Analyzing and Securing Social Networks

Analyzing and Securing Social Networks focuses on the two major technologies that have been developed for online social networks (OSNs): (i) data mining technologies for analyzing these networks and extracting useful information such as location, demographics, and sentiments of the participants of the network, and (ii) security and privacy technologies that ensure the privacy of the participants of the network as well as provide controlled access to the information posted and exchanged by the participants. The authors explore security and privacy issues for social media systems, analyze such systems, and discuss prototypes they have developed for social media systems whose data are represented using semantic web technologies. These experimental systems have been developed at The University of Texas at Dallas. The material in this book, together with the numerous references listed in each chapter, have been used for a graduate-level course at The University of Texas at Dallas on analyzing and securing social media. Several experimental systems developed by graduate students are also provided. The book is divided into nine main sections: (1) supporting technologies, (2) basics of analyzing and securing social networks, (3) the authors’ design and implementation of various social network analytics tools, (4) privacy aspects of social networks, (5) access control and inference control for social networks, (6) experimental systems designed or developed by the authors on analyzing and securing social networks, (7) social media application systems developed by the authors, (8) secure social media systems developed by the authors, and (9) some of the authors’ exploratory work and further directions.

IntroductionOverviewAnalyzing Social NetworksSecuring Social NetworksOutline of the BookNext StepsSUPPORTING TECHNOLOGIESSocial Networks: A SurveyIntroductionSurvey of Social NetworksDetails of Four Popular Social NetworksSummary and ConclusionData Security and PrivacyOverviewSecurity PoliciesPolicy Enforcement and Related IssuesData PrivacySummary and DirectionsReferencesData Mining TechniquesIntroductionOverview of Data Mining Tasks and TechniquesArtificial Neural NetworksSupport Vector MachinesMarkov ModelAssociation Rule Mining (ARM)Multiclass ProblemImage MiningSummaryReferencesCloud Computing and Semantic Web TechnologiesIntroductionCloud ComputingSemantic WebSemantic Web and SecurityCloud Computing Frameworks Based on Semantic Web TechnologiesSummary and DirectionsReferencesASPECTS OF ANALYZING AND SECURING SOCIAL NETWORKSAnalyzing and Securing Social NetworksIntroductionApplications in Social Media AnalyticsData Mining Techniques for SNASecurity and PrivacySummary and DirectionsReferencesSemantic Web-Based Social Network Representation and AnalysisIntroductionSocial Network RepresentationOur Approach to Social Network AnalysisSummary and DirectionsReferenceConfidentiality, Privacy, and Trust for Social Media DataIntroductionTrust, Privacy, and ConfidentialityCPT FrameworkOur Approach to Confidentiality ManagementPrivacy for Social NetworksTrust for Social NetworksIntegrated SystemCPT within the Context of Social NetworksSummary and DirectionsReferencesTECHNIQUES AND TOOLS FOR SOCIAL NETWORK ANALYTICSDevelopments and Challenges in Location MiningIntroductionKey Aspects of Location MiningEfforts in Location MiningChallenges in Location MiningGeospatial Proximity and FriendshipOur Contributions to Location MiningSummary and DirectionsReferencesTweetHood: A Social Media Analytics ToolIntroductionTweetHoodExperiments and ResultsSummary and DirectionsReferencesTweecalization: Location Mining Using Semisupervised LearningIntroductionTweecalizationTrustworthiness and Similarity MeasureExperiments and ResultsSummary and DirectionsReferencesTweeque: Identifying Social Cliques for Location MiningIntroductionEffect of MigrationTemporal Data MiningSocial Clique IdentificationExperiments and ResultsLocation PredictionAgglomerative Hierarchical ClusteringMapIt: Location Mining from Unstructured TextSummary and DirectionsReferencesUnderstanding News Queries with Geo-Content Using TwitterIntroductionApplication of Location Mining and Social Networks for Improving Web SearchAssigning Weights to TweetsSemantic SimilarityExperiments and ResultsSummary and DirectionsReferencesSOCIAL NETWORK ANALYTICS AND PRIVACY CONSIDERATIONSOur Approach to Studying Privacy in Social NetworksIntroductionRelated WorkDefinitional PreliminariesAnalysisData GatheringSummary and DirectionsReferencesClassification of Social Networks Incorporating Link TypesIntroductionRelated WorkLearning MethodsExperimentsResultsSummary and DirectionsReferencesExtending Classification of Social Networks through Indirect FriendshipsIntroductionRelated Work and Our ContributionsDefinitionsOur ApproachExperiments and ResultsSummary and DirectionsReferencesSocial Network Classification through Data PartitioningIntroductionRelated Work and Our ContributionsMetricsDistributed Social Network ClassificationExperimentsSummary and DirectionsReferencesSanitization of Social Network Data for Release to Semitrusted Third PartiesIntroductionLearning Methods on Social NetworksHiding Private InformationExperimentsEffect of Sanitization on Other Attack TechniquesEffect of Sanitization on UtilitySummary and DirectionsReferencesACCESS CONTROL AND INFERENCE FOR SOCIAL NETWORKSAccess Control for Social NetworksIntroductionRelated WorkModeling Social Networks Using Semantic Web TechnologiesSecurity Policies for OSNsSecurity Policy SpecificationSecurity Rule EnforcementSummary and DirectionsReferencesImplementation of an Access Control System for Social NetworksIntroductionSecurity in Online Social NetworksFramework ArchitectureExperimentsSummary and DirectionsReferencesInference Control for Social MediaOverviewDesign of an Inference ControllerInference Control through Query ModificationApplication to Social Media DataSummary and DirectionsReferencesImplementing an Inference Controller for Social Media DataOverviewInference and ProvenanceImplementation of the Inference ControllerGeneratorsUse Case: Medical ExampleImplementing ConstraintsSummary and DirectionsReferencesSOCIAL MEDIA INTEGRATION AND ANALYTICS SYSTEMSSocial Graph Extraction, Integration, and AnalysisIntroductionEntity Extraction and IntegrationOntology-Based Heuristic ReasoningGraph AnalysisManaging and Querying Large RDF GraphsSummary and DirectionsReferencesSemantic Web-Based Social Network IntegrationOverviewInformation Integration in Social NetworksJena–HBase: A Distributed, Scalable, and Efficient RDF Triple StoreStormRider: Harnessing Storm for Social NetworksOntology-Driven Query Expansion Using MapReduce FrameworkSummary and DirectionsReferencesExperimental Cloud Query Processing System for Social NetworksIntroductionOur ApproachRelated WorkArchitectureMapReduce FrameworkResults Summary and DirectionsReferencesSocial Networking in the CloudIntroductionFoundational Technologies for SNODSOC++Design of SNODSOCToward SNODSOC++Cloud-Based Social Network AnalysisStormRider: Harnessing Storm for Social NetworksRelated WorkSummary and DirectionsReferencesSOCIAL MEDIA APPLICATION SYSTEMSGraph Mining for Insider Threat DetectionIntroductionChallenges, Related Work, and Our ApproachGraph Mining for Insider Threat DetectionComprehensive FrameworkSummary and DirectionsReferencesTemporal Geosocial Mobile Semantic WebIntroductionChallenges for a Successful SAROSupporting Technologies for SAROOur Approach to Building a SARO SystemConclusionReferencesSocial Media and BioterrorismIntroductionSimulating Bioterrorism through Epidemiology AbstractionOn the Mitigation of Bioterrorism through the Game TheorySummary and DirectionsReferencesStream Data Analytics for Multipurpose Social Media ApplicationsIntroductionOur PremiseModules of InXiteOther ApplicationsRelated WorkSummary and DirectionsReferencesSECURE SOCIAL MEDIA SYSTEMSSecure Cloud Query Processing with Relational Data for Social MediaOverviewRelated WorkSystem ArchitectureImplementation Details and ResultsSummary and DirectionsReferencesSecure Cloud Query Processing for Semantic Web-Based Social MediaOverviewBackgroundAccess ControlSystem ArchitectureExperimental Setup and ResultsSummary and DirectionsReferencesCloud-Centric Assured Information Sharing for Social NetworksIntroductionDesign PhilosophySystem DesignRelated WorkCommercial DevelopmentsExtensions for Social Media ApplicationsSummary and DirectionsReferencesSocial Network Integration and Analysis with Privacy PreservationIntroductionSocial Network AnalysisLimitations of Current Approaches for Privacy-Preserving Social NetworksPrivacy Preservation of Social Network DataApproach by Yang and ThuraisinghamFramework of Information Sharing and Privacy Preservation for Integrating Social NetworksSummary and DirectionsReferencesAttacks on Social Media and Data Analytics SolutionsIntroductionMalware and AttacksAttacks on Social MediaData Analytics SolutionsCloud-Based Malware Detection for Evolving Data StreamsSummary and DirectionsReferencesSECURE SOCIAL MEDIA DIRECTIONSUnified Framework for Analyzing and Securing Social MediaOverviewDesign of Our FrameworkGlobal Social Media Security and Privacy ControllerSummary and DirectionsReferencesIntegrity Management and Data Provenance for Social MediaOverviewIntegrity, Data Quality, and ProvenanceIntegrity Management, Cloud Services, and Social MediaSummary and DirectionsReferencesMultilevel Secure Online Social NetworksIntroductionMultilevel Secure Database Management SystemsMultilevel Online Social NetworksSummary and DirectionsReferencesDeveloping an Educational Infrastructure for Analyzing and Securing Social Medi

Dr. Bhavani Thuraisingham is the Louis A. Beecherl, Jr. distinguished professor of computer science and the executive director of the Cyber Security Research and Education Institute at the University of Texas at Dallas. She has 35 years of work experience in commercial industry (Honeywell), federally funded research and development center (MITRE), government (NSF) and academia. Dr. Thuraisingham has conducted research in cyber security for thirty years and specializes in applying data analytics for cyber security. Her work has resulted in over 100 keynote addresses, 120 journal papers, 300 conference papers, 15 books, and 8 patents. Dr. Murat Kantarcioglu is a professor of computer science at The University of Texas at Dallas. He is recipient of an NSF CAREER award and a Purdue CERIAS Diamond Award for academic excellence. Currently, he is a visiting scholar at Harvard's Data Privacy Lab. His research has been supported by awards from NSF, AFOSR, ONR, NSA, and NIH. He has published over 150 peer-reviewed papers. Also, his work has been covered by media outlets such as Boston Globe and ABC News, among others, and has received three best-paper awards. He is a senior member of both ACM and IEEE. Dr. Latifur Khan is a full professor (tenured) in the computer science department at the University of Texas at Dallas, where he has been teaching and conducting research since September 2000. He earned his PhD and MS degrees in computer science from the University of Southern California in August of 2000 and December of 1996 respectively. He has received prestigious awards, including the IEEE Technical Achievement Award for Intelligence and Security Informatics. He has given many keynote addresses, such as at the IEEE International Conference on Tools with Artificial Intelligence ICTAI 2010 in Arras, France. Dr. Vaibhav Khadilkar completed his MS degree at Lamar University, and after working as a systems administrator for a few years, joined UTD for his PhD. He conducted research in secure semantic web, assured information sharing, and secure social networking, and completed his PhD in 2013. He received a scholarship from the CSI for his outstanding contributions. He has published numerous papers in top tier venues and is currently employed at NutraSpace in Dallas. Satyen Abrol is a senior member of the technical staff at VMware, San Francisco Bay Area. He was a research assistant at the University of Texas at Dallas from August 2008 to May 2013, where he was associated with data mining and machine learning in online social networks. From May 2012 to August 2012, he worked at VMware in Palo Alto, CA, where he designed and implemented modules for storage, indexing, and querying of performance data. He also built pattern recognition modules for detecting performance regression, outlier detection, step detection, and correlation calculation. Dr. Raymond Heatherly is lead data scientist at SHYFT Analytics, in the Greater Boston Area, where he is responsible for researching and implementing statistical tools for clinical and pharmaceutical analytical packages. He also is responsible for coordinating with the software development team to ensure that statistical components function within overall product offerings. Prior to that, he was a postdoctoral fellow at Vanderbilt University from August 2011 to July 2015, conducting research in electronic medical-record sharing and privacy, primarily for the eMERGE Consortium.