, Jordi Herrera-Joancomartí, Vicenç Torra
2016 Artificial Intelligence Review  
In this paper we summarize privacy-preserving techniques, focusing on graph-modification methods which alter graph's structure and release the entire anonymous network.  ...  Some of them were picked out from relational dataset anonynimization techniques, which are riper than network anonymization techniques.  ...  Sharad and Danezis (2014) presented an automated approach to re-identifying nodes in anonymized social networks which uses machine learning (decision forests) to matching pairs of nodes in disparate anonymized  ... 
doi:10.1007/s10462-016-9484-8 fatcat:urgdo2l35rag3bneqgmwyxnkhm

De-Health: All Your Online Health Information Are Belong to Us [article]

Shouling Ji, Qinchen Gu, Haiqin Weng, Qianjun Liu, Qinming He, Raheem Beyah, Ting Wang
2019 arXiv   pre-print
De-Health consists of two phases: Top-K DA, which identifies a candidate set for each anonymized user, and refined DA, which de-anonymizes an anonymized user to a user in its candidate set.  ...  We present a novel online health data De-Anonymization (DA) framework, named De-Health.  ...  After obtaining the anonymized data ∆ 1 and the auxiliary data ∆ 2 , we extract the features of the data and transform them into an anonymized graph and an auxiliary graph, denoted by G 1 = (V 1 , E 1  ... 
arXiv:1902.00717v2 fatcat:xsr4swglujhtjnjdtp35mhgcpm

Security Issues in Online Social Networks

Hongyu Gao, Jun Hu, Tuo Huang, Jingnan Wang, Yan Chen
2011 IEEE Internet Computing  
This article surveys the current state of security issues and available defense mechanisms regarding popular online social networks.  ...  They offer an in-depth discussion of each category and analyze the connections among the different security issues involved.  ...  Unfortunately, de-anonymizing attacks might be able to reidentify a particular user in the anonymized social network, thus defeating anonymization and breaching that user's privacy.  ... 
doi:10.1109/mic.2011.50 fatcat:e7gf4ye57veahefdhznoetbzgm

The Age of Confidentiality: A Review of the Security in Social Networks and Internet [chapter]

Antonio Juan Sánchez, Yves Demazeau
2014 Advances in Intelligent Systems and Computing  
Security based on content analysis in social networks has become a hot spot as a result of the recent problems of violations of privacy by governments to international security agencies.  ...  This article is an approach to the implementation of programs for extraction and analysis of the web information, this includes the technical difficulties and the legal consequences involved.  ...  and "Ley 56/2007 de Medidas de Impulso de la Sociedad de la Información".  ... 
doi:10.1007/978-3-319-07593-8_47 fatcat:cy7acvzo25c7fasgit255t2llu

Data Mining in Social Media [chapter]

Geoffrey Barbier, Huan Liu
2011 Social Network Data Analytics  
This chapter introduces the basics of data mining, reviews social media, discusses how to mine social media data, and highlights some illustrative examples with an emphasis on social networking sites and  ...  Data mining techniques provide researchers and practitioners the tools needed to analyze large, complex, and frequently changing social media data.  ...  The second author would like to acknowledge the grants by AFOSR (FA95500810132) and NSF (#0812551) on social computing and data mining.  ... 
doi:10.1007/978-1-4419-8462-3_12 fatcat:hbngavq4frhl7fenghg6rlomn4

4.3 Use of the Semantic Web in e-Research [chapter]

Kieron O'Hara, Tim Berners-Lee, Wendy Hall, Nigel Shadbolt
2010 World Wide Research  
SPARQL supports a number of querying functions, including the querying of an RDF graph for required or optional graph patterns, as well as for conjunctions and disjunctions of patterns.  ...  In particular, it can be used to express queries across diverse data sources, if the data is either stored in RDF or can be viewed as an RDF graph via middleware.  ... 
doi:10.7551/mitpress/9780262014397.003.0016 fatcat:nynfyli355cw5ooocr25ftnryi
« Previous Showing results 1 — 15 out of 7,982 results