(3.238.173.209) 您好!臺灣時間:2021/05/12 14:20
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:黎亞妮
研究生(外文):Amalia Kartika Ariyani
論文名稱:具池化策略 Simplified Linear Discriminant Analysis 使用於連續智慧型手機用戶認證中應付操作行為改變
論文名稱(外文):Simplified LDA with Pooling Strategy to Handle User Behavior Change on Continuous Smartphone Authentication
指導教授:梁德容梁德容引用關係
指導教授(外文):Deron Liang
學位類別:碩士
校院名稱:國立中央大學
系所名稱:資訊工程學系在職專班
學門:工程學門
學類:電資工程學類
論文出版年:2020
畢業學年度:108
語文別:英文
論文頁數:55
中文關鍵詞:兩步驟連續智慧型手機認證操作行為改變線性判別分析池化策略
外文關鍵詞:two-step continuous smartphone authenticationbehavior changelinear discriminant analysispooling strategy
相關次數:
  • 被引用被引用:0
  • 點閱點閱:36
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
智慧型手機已成為使用者日常執行各種活動的智慧行動裝置,而智慧型手機也逐漸需要受到保護以防個人資料遭到非法存取。過去提出使用兩階段認證:傳統認證與行為認證來加強安全性,然而在行為認證方面,使用者於不同的使用情境時常有不同的操作行為,隨著時間推移,資料逐漸變得不可靠,且因模型無法應對使用行為改變而使合法使用者進行認證時失敗。因此,使用者行為模型必須隨時重新訓練以解決這個問題。
重新訓練模型之方法會使用所有過去模型的資料來訓練新的模型,但這會造成程序耗竭且佔用大量資源。因此,我們提出一種輕量且快速的分類器:具有池化策略的簡化線性判別分析,在快速的訓練時間且不犧牲等錯誤率的狀況下來解決使用者行為改變的問題。在這份研究中,我們比較四種方法來評估我們所提出的模型,分別是M0-B SVM當作最佳基準模型、無重新訓練的M0-W1 LDA與M0-W2 SVM當作最差基準模型、以及具有池化策略的M1-Simplified LDA為我們提出的模型。實驗結果顯示我們提出的模型M1的等錯誤率為0.085,比經6次迭代的M0-W1的0.146及M0-W2的0.104還要好,而M0-B的等錯誤率為0.043。 不過M1僅有0.044秒的訓練時間及,0.029秒的測試時間,快於其他三種發法。M0-W1的訓練時間為0.344秒,M0-B的訓練時間為0.614秒,而M0-W2的測試時間為0.074秒。
Smartphones are one of the smart devices that become a daily driver for users to perform various activities that has to be secured on their smartphone to protect these personal data from unauthorized access. Two-step authentication using traditional and behavioral authentication was proposed to strengthen the security. However, in behavioral authentication, users tend to use their smartphone on different posture on different activities, it will make user data unstable and change over time and will cause the authentication process failed to predict as a legitimate user because the previous authentication model cannot handle user behavior change. Thus, the user model has to be retrained over time to handle the problem.
Retraining approach keeps all previous data to retrain the new model, it will cause the exhausting process and will take a large number of resources. Hence, we proposed a lightweight and fast classifier using Simplified LDA with pooling strategy to handle user behavior change with faster training time without sacrificing the Equal Error Rate (EER). In this research, we compared four approaches to evaluate the proposed model, M0-B SVM as the best baseline model, M0-W1 LDA and M0-W2 SVM non-Retraining as the worst baseline model, and M1-Simplified LDA with pooling strategy as our proposed model. The experiment result shows that the proposed model M1 has EER 0.085, better than M0-W1 which only got EER 0.146 and M0-W2 got 0.104 in the 6th iteration and approached M0-B EER 0.043. M1 also only need 0.044 seconds on training time and 0.029 seconds on testing time, faster than M0-W1 0.344 seconds and M0-B 0.614 seconds training time and M0-W2 0.074 seconds on testing time.
中文摘要 i
ABSTRACT ii
ACKNOWLEDGMENT iii
TABLE OF CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES viii
CHAPTER 1 INTRODUCTION 1
1.1. Background 1
1.2. Motivation 3
1.3. Research Objectives 5
1.4. Limitation of Study 6
1.5. Thesis Structure 6
CHAPTER 2 LITERATURE REVIEW 7
2.1. Mobile Authentication 7
2.2. Handling User Behavior Change on Mobile Devices 7
2.3. Linear Discriminant Analysis Classifier 8
2.4. K-Means Clustering 9
2.5. Performance Matrices 10
CHAPTER 3 METHODOLOGY 11
3.1. System Architecture 11
3.2. Data Collection 13
3.3. Data Preprocessing 14
3.2.1. Feature Extraction 15
3.2.2. Feature Transformation 18
3.4. Pooling Strategy 20
3.5. Simplified Linear Discriminant Analysis 21
3.5.1. Training Phase 23
3.5.2. Testing Phase 24
CHAPTER 4 EXPERIMENTAL PROCESS AND RESULT ANALYSIS 26
4.1. Experiment Setup 26
4.2. Experiment Result 29
4.2.1. Equal Error Rate Comparison 29
4.2.2. Training Time and Testing Time Comparison 30
4.3. Discussion 31
4.3.1. Simplified LDA Evaluation 31
4.3.2. Pooling Strategy Evaluation 34
4.3.3. Classifier Performance Comparison 35
CHAPTER 5 CONCLUSION 38
5.1. Conclusion 38
5.2. Future Works 39
BIBLIOGRAPHY 40
[1] S. O'Dea, 28 February 2020. [Online]. Available: https://www.statista.com/statistics/330695/number-of-smartphone-users-worldwide/.
[2] A. A. Alariki, A. B. A. Manaf and S. Khan, "A study of touching behavior for authentication in touch screen smart devices," 2016 International Conference on Intelligent Systems Engineering (ICISE), pp. 216-221, 2016.
[3] B. Chakraborty, K. Nakano, Y. Tokoi and T. Hashimoto, "An Approach for Designing Low Cost Deep Neural Network based Biometric Authentication Model for Smartphone User," TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), pp. 772-777, 2019.
[4] B. Zou and Y. Li, "Touch-based Smartphone Authentication Using Import Vector Domain Description," IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP), pp. 1-4, 2018.
[5] C.-C. Lin, C.-C. Chang and D. Liang, "A Novel Non-intrusive User Authentication Method Based on Touchscreen of Smartphones," 2013 International Symposium on Biometrics and Security Technologies, pp. 212-216, 2013.
[6] T. V. Bandos, L. Bruzzone and G. Camps-Valls, "Classification of Hyperspectral Images With Regularized Linear Discriminant Analysis," IEEE Transactions on Geoscience and Remote Sensing, vol. 47, no. 3, pp. 862-873, 2009.
[7] J. Gama, I. Zliobaite, A. Bifet, M. Pechenizkiy and A. Bouchachia, "A Survey on Concept Drift Adaptation," ACM Computing Surveys, vol. 46, pp. 44:1-44:37, 2014.
[8] S. Nick and K. YongSeog, "A Streaming Ensemble Algorithm (SEA) for Large-Scale Classification," in Proceedings of the seventh ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 2001.
[9] G. Zeira, O. Maimon, M. Last and L. Rokach, "Change detection in classification models induced from time series data," in Data Mining in Time Series Databases, Singapore, World Scientific Publishing Company Incorporated, 2004, pp. 101-125.
[10] R. Klinkenberg, "Predicting Phases in Business Cycles Under Concept Drift," in Machine Learning of the National German Computer Science Society (LLWA), Germany, 2003.
[11] G. Hulten, L. Spencer and P. Domingos, "Mining Time-Changing Data Streams," Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 97-106, 2001.
[12] H. K. Ekenel and R. Stiefelhagen, "Two-class Linear Discriminant Analysis for Face Recognition," 2007 IEEE 15th Signal Processing and Communications Applications, pp. 1-4, 2007.
[13] J. Feng, Y. Zhang, G. Yue, X. Liu, H. Su and P.-F. Zhang, "Atherosclerotic Plaque Pathological Analysis by Unsupervised K-Means Clustering," IEEE Access, vol. 6, pp. 21530-21535, 2018.
[14] S. Wang, M. Li, N. Hu, E. Zhu, J. Hu, X. Liu and J. Yin, "K-Means Clustering With Incomplete Data," IEEE Access, vol. 7, pp. 69162-69171, 2019.
[15] A. K. Jain and R. C. Dubes, Algorithm for Clustering Data, New Jersey: Prentice-Hall, Inc., 1998.
[16] E. Conrad, S. Misenar and J. Feldman, "Identity and access management (controlling access and managing identity)," in Eleventh Hour CISSP (Third Edition), 2017, pp. 117-134.
[17] P. Schober, C. Boer and L. A. Schwarte, "Correlation Coefficients: Appropriate Use and Interpretation," Anesthesia & Analgesia, vol. 126, no. 5, pp. 1763-1768, 2018.
電子全文 電子全文(網際網路公開日期:20230801)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔