[1]许洪军,张洪,贺维.一种基于鼠标行为的云用户异常检测方法[J].哈尔滨理工大学学报,2019,(04):127-132.[doi:10.15938/j.jhust.2019.04.021]
 XU Hong-jun,ZHANG Hong,HE Wei.A Cloud User Anomaly Detection Method Based on Mouse Behavior[J].哈尔滨理工大学学报,2019,(04):127-132.[doi:10.15938/j.jhust.2019.04.021]
点击复制

一种基于鼠标行为的云用户异常检测方法()
分享到:

《哈尔滨理工大学学报》[ISSN:1007-2683/CN:23-1404/N]

卷:
期数:
2019年04期
页码:
127-132
栏目:
计算机与控制工程
出版日期:
2019-08-25

文章信息/Info

Title:
A Cloud User Anomaly Detection Method Based on Mouse Behavior
文章编号:
1007-2683(2019)04-0127-06
作者:
许洪军12张洪2贺维3
(1.哈尔滨理工大学 计算机科学与技术学院,黑龙江 哈尔滨 150080;
2.黑龙江农业工程职业学院 信息学院,黑龙江 哈尔滨 150088;
3.哈尔滨师范大学 计算机科学与信息工程学院,黑龙江 哈尔滨 150025)
Author(s):
XU Hong-jun12ZHANG Hong2HE Wei3
(1.School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080,China;
2.School of Information, Heilongjiang Agricultural Engineering Vocational College, Harbin 150088,China;
3.School of Computer Science and Information Engineering, Harbin Normal University, Harbin 150025,China)
关键词:
云安全深度学习卷积神经网络操作行为异常行为检测
Keywords:
cloud security depth learning convolutional neural network(CNN) operational behavior Abnormal behavior detection
分类号:
TP301.6
DOI:
10.15938/j.jhust.2019.04.021
文献标志码:
A
摘要:
针对由于云用户的非法操作产生的云安全威胁问题,提出一种在保障云用户隐私的前提下,利用深度学习技术对用户工作中的鼠标操作行为进行分析,实现检测云用户异常行为的方法。该方法首先通过鼠标追踪工具,记录一定时间内用户的基本鼠标操作行为轨迹,然后利用卷积神经网络对记录的行为轨迹图像进行特征学习和分类。通过实验可知,所提出的方法能够在保障用户隐私的前提下,有效的检测用户的异常行为,同时可以避免对系统高维特征数据分析和处理,降低了异常行为检测的难度。
Abstract:
Aiming at the problem of cloud security threat caused by illegal operation of cloud users, this paper proposes a method to detect the abnormal behavior of cloud users by analyzing the mouse operation behavior in user’s work by using deep learning technology under the premise of ensuring the privacy of cloud users. Firstly, the mouse track tool is used to record the trajectory of the user’s basic mouse operation within a certain period of time. Then, the convolution neural network is used to learn and classify the recorded trajectories. The experimental results show that the proposed method can effectively detect abnormal behavior of users under the precondition of ensuring user privacy, meanwhile, it can avoid the analysis and processing of high dimensional feature data and reduce the difficulty of abnormal behavior detection.

参考文献/References:

[1]ALLIANCE CS. The Treacherous 12Cloud Computing Top Threats in 2016. https://cloudsecurityalliance.org/download/thetreacheroustwelvecloudcomputingtopthreatsin2016/,2016,02.
[2]王国峰,刘川意,潘鹤中,等.云计算模式内部威胁综述[J].计算机学报.2017,40(2):296.
[3]陈小军,时金桥,徐菲,等.面向内部威胁的最优安全策略算法研究[J].计算机研究与发展,2014,51(7):1565.
[4]SANZGIRI A, DASGUPTA D. Classification of insider threat detection technigues[C]// Proceedings of the 11th Annual Cyber and Information Security Research Conference. Oak Ridge, USA, 2016:25.
[5]MAHAJAN A, SHARMA S. The malicious insiders threat in the cloud[J]. International Journal of Engineering Research and General Science ,2015, 3(2):245.
[6]宋国峰,梁昌勇.一种基于用户行为信任的云安全访问控制模型[J].中国管理科学,2013,(S2):669.
[7]段新东,张鑫,林玉香.云计算环境下非法用户入侵行为的检测与分析[J].吉林大学学报(理学版),2017,55(3):623.
[8]沈超,蔡忠闽,管晓宏,等.基于鼠标行为特征的用户身份认证与监控[J].通信学报,2010,31(7):68.
[9]彭雅琴,成孝刚.一种优化的卷积神经网络深度学习算法[J].现代电子技术,2016,(23):179.
[10]CHA YJ, CHOI W, BUYUKOZTURK O.Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks[J].Computer‐Aided Civil and Infrastructure Engineering,2017,32(5):361.
[11]廖祥文,张丽瑶,宋志刚,等.基于卷积神经网络的中文微博观点分类[J].模式识别与人工智能,2016(12):1072.
[12]TOTH L. Phone recognition with hierarchical convolutional deep maxout networks [J].EURASIP Journal on Audio,Speech,and Music Processing,2015,(1):1.
[13]刘明珠,郑云非,樊金,等. 基于深度学习法的视频文本区域定位与识别[J]. 哈尔滨理工大学学报,2016,21(6): 61.
[14]卢宏涛,张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理. 2016, 31 (1) :1.
[15]李彦冬,郝宗波,雷航. 卷积神经网络研究综述[J]. 计算机应用,2016, 36 (9) :2508.
[16]韩磊,曲中水. 一种RGB模型彩色图像增强方法[J]. 哈尔滨理工大学学报,2014,19(6):59.
[17]YUAN ZW, ZHANG J. Feature extraction and image retrieval based on AlexNet[C]// Eighth International Conference on Digital Image Processing. 2016:100330E.
[18]邓柳,汪子杰. 基于深度卷积神经网络的车型识别研究[J]. 计算机应用研究,2016,33(3):930.
[19]TAIGMAN Y, YANG M, RANZATO M,et al. Deepface: Closing the Gap to Humanlevel Performance in Face Verification[C]// Computer Vision & Pattern Recognition, 2014 :1701.
[20]GE FX, SHI Y, SUN B,et al. Sparse representation based classification by using PCASIFT descriptors[C]// IEEE International Conference on Information Science and Technology, 2014: 429. 

相似文献/References:

[1]曲媛媛,宫莉莹,贺维.一种RNN-DBN的网络购物风险评估方法[J].哈尔滨理工大学学报,2019,(04):105.[doi:10.15938/j.jhust.2019.04.018]
 QU Yuan-yuan,GONG Li-ying,HE Wei.A Method of Online Shopping Risk Assessment Based on RNN-DBN[J].哈尔滨理工大学学报,2019,(04):105.[doi:10.15938/j.jhust.2019.04.018]

备注/Memo

备注/Memo:
?收稿日期: 2017-12-27
基金项目: 国家自然科学基金(61370031,61702142).
作者简介:
许洪军(1966—),男,硕士,教授;
张洪(1980—),男,硕士,讲师.
通信作者:
贺维(1980—),男,博士,讲师,E-mail: 64282426@qq.com.
更新日期/Last Update: 2019-09-04