跳到主要內容

簡易檢索 / 詳目顯示

研究生: 林宗杰
lin tsung-chieh
論文名稱: 基於方位感測器與觸控螢幕之智慧型手機非侵入式多模組識別機制
指導教授: 梁德容
Deron-Liang
口試委員:
學位類別: 碩士
Master
系所名稱: 資訊電機學院 - 軟體工程研究所
Graduate Institute of Software Engineering
論文出版年: 2012
畢業學年度: 101
語文別: 中文
論文頁數: 38
中文關鍵詞: 身份識別方位感測器觸控螢幕非侵入式
外文關鍵詞: Authentication, orientation sensor, touch screen, Non-intrusive
相關次數: 點閱:11下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 近年來隨著手機的普遍性與手機科技的進步,越來越多的人使用智慧型手機,並利用智慧型手機上有關個人隱私亦或是身分認證等功能,若手機遭盜用後損失難以估計。上述許多功能需要使用者對智慧型手機進行較長時間的操作以存取資料,而目前市面上此類的應用程式僅透過密碼驗證方式進行識別,若使用過程中需要一直登入驗證使用者,則使用者很有可能為了方便而關閉此種驗證方式,或是直接將密碼記憶於手機中,導致登入驗證形同虛設。故本論文主要以利用智慧型手機上內建之方位感測器(orientation sensor)與觸控螢幕(touch screen)達到非侵入式(Non-intrusive)識別使用者行為習慣,以提高智慧型手機的安全等級。根據實驗結果顯示識別機制的相等錯誤率(Equal Error Rate)達到7%,證實此機制確實能夠區分不同使用者。


    In recent years, with the widely used of the smartphone and advances in smartphone technology, more and more people use smartphones, and use the services on the smartphones, such as personal privacy information services and ID identification services. If the smartphone has been stolen or someone illegally uses your smartphone, it will make you suffer heavy losses. Most of the above mentioned functionalities are needed user to operate for a long time on smartphone so as to access data. However, currently, most of the applications are just only using the password authentication. If during using the smartphone, will often needing to authenticate user, will make user turn off the authentication mechanism, or save the password in the smartphone, makes the authentication mechanism useless. So the purpose of this paper use the smartphone’s embedded sensor, orientation sensor and touch screen, to achieve the non-intrusive user authentication, and enhance smartphone security level. The experiment results show that the proposed approach has an Equal-Error-Rate (EER) about 7%. Therefore, the multimodal authentication mechanism can distinguish users’ differences.

    中文摘要 1 Abstract 2 誌謝 3 一、 緒論 1 1-1.前言 1 1-2.研究動機 3 1-3.研究目的 6 1-4.論文架構 6 二、 文獻探討 7 2-1.驗證方法探討 7 2-2.觸控螢幕(Touch Screen) 7 2-3.方位感測器(Orientation Sensor) 8 2-4.使用多Sensors在不同情境下識別使用者 9 2-5.使用方位感測器於接聽電話情境下識別使用者 10 三、 系統架構 11 3-1.特徵萃取 11 3-2.資料前處理 12 3-3.抽樣 13 3-4.相似度量測演算法(KL-Divergence) 14 3-5.權重計算 16 3-6.驗證模型 16 四、 實驗 18 4-1資料收集 18 4-1-1資料收集環境 18 4-1-2資料收集情境 19 4-2建模抽樣實驗結果與分析 20 4-3單一Orientation Sensor與單一Touch screen個別實驗結果與分析: 21 4-4結合Orientation Sensor與Touch screen之multi-modalities model實驗結果與分析: 25 4-5 Histogram驗證時間 29 4-6討論:相對夾角與絕對夾角 29 五、 研究討論與未來展望 34 5-1結論 34 5-2未來展望 34 六、 參考文獻 36 七、 附錄一 特徵計算公式 37

    [1]Gartner Inc. (2012). Mobility Trends that Will Define the Next Decade. Available: http://www.businessinsider.com/android-9-charts-that-show-its-amazing-growth-2012-3#first-a-general-comparison-of-growth-rates-the-worlds-population-has-grown-6-in-the-last-five-years-the-number-of-mobile-internet-users-has-gone-up-more-than-4x-1
    [2] Androidauthority. Global smartphone unit sales forecast. Available: http://www.androidauthority.com/smartphone-sales-statistics-vs-pc-58687/worldwide-smartphone-unit-sales-forecast/
    [3] Gartner Inc. (2011). Gartner Identifies 10 Consumer Mobile Applications to Watch in 2012. Available: http://www.gartner.com/it/page.jsp?id=1544815
    [4] Nakedsecurity. (2011). Survey says 70% don't password-protect mobiles. Available: http://nakedsecurity.sophos.com/2011/08/09/free-sophos-mobile-security-toolkit/
    [5] J. Yan, et al., "Password memorability and security: Empirical results," Security & Privacy, IEEE, vol. 2, pp. 25-31, 2004.
    [6] D. Weinshall and S. Kirkpatrick, "Passwords you'll never forget, but can't recall," presented at the CHI '04 extended abstracts on Human factors in computing systems, Vienna, Austria, 2004.
    [7] N. Clarke, et al., "Flexible and transparent user authentication for mobile devices," Emerging Challenges for Security, Privacy and Trust, pp. 1-12, 2009.
    [8] Google-Android. TouchScreen. Available: http://developer.android.com/guide/topics/ui/ui-events.html.
    [9] Google-Android. Orientation sensor. Available: http://developer.android.com/guide/topics/sensors/sensors_position.html.
    [10] S. Weidong, et al., "SenGuard: Passive user identification on smartphones using multiple sensors," in Wireless and Mobile Computing, Networking and Communications (WiMob), 2011 IEEE 7th International Conference on, 2011, pp. 141-148.
    [11] M. Conti, et al., "Mind how you answer me!: transparently authenticating the user of a smartphone when answering or placing a call," presented at the Proceedings of the 6th ACM Symposium on Information, Computer and Communications Security, Hong Kong, China, 2011.

    QR CODE
    :::