進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0205201915082900
論文名稱(中文) 社群網路打卡之隱私保護研究
論文名稱(英文) A Study of Check-in Privacy Protection in Social Networks
校院名稱 成功大學
系所名稱(中) 資訊工程學系
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 107
學期 2
出版年 108
研究生(中文) 陳榮祥
研究生(英文) Weng-Siang Tan
學號 P76047049
學位類別 碩士
語文別 英文
論文頁數 32頁
口試委員 指導教授-莊坤達
口試委員-李政德
口試委員-陳朝鈞
中文關鍵字 熟人推測  基於位置的服務  打卡防護 
英文關鍵字 Acquaintance inference  Location-based social networks  check-in shielding 
學科別分類
中文摘要 今日的社群網路發展進步,越來越多用戶使用Foursquare, Instagram, Twitter, Facebook 等社群分享個人生活資訊,並通過網路與他人互動及結交朋友。其中不少用戶熱衷於使用基於位置的社交服務(Location based services LBS),例如:通過打卡方式來和他人分享自己曾到訪過的地方。然而研究表明,傳統的打卡方式未考慮
用戶的社交隱私,歹徒可通過用戶的打卡歷史紀錄準確地推斷出用戶現實生活中的朋友,造成安全隱憂問題。
因此,我們提出一個新的研究方向,針對熟人推測的打卡防護問題(Check-in Shielding against Acquaintance Inference CSAI),目標是為用戶推薦安全的打卡地點來降低其社交隱私暴露的風險。針對CSAI問題,本研究建立了包含兩步驟的打卡防護解決方案(Check-in Shielding Scheme CSS),其一是量化用戶之間的社交强度,其二是為用戶推薦隱私風險低的安全打卡地點。
基於 Gowalla 和Foursquare 資料集進行的實驗結果表明,CSS 在各種實驗狀況下都優越於其他競爭方法,能有效降低社交隱私風險。新推薦的地點不僅能保持和原有打卡地點之距離在合理範圍内,而且不影響打卡資料的其他應用,例如:興趣點推薦(Point of Interest POI)。
英文摘要 The rapid development of social networks such as Foursquare, Instagram, Twitter, Facebook has led to a significant increase in users of location-based services (LBS). These social networks allow users to check-in at the place they have visited and interact with others. However, recent researches show that the traditional check-in mechanism does not consider user’s social privacy problem, adversary can easily infer user’s social relationship with others based on their check-in history data.
So that, we introduce a novel problem in social network privacy protection research, called Check-in Shielding against Acquaintance Inference (CSAI), the goal is to reduce user’s privacy risk by suggesting secure locations for user to perform check-in. To address the CSAI problem, we devise a check-in shielding framework, called Check-in Shielding Scheme (CSS), which consist of two steps: quantify the social strength between users and recommend low privacy risk check-in locations for users.
We conducted experiment with two real-world datasets and the result show that CSS can effectively reduce the users’ acquaintances privacy risk and it is the best shielding method compared to other competitors under various experiment scenarios. In addition, CSS also can preserve the check-in distance of recommended place within reasonable range, such that the usability of check-in data can be preserved.
論文目次 中文摘要 ... i
Abstract ... ii
Contents ... iii
List of Tables ... iv
List of Figures ... v
Chapter 1 Introduction ... 1
Chapter 2 Related Work ... 6
2.1 Privacy Preserving in Social Networks ... 6
2.2 Privacy Preserving in Geo-Social Services ... 7
2.3 Social Strength Inference in Location-Based Services ... 7
Chapter 3 Problem Formulation ... 9
Chapter 4 Methodology ... 12
4.1 Social Strength Quantification ... 12
4.1.1 Personal Factor ... 12
4.1.2 Global Factor ... 13
4.1.3 Temporal Factor ... 14
4.1.4 Diversity Factor ... 15
4.2 Shielding Place List Generation ... 16
Chapter 5 Evaluation ... 19
5.1 Data description ... 19
5.2 Evaluation settings ... 20
5.2.1 Social Density ... 21
5.2.2 Evaluation Metric ... 21
5.3 Experimental Results ... 22
5.3.1 Comparison of different Shielding Methods ... 22
5.3.2 Average Check-in Distance of different Shielding Methods ... 24
5.3.3 Effect on Acquaintance Weight Parameter α in CSS ... 25
5.3.4 Effect on Social Density threshold ... 26
5.3.5 Effect on Users’ Existing Check-ins ... 28
Chapter 6 Conclusion ... 30
Bibliography ... 31
參考文獻 [1] Acs, G., Castelluccia, C.: A case study: privacy preserving release of spatiotemporal density in paris. In: Proceedings of ACM SIGKDD (2014)
[2] Andr´es, M.E., Bordenabe, N.E., Chatzikokolakis, K., Palamidessi, C.: Geo indistinguishability: Differential privacy for location-based systems. In: Proceedings of ACM CCS (2013)
[3] Backes, M., Humbert, M., Pang, J., Zhang, Y.: walk2friends: inferring social links from mobility profiles. In: Proceedings of ACM CCS (2017)
[4] Bordenabe, N.E., Chatzikokolakis, K., Palamidessi, C.: Optimal geoindistinguishable mechanisms for location privacy. In: Proceedings of ACM CCS (2014)
[5] Cheng, R., Pang, J., Zhang, Y.: Inferring friendship from check-in data of locationbased social networks. In: Proceedings of ASONAM (2015)
[6] Cho, E., Myers, S.A., Leskovec, J.: Friendship and mobility: user movement in location-based social networks. In: Proceedings of ACM KDD (2011)
[7] Cranshaw, J., Toch, E., Hong, J.I., Kittur, A., Sadeh, N.M.: Bridging the gap between physical location and online social networks. In: Proceedings of UbiComp (2010)
[8] Dey, R., Jelveh, Z., Ross, K.W.: Facebook users have become much more private: a large-scale study. In: Proceedings of PerCom Workshops (2012)
[9] Fire, M., Goldschmidt, R., Elovici, Y.: Online social networks: threats and solutions. IEEE Communications Surveys and Tutorials (2014)
[10] Grover, A., Leskovec, J.: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, 2016, pp. 855–864 (2016)
[11] Hay, M., Miklau, G., Jensen, D.D., Towsley, D.F., Li, C.: Resisting structural reidentification in anonymized social networks. VLDB J (2010)
[12] Hsieh, H.-P., Yan, R., Li, C.-T.: Where you go reveals who you know: Analyzing social ties from millions of footprints. In: Proceedings of ACM CIKM (2015)
[13] Likhyani, A., Bedathur, S., Deepak, P.: Locate: influence quantification for location promotion in location-based social networks. In: Proceedings of IJCAI (2017)
[14] Liu, K., Terzi, E.: Towards identity anonymization on graphs. In: Proceedings of ACM SIGMOD (2008)
[15] Mir, D.J., Isaacman, S., C´aceres, R., Martonosi, M., Wright, R.N.: Dp-where: Differentially private modeling of human mobility. In: Proceedings of IEEE Big Data (2013)
[16] Njoo, G.S., Kao, M.-C., Hsu, K.-W., Peng,W.-C.: Exploring check-in data to infer social ties in location based social networks. In: Proceedings of PAKDD (2017)
[17] .Noulas, A., Scellato, S., Lathia, N., Mascolo, C.: A random walk around the city New venue recommendation in location-based social networks. In: SocialCom/PASSAT, pp. 144–153 (2012)
[18] Pham, H., Hu, L., Shahabi, C.: Towards integrating real-world spatiotemporal data with social networks. In: Proceedings of ACM SIGSPATIAL (2011)
[19] Pham, H., Shahabi, C., Liu, Y.: EBM: an entropy-based model to infer social strength from spatiotemporal data. In: Proceedings of ACM SIGMOD (2013)
[20] Pisinger, D.: Upper bounds and exact algorithms for p-dispersion problems. Computers & OR (2006)
[21] Puttaswamy, K.P.N., Wang, S., Steinbauer, T., Agrawal, D., El Abbadi, A., Kruegel, C., Zhao, B.Y.: Preserving location privacy in geosocial applications. IEEE Transactions on Mobile Computing (2014)
[22] Sun, C., Philip, S.Y., Kong, X., Fu, Y.: Privacy preserving social network publication against mutual friend attacks. In: Proceedings of ICDM Workshops (2013)
[23] Tai, C.-H., Yu, P.S., Yang, D.-N., Chen, M.-S.: Privacy-preserving social network publication against friendship attacks. In: Proceedings of ACM SIGKDD (2011)
[24] Wang, H., Li, Z., Lee, W.-C.: PGT: measuring mobility relationship using personal, global and temporal factors. In: Proceedings of IEEE ICDM (2014)
[25] Wang, Y., Zheng, B.: Preserving privacy in social networks against connection fingerprint attacks. In: Proceedings of ICDE (2015)
[26] Zhou, B., Pei, J., Luk, W.-S.: A brief survey on anonymization techniques for privacy preserving publishing of social network data. SIGKDD Explorations (2008)
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2023-12-31起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw