為了保護手機上的隱私資料，目前已存在數個識別機制，如：PIN碼、密碼解鎖，及生物特徵方式的識別機制。然而這些識別方法於便利性及安全性上人仍有所不足。非侵入式識別機制由於僅須收集使用者行為即能進行識別，故能彌補上述識別方式之不便利性。目前已存有數個非侵入式識別機制，但並沒有考慮訓練樣本的收集時間過長的問題。而以門檻為停止條件的主動學習方法雖能減少訓練樣本量，卻會造成錯誤率上升。
　　於本研究中，我們提出一個優化後的主動學習方法，使其更為有效地收集訓練資料。支持向量機器被用來分析少量的訓練資料。本研究提出兩項主要的方法，其一為使用優化後的停止條件，藉以減少資料量。其二則為使用改善的模型分析方法決定訓練資料之來源，藉以保持其原有的錯誤率。
　　於實驗後，我們發現本研究所提出方法相比原有主動學習方法有較好的效果。訓練資料收集時間可從17分鐘降至10分鐘，約減少至原所需時間量的41%，並保持相同的錯誤率。

關鍵字:非侵入式識別，使用者識別，主動學習方法，支持向量機器

In order to protect the data in the smartphone, there is some protection mechanism that has been used. The current authentication uses PIN, password, and biometric-based method. These authentication methods are not sufficient due to convenience and security issue. Non-Intrusive authentication is more comfortable because it just collects user’s behavior to authenticate the user to the smartphone. Several non-intrusive authentication mechanisms were proposed but they do not care about the training sample that has a long data collection time. The Threshold-based active learning has proposed the method that cut down the training data but it makes the error rate increase.
In this research, we propose a method to collect data more efficient using Optimized Active Learning. The Support Vector Machine (SVM) used to identify the effect of some small amount of training data. This proposed system has two main functionalities. First, to cut down the training data using optimized stop rule. Second, maintain the Error Rate using modified model analysis to determine the training data that fit for each user.
Finally, after we done the experiment, we conclude that our proposed system is better than Threshold-based Active Learning. The time required to collect the data can cut down to 41% from 17 to 10 minutes with the same Error Rate.

Keywords: non-intrusive authentication, user authentication, active learning, support vector machine

[1] O. Mazhelis, J. Markuula, and J. Veijalainen, “An integrated identity verification system for mobile erminals,” Information Management & Computer Security, vol. 13, no. 5, pp. 367-378, 200.
[2] Smart Credit. “Consumer Reports survey on mobile phones and security.” 2011 Press. available from: http://www.smartcredit.com/blog/2011/09/02/consumer-reports-surveyon-mobile-phones-and-security/ (2011/11/15).
[3] C. Theriault, “Survey says 70% don't password-protect mobiles.” 2011 Press. available from: http://nakedsecurity.sophos.com/2011/08/09/freesophos-mobile-security-toolkit/ (2011/11/11).
[4] N. Clarke, S. Karatzouni, and S. Furnell, “Flexible and transparent user authentication for mobile devices,” IFIP Advances in Information and Communication Technology, 297/2009, 1-12, 2009.
[5] T. Feng, Z. Liu, K.-A. Kwon, W. Shi, B. Carbunary, Y. Jiangz and N. Nguyen, “Continuous Mobile Authentication using Touchscreen Gestures”, To appear in the 12th IEEE Conference on Technologies for Homeland Security (HST), Waltham, MA, November 2012.
[6] C.C. Lin, C.C. Chang, and D. Liang, “A New Non-intrusive Authentication Approach for Data Protection Based on Mouse Dynamics,” International Symposium on Biometrics and Security Technologies, Taipei, Taiwan, March 26-19, pp. 9-14, 2012.
[7] A.A.E. Ahmed, and I. Traore, “A New Biometric Technology Based on Mouse Dynamics,” IEEE Trans. on Dependable and Secure Computing, vol. 4, no. 3, pp. 165-179, 2007.
[8] H. Gamboa, and A. Fred, “A User Authentication Technic Using a Web Interaction Monitoring System”, Lecture Notes in Computer Science (Pattern Recognition and Image Analysis), vol. 2652, pp. 246-254, 2003.
[9]C. C. Lin, C. C. Chang, D. R. Liang, and C. H. Yang, "A Preliminary Study on Non-Intrusive User Authentication Method Using Smartphone Sensors," Applied Mechanics and Materials, vol. 284, pp. 3270-3274, 2013
[10]C.-C. Lin, C.-C. Chang, and D. Liang, "A Novel Non-intrusive User Authentication Method Based on Touchscreen of Smartphones," to appear in Journal of Internet Technology, vol. 16, p. 1-10, 2015.
[11] Gartner Inc. Gartner identifies the top 10 consumer mobile applications for 2012. November 18, 2009 Press Releases. available from: http://www.gartner.com/it/page.jsp? id=1230413 (2011/11/11).
[12] L. Kamp, Mobility Trends that Will Define the Next Decade, Mobile World Congress 2012, Accenture Mobility, available from: http://www.slideshare.net/scapecast/accenture -mobility-mwc-2012-bubble-over-barcelona-lars-kamp (2012/2/29 published).
[13] Martin, A. F. et al., "The DET Curve in Assessment of Detection Task Performance", Proc. Eurospeech '97, Rhodes, Greece, September 1997, Vol. 4, pp. 1899–1903.
[14] Angluin, D., 1988, “Queries and concept learning”, Machine Learning, pp.319-342.
[15] Settles, B., 2009, “Active learning literature survey”, Computer Sciences Technical Report 1648, University of Wisconsin-Madison.
[16] Cortes, C., Vapnik, V. (1995). "Support-vector networks". Machine Learning 20 (3): 273–297.
[17] M. Pusara and C. E. Brodley, "User re-authentication via mouse movements," in Proceedings of the 2004 ACM workshop on Visualization and data mining for computer security, 2004, pp. 1-8.
[18] Dekel, Ofer. “From Online to Batch Learning with Cutoff-Averaging”. One Microsoft Way .Microsoft Research
[19] Wikispaces : Batch, Online & real time Processing. November 3, 2010, Taken from : http://dis-dpcs.wikispaces.com/3.3.5+Batch,+Online+%26+real+time+Processing
[20] Walker, Michael : Batch vs. Real Time Data Processing. August 13, 2013, Taken from : http://www.datasciencecentral.com/profiles/blogs/batch-vs-real-time-data-processing
[21] Lewis, D., Catlett., 994, “Heterogeneous uncertainty sampling for supervised learning”, Machine Learning: Proceedings of the Eleventh International Conference, Morgan Kaufmann Publishers, San Francisco, CA, pp. 148–156.
[22] Tong S, Koller D. Support vector machine active learning with applications to text classification [C] //Proc of ICMI 2000. San Francisco: Morgan Kaufmann, 2000: 999-1066.
[23] Seung, H. S., Opper, M., Sompolinsky, H., 1992, “Query by committee”, COLT '92 Proceedings of the fifth annual workshop on Computational learning, pp.287-294.