基于计算机击键动力学的用户身份鉴别
|
摘要
为了维护计算机系统的安全，一般通过设置用户口令以便进行身份鉴别，防止他人冒名顶替。口令鉴别的主要弱点在于，一旦被窃，冒名顶管者就可以轻而易举地进入用户的私人账户进行非法活动。击键动力学的研究初衷正是要给口令加上一个简便而有效的保护措施。击键动力学方法通过获取并分析用户敲击键盘的特征数据，自动地识别出用户的真实身份。这一辅助身份鉴别的关键问题主要是寻找准确率高、执行速度快的识别算法。国内外现有相关算法研究热点主要集中在统计学、神经网络、模糊数学等领域，但通常存在准确率与执行速度不能兼顾、新模仿者无法检测等问题。本论文针对这些问题进行了深入研究，并完成了一个计算机击键动力学身份鉴别系统。
本文首先介绍了基于击键特征的身份鉴别系统的设计，该系统包括数据采集、数据预处理与分析、用户管理等多个层次。在总体设计基础上，作者首先开展了数据采集研究与实验，然后采用Levenberg-Marquardt(LM)算法进行身份鉴别研究。论文通过MATLAB仿真实现了整个算法鉴别过程，并将鉴别结果及执行速度分别与前人所用算法进行了比较。为了能够有效地解决新模仿者检测的问题，本文又提出在训练数据集中加入等差均值序列噪声的思路，采用具有较强推广能力的支持向量机进行识别，并将识别结果与LM算法进行了对比。最后，论文对基于鼠标轨迹的身份鉴别方法进行了初步探讨，在建立动态模型、系统设计、数据采集与分析等方面做了一些初步工作。
In order to protect computer system, password is the most widely used method to control the access of computer system by authenticating the users' identity. However, the policy of password is vulnerable to impostor attacks due to its simplicity. Therefore, the original intention of keystroke dynamics is to provide a convenient and effective protection on password verification. In keystroke dynamics, the characteristics of a user' keystrokes is captured when password is being typed, and is analyzed by algorithms to automatically recognize the authentic identity. What is critical for such an auxiliary identity authentication is to find a recognition algorithm with high accuracy and high speed. Up to now the known recognition algorithms mainly come from the fields of statistics, neural networks, fuzzy logic, etc, but improvements are required because satisfactory accuracy and speed cannot be achieved simultaneously, and most of them are not suitable in detecting novel impostors. In this thesis, these problems a
re explored in depth, and an identity authentication system based on computer keystroke dynamics is designed and implemented.
The thesis firstly presents the overall identity authentication system design, including the levels of data acquisition, data preprocessing, data analysis, and user management. Based on the overall system design, the research and experiment of data acquisition are conducted. Then, Levenberg-Marquardt algorithm is adopted for data analysis. The entire procedures of authentication are simulated in MATLAB and the results are compared with those of previous research both in accuracy and speed. As for the problem of novel impostor detection, the idea of adding equi-distant mean noise sequences into training set is presented. Based on support vector machine, a generalized algorithm is adopted for password verification, together with a comparison between SVM and LM. Finally, some initial works of identity authentication based on mouse trajectories are explored, including the construction of dynamic model, system architecture, data acquisition and analysis, etc.
本文首先介绍了基于击键特征的身份鉴别系统的设计，该系统包括数据采集、数据预处理与分析、用户管理等多个层次。在总体设计基础上，作者首先开展了数据采集研究与实验，然后采用Levenberg-Marquardt(LM)算法进行身份鉴别研究。论文通过MATLAB仿真实现了整个算法鉴别过程，并将鉴别结果及执行速度分别与前人所用算法进行了比较。为了能够有效地解决新模仿者检测的问题，本文又提出在训练数据集中加入等差均值序列噪声的思路，采用具有较强推广能力的支持向量机进行识别，并将识别结果与LM算法进行了对比。最后，论文对基于鼠标轨迹的身份鉴别方法进行了初步探讨，在建立动态模型、系统设计、数据采集与分析等方面做了一些初步工作。
In order to protect computer system, password is the most widely used method to control the access of computer system by authenticating the users' identity. However, the policy of password is vulnerable to impostor attacks due to its simplicity. Therefore, the original intention of keystroke dynamics is to provide a convenient and effective protection on password verification. In keystroke dynamics, the characteristics of a user' keystrokes is captured when password is being typed, and is analyzed by algorithms to automatically recognize the authentic identity. What is critical for such an auxiliary identity authentication is to find a recognition algorithm with high accuracy and high speed. Up to now the known recognition algorithms mainly come from the fields of statistics, neural networks, fuzzy logic, etc, but improvements are required because satisfactory accuracy and speed cannot be achieved simultaneously, and most of them are not suitable in detecting novel impostors. In this thesis, these problems a
re explored in depth, and an identity authentication system based on computer keystroke dynamics is designed and implemented.
The thesis firstly presents the overall identity authentication system design, including the levels of data acquisition, data preprocessing, data analysis, and user management. Based on the overall system design, the research and experiment of data acquisition are conducted. Then, Levenberg-Marquardt algorithm is adopted for data analysis. The entire procedures of authentication are simulated in MATLAB and the results are compared with those of previous research both in accuracy and speed. As for the problem of novel impostor detection, the idea of adding equi-distant mean noise sequences into training set is presented. Based on support vector machine, a generalized algorithm is adopted for password verification, together with a comparison between SVM and LM. Finally, some initial works of identity authentication based on mouse trajectories are explored, including the construction of dynamic model, system architecture, data acquisition and analysis, etc.
引文
[1] B. Miller. Vital Signs of Identity (Biometrics). IEEE Spectrum, 1994, Vol.31 (2): 22-30.
[2] F. Monrose, A. Rubin. Authentication via Keystroke Dynamics. Proceedings of the Fourth ACM Conference on Computer and Communications Security, 1997, 4: 48-56.
[3] F. Monrose, A. Rubin. Keystroke Dynamics as a Biometric for Authentication. Future Generation Computer Systems, 2000, Vol. 16(4): 351-359.
[4] C. S. Zhang, Y. H. Sun. AR Model for Keystroke Verification, IEEE International Conference on Systems, Man, and Cybernetics, 2000, Vol.4: 2887-2890.
[5] S. Haider, A. Abbas, A.K. Zaidi. A Multi-Technique Approach for User Identification through Keystroke Dynamics. IEEE International Conference on Systems, Man, and Cybernetics, 2000, Vol.2: 1336-1341.
[6] M. S. Obaidat, D. T. Macchairolo. A multilayer Neural Network System for Computer Access Security. IEEE Transactions on Systems, Man and Cybernetics, 1994, Vol.24(5): 806-813.
[7] M. S. Obaidat, B. Sadoun. Keystroke Dynamics based Authentication, Biometrics Personal Identification in Networked Society, Kluwer Academic Publishers, 1998:213-225.
[8] D. T. Lin. Computer-access Authentication with Neural Network based Keystroke Identity Verification. International Conference on Neural Networks, 1997, Vol.1: 174-178.
[9] http://www.biopassword.com
[10] C.C. Chang, C.J. Lin. LIBSVM : a Library for Support Vector Machines. 2001.
[11] http://www.csie.ntu.edu.tw/～cjlin/libsvm
[12] S. Haykin. Neural Networks: A Comprehensive Foundation (2nd Edition). Beijing: Tsinghua University Press, Prentice Hall, 2001.
[13] V．N．Vapnik著，张学工译．统计学习理论的本质．清华大学出版社，2000年9月．
[14] http://www.eleceng.ohio-state.edu/～maj/osu_svm/
[15] M. E. Whitman, H. J. Mattord. Principle of Information Security(影印版)．清华大学出版社．2003年7月．
[16] E. Yu, S. Cho, Ga-SVM Wrapper Approach for Feature Subset Selection in Keystroke Dynamics Identity Verification. Proceedings of the International Joint Conference on Neural Networks, 2003, Vol.3: 2253-2257.
[17] E. Yu, S. Cho, Novelty Detection Approach for Keystroke Dynamics Identity Verification. Fourth International Conference on Intelligent Data Engineering and Automated Learning, 2003: 1016-1023.
[18] S. Cho, C. Han, D. Han, H. Kim. Web-based Keystroke Dynamics Identity Verification Using Neural Network. Journal of Organizational Computing and Electronic Commerce, 2000, 4: 295-307.
[19] 刘学军，陈松灿，彭宏京．基于支持向量机的计算机键盘用户身份验真．计算机研究与发展，2002年第9期，第39卷：1082-1086．
[20] 朱明，周津，王继康．基于击键特征的用户身份认证新方法．计算机工程．2002年第10期，第28卷：138-140．
[21] L. K, Maisuria, C. S. Ong, W. K. Lai. A Comparison of Artificial Neural Networks and Cluster Analysis for Typing Biometrics Authentication. International Joint Conference on Neural Networks, 1999, Vol.5: 3295-3299.
[22] S. Bleha, D. Gillespie. Computer User Identification Using the Mean and the Median as features. IEEE International Conference on Systems, Man, and Cybernetics, 1998, Vol.5: 4379-4381.
[23] M. S. Obaidat, B. Sadoun. Verification of Computer Users Using Keystroke Dynamics. IEEE Transactions on Systems, Man and Cybernetics, 1997, Vol.27(2): 261-269.
[24] M. S. Obaidat. A Comparative Performance Study of Neural Network Paradigms for Identifying Computer Users. IEEE 13th Annual International Phoenix Conference on Computers and Communications, 1994, 4:161.
[25] M. S. Obaidat, D. T. Macchiarolo. An On-Line Neural Network System for Computer Access Security. IEEE Transactions on Industrial Electronics, 1993, Vol.40(2): 235-242.
[26] S. A. Bleha, J. Knopp, M.S. Obaidat. Performance of the Perceptron Algorithm for the Classification of Computer Users. Proceedings of the 1992 ACM/SIGAPP Symposium on Applied Computing: 863-866.
[27] S. Bleha, C. Slivinsky, B. Hussien. Computer-Access Security Systems Using Keystroke Dynamics. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, Vol.12(12): 1217-1222.
[28] S. A. Bleha, M. S. Obaidat. Dimensionality Reduction and Feature Extraction Application in Identifying Computer Users. IEEE Transactions on Systems, Man and Cybernetics, 1991, Vol. 21(2): 452-456.
[29] S. A. Bleha, M. S. Obaidat. Computer Users Verification Using the Perceptron Algorithm. IEEE Transactions on Systems, Man and Cybernetics, 1993, Vol. 23(3): 900-902.
[30] J. A. Robinson, V. M. Liang, J. A. M. Chambers, C.L. Mackenzie. Computer User Verification Using Login String Keystroke Dynamics. IEEE Transactions on Systems, Man and Cybernetics, 1998, Vol.28(2): 236-241.
[31] T. Ord, S, M. Furnell. User Authentication for Keypad-based Devices Using Keystroke Analysis. Proceedings of the Second International Network Conference, 2000: 263-272,
[32] 司捷，周贵安，李函，韩英铎．基于梯度监督学习的理论与应用(Ⅰ、Ⅱ)．清华大学学报(自然科学版)，1997年，第37卷第7期：71-73．第37卷第9期：104-107．
[33] 曾黄麟．粗集理论及其应用(一、二、三、四)．四川轻化工学院学报，1996年，第9卷第1期：18-28，第2期：1-7，第3期：34-41，第4期：20-26．
[34] 张学工．关于统计学习理论与支持向量机．自动化学报．2000年1月，第26卷第1期：32-42．
[35] R. Plamondon, S.N. Srihari. On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, Vol.22(1): 63-84.
[36] 朱勇，谭铁牛，王蕴红．基于笔迹的身份识别．自动化学报．2001年3月，第27卷第2期：229-234．
[37] 梁艳春，王在中．人工神经网络BP算法密集型数据的预处理．吉林大学自然科学学报，1995年8月，第3期：19-22．
[38] 赵弘，周瑞祥，林廷沂．基于Levenberg-Marquardt算法的神经网络监督控制．西安交通大学学报，2002年5月，第36卷第5期：523-527．
[39] 袁玲．交通噪声预测的神经网络模型．长安大学学报(自然科学版)，2003年3月，第23卷第2期：84-87．
[40] 张栋，蔡开元．基于遗传算法的神经网络两阶段学习方案．系统仿真学报，2003年8月，第15卷第8期：1088-1090．
[41] 郑宏，陆阳，徐朝农．基于BP神经网络的入侵检测系统分类器的实现．合肥工业大学学报(自然科学版)，2003年4月，第26卷第2期：281-285．
[42] N. Ampazis, S. J. Perantonis. Levenberg-Marquardt Algorithm with Adaptive Momentum for the Efficient Training of Feedforward Networks. Proceedings of the IEEE international Joint Conference on Neural Networks, 2000. Vol. 1: 126-131.
[43] D Dasgupta, S. Forrest. Novelty Detection in Time Series Data Using Ideas from Immunology. 5th International Conference on Intelligent Systems, 1996: 1-6.
[44] S. Mukkamala, G. Janoski, A. Sung. Intrusion Detection using Neural Networks and Support Vector Machines. Proceedings of the International Joint Conference on Neural Networks, 2002, Vol.2: 1702-1707.
[45] V. N. Vapnik. An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks, 1999, Vol. 10(5): 988-999.
[46] Z. Wu, D. Li. Neural Network based on Rough Sets and its Application to Remote Sensing Image Classification. Geo-spatial Information Science(Quarterly), 2002, Vol.5(2): 17-21.
[47] 何立民，万跃华．基于隐马尔可夫链和支持向量机人脸识别混合模型的视频节目聚类标注．上海交通大学学报，2003年9月，第37卷增刊：176-183．
[48] 苏毅，吴文虎，郑方，方棣棠．基于支持向量机的语音识别．第六届全国人机语音通讯学术会议，2001年11月：223-226．
[49] 石剑琛，汪厚洋．存取控制技术研究．计算机与数字工程，2003年第4期，第31卷：58-60．
[50] 冯登国．关于发展我国信息安全的几点建议．中国科学院院刊，2002年第4期：289-291．
[51] J．Richter著，王建华等泽．Windows核心编程．机械工业出版社，2000年5月．
[2] F. Monrose, A. Rubin. Authentication via Keystroke Dynamics. Proceedings of the Fourth ACM Conference on Computer and Communications Security, 1997, 4: 48-56.
[3] F. Monrose, A. Rubin. Keystroke Dynamics as a Biometric for Authentication. Future Generation Computer Systems, 2000, Vol. 16(4): 351-359.
[4] C. S. Zhang, Y. H. Sun. AR Model for Keystroke Verification, IEEE International Conference on Systems, Man, and Cybernetics, 2000, Vol.4: 2887-2890.
[5] S. Haider, A. Abbas, A.K. Zaidi. A Multi-Technique Approach for User Identification through Keystroke Dynamics. IEEE International Conference on Systems, Man, and Cybernetics, 2000, Vol.2: 1336-1341.
[6] M. S. Obaidat, D. T. Macchairolo. A multilayer Neural Network System for Computer Access Security. IEEE Transactions on Systems, Man and Cybernetics, 1994, Vol.24(5): 806-813.
[7] M. S. Obaidat, B. Sadoun. Keystroke Dynamics based Authentication, Biometrics Personal Identification in Networked Society, Kluwer Academic Publishers, 1998:213-225.
[8] D. T. Lin. Computer-access Authentication with Neural Network based Keystroke Identity Verification. International Conference on Neural Networks, 1997, Vol.1: 174-178.
[9] http://www.biopassword.com
[10] C.C. Chang, C.J. Lin. LIBSVM : a Library for Support Vector Machines. 2001.
[11] http://www.csie.ntu.edu.tw/～cjlin/libsvm
[12] S. Haykin. Neural Networks: A Comprehensive Foundation (2nd Edition). Beijing: Tsinghua University Press, Prentice Hall, 2001.
[13] V．N．Vapnik著，张学工译．统计学习理论的本质．清华大学出版社，2000年9月．
[14] http://www.eleceng.ohio-state.edu/～maj/osu_svm/
[15] M. E. Whitman, H. J. Mattord. Principle of Information Security(影印版)．清华大学出版社．2003年7月．
[16] E. Yu, S. Cho, Ga-SVM Wrapper Approach for Feature Subset Selection in Keystroke Dynamics Identity Verification. Proceedings of the International Joint Conference on Neural Networks, 2003, Vol.3: 2253-2257.
[17] E. Yu, S. Cho, Novelty Detection Approach for Keystroke Dynamics Identity Verification. Fourth International Conference on Intelligent Data Engineering and Automated Learning, 2003: 1016-1023.
[18] S. Cho, C. Han, D. Han, H. Kim. Web-based Keystroke Dynamics Identity Verification Using Neural Network. Journal of Organizational Computing and Electronic Commerce, 2000, 4: 295-307.
[19] 刘学军，陈松灿，彭宏京．基于支持向量机的计算机键盘用户身份验真．计算机研究与发展，2002年第9期，第39卷：1082-1086．
[20] 朱明，周津，王继康．基于击键特征的用户身份认证新方法．计算机工程．2002年第10期，第28卷：138-140．
[21] L. K, Maisuria, C. S. Ong, W. K. Lai. A Comparison of Artificial Neural Networks and Cluster Analysis for Typing Biometrics Authentication. International Joint Conference on Neural Networks, 1999, Vol.5: 3295-3299.
[22] S. Bleha, D. Gillespie. Computer User Identification Using the Mean and the Median as features. IEEE International Conference on Systems, Man, and Cybernetics, 1998, Vol.5: 4379-4381.
[23] M. S. Obaidat, B. Sadoun. Verification of Computer Users Using Keystroke Dynamics. IEEE Transactions on Systems, Man and Cybernetics, 1997, Vol.27(2): 261-269.
[24] M. S. Obaidat. A Comparative Performance Study of Neural Network Paradigms for Identifying Computer Users. IEEE 13th Annual International Phoenix Conference on Computers and Communications, 1994, 4:161.
[25] M. S. Obaidat, D. T. Macchiarolo. An On-Line Neural Network System for Computer Access Security. IEEE Transactions on Industrial Electronics, 1993, Vol.40(2): 235-242.
[26] S. A. Bleha, J. Knopp, M.S. Obaidat. Performance of the Perceptron Algorithm for the Classification of Computer Users. Proceedings of the 1992 ACM/SIGAPP Symposium on Applied Computing: 863-866.
[27] S. Bleha, C. Slivinsky, B. Hussien. Computer-Access Security Systems Using Keystroke Dynamics. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, Vol.12(12): 1217-1222.
[28] S. A. Bleha, M. S. Obaidat. Dimensionality Reduction and Feature Extraction Application in Identifying Computer Users. IEEE Transactions on Systems, Man and Cybernetics, 1991, Vol. 21(2): 452-456.
[29] S. A. Bleha, M. S. Obaidat. Computer Users Verification Using the Perceptron Algorithm. IEEE Transactions on Systems, Man and Cybernetics, 1993, Vol. 23(3): 900-902.
[30] J. A. Robinson, V. M. Liang, J. A. M. Chambers, C.L. Mackenzie. Computer User Verification Using Login String Keystroke Dynamics. IEEE Transactions on Systems, Man and Cybernetics, 1998, Vol.28(2): 236-241.
[31] T. Ord, S, M. Furnell. User Authentication for Keypad-based Devices Using Keystroke Analysis. Proceedings of the Second International Network Conference, 2000: 263-272,
[32] 司捷，周贵安，李函，韩英铎．基于梯度监督学习的理论与应用(Ⅰ、Ⅱ)．清华大学学报(自然科学版)，1997年，第37卷第7期：71-73．第37卷第9期：104-107．
[33] 曾黄麟．粗集理论及其应用(一、二、三、四)．四川轻化工学院学报，1996年，第9卷第1期：18-28，第2期：1-7，第3期：34-41，第4期：20-26．
[34] 张学工．关于统计学习理论与支持向量机．自动化学报．2000年1月，第26卷第1期：32-42．
[35] R. Plamondon, S.N. Srihari. On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, Vol.22(1): 63-84.
[36] 朱勇，谭铁牛，王蕴红．基于笔迹的身份识别．自动化学报．2001年3月，第27卷第2期：229-234．
[37] 梁艳春，王在中．人工神经网络BP算法密集型数据的预处理．吉林大学自然科学学报，1995年8月，第3期：19-22．
[38] 赵弘，周瑞祥，林廷沂．基于Levenberg-Marquardt算法的神经网络监督控制．西安交通大学学报，2002年5月，第36卷第5期：523-527．
[39] 袁玲．交通噪声预测的神经网络模型．长安大学学报(自然科学版)，2003年3月，第23卷第2期：84-87．
[40] 张栋，蔡开元．基于遗传算法的神经网络两阶段学习方案．系统仿真学报，2003年8月，第15卷第8期：1088-1090．
[41] 郑宏，陆阳，徐朝农．基于BP神经网络的入侵检测系统分类器的实现．合肥工业大学学报(自然科学版)，2003年4月，第26卷第2期：281-285．
[42] N. Ampazis, S. J. Perantonis. Levenberg-Marquardt Algorithm with Adaptive Momentum for the Efficient Training of Feedforward Networks. Proceedings of the IEEE international Joint Conference on Neural Networks, 2000. Vol. 1: 126-131.
[43] D Dasgupta, S. Forrest. Novelty Detection in Time Series Data Using Ideas from Immunology. 5th International Conference on Intelligent Systems, 1996: 1-6.
[44] S. Mukkamala, G. Janoski, A. Sung. Intrusion Detection using Neural Networks and Support Vector Machines. Proceedings of the International Joint Conference on Neural Networks, 2002, Vol.2: 1702-1707.
[45] V. N. Vapnik. An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks, 1999, Vol. 10(5): 988-999.
[46] Z. Wu, D. Li. Neural Network based on Rough Sets and its Application to Remote Sensing Image Classification. Geo-spatial Information Science(Quarterly), 2002, Vol.5(2): 17-21.
[47] 何立民，万跃华．基于隐马尔可夫链和支持向量机人脸识别混合模型的视频节目聚类标注．上海交通大学学报，2003年9月，第37卷增刊：176-183．
[48] 苏毅，吴文虎，郑方，方棣棠．基于支持向量机的语音识别．第六届全国人机语音通讯学术会议，2001年11月：223-226．
[49] 石剑琛，汪厚洋．存取控制技术研究．计算机与数字工程，2003年第4期，第31卷：58-60．
[50] 冯登国．关于发展我国信息安全的几点建议．中国科学院院刊，2002年第4期：289-291．
[51] J．Richter著，王建华等泽．Windows核心编程．机械工业出版社，2000年5月．
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |