计算机科学 ›› 2020, Vol. 47 ›› Issue (11): 19-24.doi: 10.11896/jsjkx.200600004

• 智能移动身份认证 • 上一篇    下一篇

基于上采样单分类的智能手机手势密码隐式身份认证机制

姚沐言, 陶丹   

  1. 北京交通大学电子信息工程学院 北京 100044
  • 收稿日期:2020-06-01 修回日期:2020-09-14 出版日期:2020-11-15 发布日期:2020-11-05
  • 通讯作者: 陶丹(dtao@bjtu.edu.cn)
  • 作者简介:20120019@bjtu.edu.cn
  • 基金资助:
    国家自然科学基金“面上”基金项目(61872027);综合业务网理论及关键技术国家重点实验室开放研究基金(ISN21-16)

Implicit Authentication Mechanism of Pattern Unlock Based on Over-sampling and One-class Classification for Smartphones

YAO Mu-yan, TAO Dan   

  1. School of Electronic and Information Engineering,Beijing Jiaotong University,Beijing 100044,China
  • Received:2020-06-01 Revised:2020-09-14 Online:2020-11-15 Published:2020-11-05
  • About author:YAO Mu-yan,born in 1998.His main research interests include big data analysis,privacy and security.
    TAO Dan,born in 1978,Ph.D,professor,Ph.D supervisor,is a senior member of China Computer Federation and a member of CCF TCIoT.Her main research interests include the IoT,mobile computing,wireless network,big data security and intelligent information processing.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61872027) and Open Research Fund of State Key Laboratory of Integrated Services Networks (ISN21-16).

摘要: 现有智能手机往往使用广泛且存储有敏感信息,一旦丢失会造成巨大的安全隐患,故数据安全的重要性日益凸显。 鉴于传统认证策略的脆弱性,提出了一种基于上采样单分类的隐式身份认证机制。首先,融合使用了时间、二维及三维等多类手机内置传感器从不同维度采集用户的行为特征。 其次,为降低高维数据所含噪声对分类的影响,提出了一种精选特征并降维的行为特征筛选方法,对所提取的特征进行向量排序、筛选以及降维。特别地,考虑到现有基于二分类算法方案的局限性,采用SVM SMOTE对正样本数据进行上采样,并提出了基于单分类的认证决策机制,以在单类小规模训练集上实现分类。 最后基于实际的样本集进行性能测试,结果表明,所提方案在准确率、FAR、FRR与AUC指标上的表现部分优于使用大规模数据进行训练的传统KNN二分类器。

关键词: 隐式身份认证, 手势密码, 单类支持向量机, 超小规模训练集, 上采样

Abstract: Nowadays,smartphones are widely used and stored with sensitive information,and the loss of any personal device can cause fatal information compromise.Thus,the people's attention towards data security has been elevated to a higher level.Considering the delicacy of traditional authentications,this paper investigates an implicit authentication mechanism based on over-sampling and one-class classification,for pattern unlock on smartphones.First,a fusion of time,two-dimensional and three-dimensional sensors is employed,to collect user behavioral biometrics comprehensively.Second,in order to ease the impact caused by noise contained in high-dimensional data,a feature screening,which is composed of feature selection and dimensional compression,is designed.Particularly,in view of the existing limitations of the current binary classification schemes,SVM SMOTE is used to over-sample the user behavioral data,and a one-class classification authentication mechanism is delivered to implement classification,of which the learning process is only based on a single-class diminutive training set.A series of experiments have been conducted on actual data,and results show that the proposed scheme,when only relies on a single-class diminutive training set,performs partially better than the traditional binomial KNN classifier which is trained on large-scale data,in terms of accuracy,FAR,FRR and AUC.

Key words: Implicit authentication, Gesture pattern, One-class support vector machine, Diminutive training data set, Over-sampling

中图分类号: 

  • TP391.4
[1] LEE M K.Security notions and advanced method for humanshoulder-surfing resistant PIN-entry [J].IEEE Transactions on Information Forensics and Security,2014,9(4):695-708.
[2] SCHNEEGASS S,STEIMLE F,BULLING A,et al.SmudgeSafe:geometric image transformations for smudge-resistant user authentication [C] //Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '14).2014:775-786.
[3] HOANG T,NGUYEN T C,LUONG C,et al.Adaptive crossdevice gait recognition using a mobile accelerometer [J].Journalof Information Processing Systems,2013,9(2):333-348.
[4] SITOVAZ,SEDENKA J,YANG Q,et al.HMOG:new behavioral biometric features for continuous authentication of smartphone users [J].IEEE Transactions on Information Forensics and Security,2016,11(5):877-892.
[5] LIU L C,LI R G,YIN L H,et al.Research on multi-feature fusion impact authentication for intelligent mobile device[J].Acta Electronica Sinica,2016,44(11):2713-2719.
[6] KONGJ,GUO Y B,LIU C H,et al.Gait feature identification method based on motion sensor in smartphone[J].Journal of Computer Applications,2019,39(6):1747-1752.
[7] XIANG D D,CHEN H G,XIONG J J.Research on identity verification of mobile based on user behavior characteristics [J].Journal of Shanghai Normal University(Natural Sciences),2019,48(2):151-159.
[8] WANG R Z,TAO D.Context-aware implicit authentication of smartphone users based on multi-sensor behavior [J].IEEE Access,2019,7:119654-119667.
[9] YANG Y F,GUO B,WANG Z,et al.BehaveSense:Continuous authentication for security-sensitive mobile apps using behavioral biometrics [J].Ad Hoc Networks,2019,2019(84):9-18.
[10] SUN C,WANG Y,ZHENG J.Dissecting pattern unlock:Theeffect of pattern strength meter on pattern selection [J].Journal of Information Security and Applications,2014,19:4-5.
[11] SHI X P,WONG Y D,LI M Z,et al.A feature learning approach based on XGBoost for driving assessment and risk prediction [J].Accident Analysis & Prevention,2019,129:170-179.
[12] DONG M G,JIANG Z L,JING C.Multi-class imbalanced learning algorithm based on hellinger distance and smote algorithm[J].Computer Science,2020,47(1):102-109.
[13] LIU B Y.Smart phone identity authentication based on gesture recognition [D].Beijing:Beijing Jiaotong University,2018.
[1] 董明刚,姜振龙,敬超. 基于海林格距离和SMOTE的多类不平衡学习算法[J]. 计算机科学, 2020, 47(1): 102-109.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[2] 施超,谢在鹏,柳晗,吕鑫. 基于稳定匹配的容器部署策略的优化[J]. 计算机科学, 2018, 45(4): 131 -136 .
[3] 刘琴. 计算机取证过程中基于约束的数据质量问题研究[J]. 计算机科学, 2018, 45(4): 169 -172 .
[4] 郭帅,刘亮,秦小麟. 用户偏好约束的空间关键词范围查询处理方法[J]. 计算机科学, 2018, 45(4): 182 -189 .
[5] 张景,朱国宾. 基于CBOW-LDA主题模型的Stack Overflow编程网站热点主题发现研究[J]. 计算机科学, 2018, 45(4): 208 -214 .
[6] 文俊浩,孙光辉,李顺. 基于用户聚类和移动上下文的矩阵分解推荐算法研究[J]. 计算机科学, 2018, 45(4): 215 -219 .
[7] 丁舒阳,黎冰,侍洪波. 基于改进的离散PSO算法的FJSP的研究[J]. 计算机科学, 2018, 45(4): 233 -239 .
[8] 侯彦娥,孔云峰,党兰学. 求解多车型校车路径问题的混合集合划分的GRASP算法[J]. 计算机科学, 2018, 45(4): 240 -246 .
[9] 锁延锋,王少杰,秦宇,李秋香,丰大军,李京春. 工业控制系统的安全技术与应用研究综述[J]. 计算机科学, 2018, 45(4): 25 -33 .
[10] 王振武,吕小华,韩晓辉. 基于四叉树分割的地形LOD技术综述[J]. 计算机科学, 2018, 45(4): 34 -45 .