Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/6260Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 雷欽隆(Chin-Laung Lei) | |
| dc.contributor.author | Pei-jinn Chai | en |
| dc.contributor.author | 蔡佩真 | zh_TW |
| dc.date.accessioned | 2021-05-16T16:24:24Z | - |
| dc.date.available | 2013-07-08 | |
| dc.date.available | 2021-05-16T16:24:24Z | - |
| dc.date.copyright | 2013-07-08 | |
| dc.date.issued | 2013 | |
| dc.date.submitted | 2013-06-27 | |
| dc.identifier.citation | [1] Choose who you share with. http://www.facebook.com/help/459934584025324/. Online; accessed 2013.
[2] Class adaboostm1. http://weka.sourceforge.net/doc/weka/classifiers/meta/AdaBoostM1.html. Online; accessed 2013. [3] A priori selection of svm class weights. http://stats.stackexchange.com/questions/24959/a-priori-selection-of-svm-class-weights. On-line; accessed 2012. [4] Mohamed Aly. Survey on multiclass classification methods. Neural Netw, pages 1–9, 2005. [5] Beomjoon Kim Boris Babenko, Abhishek Shivkumar. For what kind of classification problems is svm a bad approach? http://www.quora.com/Support-Vector-Machines/ For-what-kind-of-classification-problems-is-SVM-a-bad-approach, 2013. Online; accessed 2013. [6] Josh Constine. Facebook has users identify friends in photos to verify accounts, prevent unauthorized access. http://www.insidefacebook.com/2010/07/26/facebook-photos-verify/, 2010. Online; accessed 2013. [7] Hanif Mohaddes Deylami and Yashwant Prasad Singh. Cybercrime detection tech-niques based on support vector machines. Artificial Intelligence Research, 2(1):1–12, 2012. [8] Dominique Gay et. al. Can we say that svm is the best classifier to date? http://www.researchgate.net/post/Can_we_say_that_SVM_is_the_best_classifier_to_date14, 2012. Online; accessed 2013. [9] Lenny Zeltser (GIAC Security Expert). Beyond logins: Continuous and seamless user authentication. http://blog.zeltser.com/post/41275913909/continuous-user-authentication, 2013. Online; accessed 2013. [10] Facebook. Facebook security. http://www.facebook.com/security. Online; accessed 2012. [11] A. Felt and D. Evans. Privacy protection for social networking apis. 2008 Web 2.0 Security and Privacy (W2SP’08), 2008. [12] L. Gyarmati and T.A. Trinh. Measuring user behavior in online social networks. Network, IEEE, 24(5):26–31, 2010. [13] Jianming He, Wesley Chu, and Zhenyu Liu. Inferring privacy information from social networks. Intelligence and Security Informatics, pages 154–165, 2006. [14] Plurilock Security Solutions Inc. What is continuous authentication? http://www.plurilock.com/blog/what-continuous-authentication, 2011. Online; accessed 2013. [15] Alexandros Karatzoglou, Alex Smola, Kurt Hornik, and Achim Zeileis. kernlab-ans4 package for kernel methods in r. 2004. [16] Paul Mah. Stored passwords add to mobile security risks. http://www.itbusinessedge.com/cm/blogs/mah/stored-passwords-add-to-mobile-security-risks/?cs=47183, 2011. Online; accessed 2013. [17] S. Mahmood and Y. Desmedt. Your facebook deactivated friend or a cloaked spy. In 10th IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops), pages 367–373. IEEE, 2012. [18] Lee Newberg. Some useful statistics definitions. http://www.cs.rpi.edu/~leen/misc-publications/SomeStatDefs.html, 2005. Online; accessed 2013. [19] Koichiro Niinuma and Anil K Jain. Continuous user authentication using temporal information. Defense, Security, and Sensing, 7667:76670L, 2010. [20] Koichiro Niinuma, Unsang Park, and Anil K Jain. Soft biometric traits for continu-ous user authentication. IEEE Transactions on Information Forensics and Security, 5(4):771–780, 2010. [21] SJ Shepherd. Continuous authentication by analysis of keyboard typing characteristics. 1995. [22] StatSoft. Support vector machines (svm). http://www.statsoft.com/textbook/support-vector-machines/. Online; accessed 2012. [23] S Sudarvizhi and S Sumathi. A review on continuous authentication using mul-timodal biometrics. International Journal of Emerging Technology and Advanced Engineering, 3(1), 2013. [24] Cong Tang, Keith Ross, Nitesh Saxena, and Ruichuan Chen. What’s in a name: A study of names, gender inference, and gender behavior in facebook. Database Systems for Adanced Applications, pages 344–356, 2011. [25] Credant Technologies. Phone data makes 4.2 million* brits vulnerable to id theft. http://www.credant.com/news-a-events/press-releases/4569-phone-data-makes-42-million-brits-vulnerable-to-id-theft.html. Online; accessed 2013. [26] Telerik. Fiddler web debugger. http://www.fiddler2.com/fiddler2/. Online; accessed 2012. [27] Jason Weston, Sayan Mukherjee, Olivier Chapelle, Massimiliano Pontil, Tomaso Poggio, and Vladimir Vapnik. Feature selection for svms. Advances in neural information processing systems, pages 668–674, 2001. [28] Wikipedia. Cross-validation (statistics). http://en.wikipedia.org/wiki/Cross-validation_(statistics). Online; accessed 2013. [29] Wikipedia. Mann–whitney u. http://en.wikipedia.org/wiki/Mann\%E2%80%93Whitney_U. Online; accessed 2012. [30] Wikipedia. P-value. http://en.wikipedia.org/wiki/P-value. Online; accessed 2012. [31] Wikipedia. Six degrees of separation. http://en.wikipedia.org/wiki/Six_degrees_of_separation. Online; accessed 2013. [32] C. Wilson, B. Boe, A. Sala, K.P.N. Puttaswamy, and B.Y. Zhao. User interactions in social networks and their implications. In Proceedings of the 4th ACM European conference on Computer systems, pages 205–218. ACM, 2009. [33] R. Wishart, D. Corapi, A. Madhavapeddy, and M. Sloman. Privacy butler: A per-sonal privacy rights manager for online presence. In 8th IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Work-shops), pages 672–677. IEEE, 2010. [34] Roland HC Yap, Terence Sim, Geraldine XY Kwang, and R Ramnath. Physical access protection using continuous authentication. In 2008 IEEE Conference on Technologies for Homeland Security, pages 510–512. IEEE, 2008. [35] Sausan Yazji, Xi Chen, Robert P Dick, and Peter Scheuermann. Implicit user re-authentication for mobile devices. In Ubiquitous Intelligence and Computing, pages 325–339. Springer, 2009. [36] Alyson L Young and Anabel Quan-Haase. Information revelation and internet privacy concerns on social network sites: a case study of facebook. In Proceedings of the fourth international conference on Communities and technologies, pages 265–274. ACM, 2009. [37] Chong Ho Yu. Resampling methods: concepts, applications, and justification. Prac-tical Assessment, Research & Evaluation, 8(19):1–23, 2003. [38] E. Zheleva and L. Getoor. To join or not to join: the illusion of privacy in social networks with mixed public and private user profiles. In Proceedings of the 18th international conference on World wide web, pages 531–540. ACM, 2009. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/6260 | - |
| dc.description.abstract | 社群網站上的個人資料是重要的課題，因為一旦社群網站的個人帳號被盜用，所有在上面的個人資料都會被第三者取得，不論帳號擁有者做過任何隱私權設定。因此，本篇論文以統計方法並使用Support Vector Machine (SVM)，進行臉書的盜用行為偵測。經由分析使用者在線上的瀏覽紀錄，可以發現正常的使用者在社群網站的行為比較主動，盜用帳號者偏好閱讀私人訊息。 | zh_TW |
| dc.description.abstract | Privacy of personal information on social networking websites has become an important issue, because when a social networking website account is used by a person other than the owner, all personal data stored on the website can be retrieved, no matter how the owner sets the privacy options. Therefore, this paper proposes a statistical approach with the use of Support Vector Machine (SVM) to detect whether the Facebook account user is the actual owner. By analyzing online browsing behavior features, it is found that the normal user tends to be more active and that the stealthy user prefers to read personal messages. | en |
| dc.description.provenance | Made available in DSpace on 2021-05-16T16:24:24Z (GMT). No. of bitstreams: 1 ntu-102-R00921029-1.pdf: 542164 bytes, checksum: f10d91783f76f9d6267377464a0fa1b3 (MD5) Previous issue date: 2013 | en |
| dc.description.tableofcontents | List of Figures 7
List of Tables 8 1 Introduction 9 1.1 Personal Information Online . . . . . . . . . . . . . . . . . . . . . . . . 9 1.2 The Problem of Online Social Networks . . . . . . . . . . . . . . . . . . 10 1.3 Our Contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2 Related Work 12 2.1 Security and Privacy for Online Social Networks . . . . . . . . . . . . . 12 2.2 Continuous Authentication . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.3 The Importance of Statistical Behavior Analysis . . . . . . . . . . . . . . 13 3 Problem Description 15 3.1 Assumptions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 3.2 Limitations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.3 Goals . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4 Data Collection and Processing 17 4.1 Experiment Conduction . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.2 Data Recording . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.3 Data Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5 Models for Data Analysis 23 5.1 Support Vector Machine . . . . . . . . . . . . . . . . . . . . . . . . . . 23 5.2 Cross Validation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 5.3 Structure of Data Results . . . . . . . . . . . . . . . . . . . . . . . . . . 26 5.4 Primary Methods and Results . . . . . . . . . . . . . . . . . . . . . . . . 28 5.4.1 Discovering New Features . . . . . . . . . . . . . . . . . . . . . 29 5.4.2 Basic 2-class SVM . . . . . . . . . . . . . . . . . . . . . . . . . 30 5.4.3 SVM with P-value Variable Selection . . . . . . . . . . . . . . . 30 5.5 Secondary Methods and Results . . . . . . . . . . . . . . . . . . . . . . 32 5.5.1 Weight Adjustment . . . . . . . . . . . . . . . . . . . . . . . . . 34 5.5.2 Oversampling . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 5.5.3 3-class SVM . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 6 Model Validation and Discussion 38 6.1 Separate Training and Testing Dataset Results . . . . . . . . . . . . . . . 38 6.2 Method Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 6.3 Explanation of Results . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 6.4 Security Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 6.5 Limitations to this Research . . . . . . . . . . . . . . . . . . . . . . . . 40 7 Conclusion 42 References 43 Appendices 48 A The Most Important 36 Features 48 B All 43 Binary Features 52 C Initial Top 30 Features 56 | |
| dc.language.iso | en | |
| dc.subject | cross validation | en |
| dc.subject | en | |
| dc.subject | account misuse | en |
| dc.subject | statistical approach | en |
| dc.subject | Support Vector Machine (SVM) | en |
| dc.subject | classification | en |
| dc.title | 以統計方法進行Facebook盜用行為偵測 | zh_TW |
| dc.title | Facebook Account Misuse Detection - A Statistical Approach | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 101-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 王勝德(Sheng-De Wang),連耀南(Yao-Nan Lien),黃秋煌(Chua-Huang Huang),黃俊穎(Chun-Ying Huang) | |
| dc.subject.keyword | 臉書,盜用帳號,統計方法,Support Vector Machine (SVM),分類,交叉驗證, | zh_TW |
| dc.subject.keyword | Facebook,account misuse,statistical approach,Support Vector Machine (SVM),classification,cross validation, | en |
| dc.relation.page | 58 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2013-06-28 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| Appears in Collections: | 電機工程學系 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-102-1.pdf | 529.46 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.