隨著智慧型手機與平板電腦的普及，越來越多人使用智慧型行動裝置。而行動裝置作業系統(如: Android) 為了顧及使用者的安全性，增設了自動鎖定機制，在手機休眠後會自動鎖定螢幕，必須輸入圖形鎖、PIN碼或密碼才能解鎖。而作業系統開發商為了兼顧安全性與便利性，另外增加了自動鎖定倒數設定，使用者可以決定在行動裝置休眠後要等待多久後才把螢幕上鎖。但此自動鎖定倒數時間在系統中通常只有幾種固定選項來讓使用者作選擇，使用者不易挑出最符合自身使用習慣的倒數時間。
因此，本篇論文開發了一套為行動裝置設計之智慧型自動鎖定機制，能根據使用者的過去習慣 (如：過去常去的地點、不同時間的手機使用頻率) 來動態調整自動鎖定倒數時間，能針對不同的使用者提供客製化的自動鎖定機制，並同時在安全性與便利性中找出最佳的平衡點。

As the popularity of smart phone and tablet, there are more and more people have their own mobile devices. To increase the security of the phone, some of operating systems (e.g. Android) add auto-lock mechanism. The mechanism will lock the screen after the device sleep. In order to balance the security and convenience, they also develop counting time of auto-lock. After the device sleep, if the device does not wake up in counting time, the screen will lock. But the auto-lock time only has few options to let the user choose. User may not know which one is the best choice for him.
In the paper, we present Intelligent Auto-lock Scheme for mobile devices. It can change the auto-lock time based on the user behavior dynamically (e.g. the place where user often to go, the frequency of using the device in different time period), and trade off security and convenience. For different user, the scheme can provide different auto-lock time strategy for each device.

中文摘要I
ABSTRACTII
誌謝III
List of FiguresV
List of TablesVI
Chapter 1Introduction1
Chapter 2Related Work6
2.1Related mechanisms used in implicit authentication6
2.1.1Related mechanisms used in location based implicit authentication6
2.1.2Related mechanisms used in screen status based implicit authentication9
2.1.3Related mechanisms used in multiple factor based implicit authentication10
2.2Term Frequency–Inverse Document Frequency (TF-IDF) scheme12
2.3Vector Space Model (VSM)13
Chapter 3Intelligent Auto-lock Scheme16
3.1Overview16
3.2User Behavior Measurement17
3.3User Behavior Model19
3.4Auto-lock Time Algorithm24
Chapter 4Performance Analysis26
4.1Experiment Environment26
4.2Experiment Process26
4.3Experiment Evaluation28
Chapter 5Conclusion30
References31
Appendix A Database Schema33

[1]Google. Our Mobile Planet. Available from: http://think.withgoogle.com/mobileplanet/zh-tw/downloads/.
[2]Ildar Muslukhov, Survey: Data Protection in Smartphones Against Physical Threats. Term Project Papers on Mobile Security. University of British Columbia, 2012.
[3]Privacy and Data Management on Mobile Devices. Available from: http://www.pewinternet.org/2012/09/05/privacy-and-data-management-on-mobile-devices/.
[4]Elaine Shi, Yuan Niu, Markus Jakobsson, and Richard Chow, Implicit authentication through learning user behavior, in Information Security. 2011, Springer. p. 99-113.
[5]Eiji Hayashi, Sauvik Das, Shahriyar Amini, Jason Hong, and Ian Oakley. Casa: context-aware scalable authentication. in Proceedings of the Ninth Symposium on Usable Privacy and Security. 2013. ACM.
[6]Yusuf Albayram, Sotirios Kentros, Ruhua Jiang, and Athanasios Bamis, A Method for Improving Mobile Authentication Using Human Spatio-Temporal Behavior.
[7]Alexander De Luca, Alina Hang, Frederik Brudy, Christian Lindner, and Heinrich Hussmann, Implicit Authentication Based on Touch Screen Patterns. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2012, pp.987-996.
[8]Yonggon Kim, Ohmin Kwon, Sunwoo Kim, Byungjin Jeong, and Hyunsoo Yoon, Protecting Mobile Devices from Adversarial User by Fine-Grained Analysis of User Behavior, in Advanced in Computer Science and its Applications. 2014, Springer. p. 445-451.
[9]Richard Chow, Markus Jakobsson, Ryusuke Masuoka, Jesus Molina, Yuan Niu, Elaine Shi, and Zhexuan Song, Authentication in the clouds: a framework and its application to mobile users, in Proceedings of the 2010 ACM workshop on Cloud computing security workshop2010, ACM: Chicago, Illinois, USA. p. 1-6.
[10]Markus Jakobsson, Elaine Shi, Philippe Golle, and Richard Chow. Implicit authentication for mobile devices. in Proceedings of the 4th USENIX conference on Hot topics in security. 2009. USENIX Association.
[11]Jiang Zhu, Pang Wu, Xiao Wang, and Joy Zhang. SenSec: Mobile security through passive sensing. IEEE International Conference on Computing, Networking and Communications (ICNC), 2013, pp.1125-1133.
[12]Karen Sparck Jones, A statistical interpretation of term specificity and its application in retrieval. Journal of documentation, 1972. 28(1): p. 11-21.
[13]Gerard Salton, Anita Wong, and Chung-Shu Yang, A vector space model for automatic indexing. Communications of the ACM, 1975. 18(11): p. 613-620.