基于智能手表运动传感器的新型攻击及其防范

doi:10.11959/j.issn.1000-436x.2015304

通信学报 ›› 2015, Vol. 36 ›› Issue (Z1): 235-242.doi: 10.11959/j.issn.1000-436x.2015304

基于智能手表运动传感器的新型攻击及其防范

宋晨光,刘建伟,伍前红,关振宇

北京航空航天大学电子信息工程学院，北京 100191

出版日期:2015-11-25 发布日期:2015-12-29
基金资助:
国家重点基础研究发展计划（“973”计划）基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;中央高校基本科研业务费专项基金资助项目

New attack based on smartwatch motion sensors and the protection method research

Chen-guang SONG,Jian-wei LIU,Qian-hong WU,Zhen-yu GUAN

School of Electronics and Information Engineering,Beihang University,Beijing 100191,China

Online:2015-11-25 Published:2015-12-29
Supported by:
The National Basic Research Program of China (973 Program);The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China;The Fundamental Research Funds for the Central Universities

摘要/Abstract

摘要：

智能手表上搭载了加速度计、陀螺仪等运动传感器，且会随着手部运动而产生位移，使通过智能手表窃取用户外部键盘输入成为了可能。研究了智能设备上基于6轴加速度计/陀螺仪来推断用户键盘输入的可行性，建立了用户进行键盘输入时的运动模型来对手部运动进行分类识别。当用户执行敏感输入，如在数字键盘上输入密码时，可根据传感器信息推断出密码。经实验验证，该方法可有效识别4位PIN码，证明此安全问题值得人们重视。

关键词: 智能手表, 运动传感器, 加速度计, 陀螺仪, 信息泄露

Abstract:

Smart watch shipped with various embedded motion sensors,such as the accelerometer and gyroscope.Smart watch can follow the movement of hand to recognize the corresponding displacement,so that others can steal user’s external keyboard input through smart watches.The feasibility of intelligent device based on 6 axis accelerometer/gyroscope to infer the user’s keyboard input was researched,and the user’s keyboard input kinematic model for motion classification recognition was established.When users perform sensitive inputting,such as passwords inputting on digital keyboard,the passwords according to sensor information can be deduced.The results show that the approach can effectively recognize the PIN code on keyboard,which absolutely prove the seriousness of this safety problem.

Key words: smart watch, motion sensor, accelerometer sensor, gyroscope sensor, information leakage

宋晨光,刘建伟,伍前红,关振宇. 基于智能手表运动传感器的新型攻击及其防范[J]. 通信学报, 2015, 36(Z1): 235-242.

Chen-guang SONG,Jian-wei LIU,Qian-hong WU,Zhen-yu GUAN. New attack based on smartwatch motion sensors and the protection method research[J]. Journal on Communications, 2015, 36(Z1): 235-242.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

表2

图11

参考文献 22

[1]	CHIN E , FELT A P , SEKAR V , et al. Measuring user confidence in smartphone security and privacy[A]. Proceedings of the Eighth Symposium on Usable Privacy and SecurityACM[C]. 2012.
[2]	JEON W , KIM J , LEE Y , et al. A practical analysis of smartphone security[J]. Lecture Notes in Computer Science, 2011,6771: 311-320.
[3]	WU L , DU X , FU X . Security threats to mobile multimedia applications:camera-based attacks on mobile phones[J]. IEEE Communications Magazine, 2014,52(3): 80-87.
[4]	Google. Android Sensors[EB/OL]. . 2015.
[5]	MARQUARDT P , VERMA A , CARTER H , et al. (sp)iPhone:decoding vibrations from nearby keyboards using mobile phone accelerometers[A]. Proceedings of ACM CCS[C]. 2011. 551-562.
[6]	CAI L , CHEN H . Touchlogger:inferring keystrokes on touch screen from smartphone motion[A]. HotSec’11 Proceedings of the 6th USENIX Conference on Hot Topics in Security[C]. 2011.9.
[7]	XU Z , BAI K , ZHU S . Taplogger:inferring user inputs on smartphone touchscreens using on-board motion sensors[A]. Proceedings of the Fifth Acm Conference on Wireless Network Security[C]. 2012. 113-124.
[8]	Apple. Apple Pay[EB/OL]. . 2015.
[9]	KELA J , KORPIP?? P , M?NTYJ?RVI J , et al. Accelerometer-based gesture control for a design environment[J]. Personal and Ubiquitous Computing, 2006,10(5): 285-299.
[10]	乔相伟 . 基于四元数非线性滤波的飞行器姿态确定算法研究[D]. 哈尔滨工程大学, 2011. QIAO X W . Attitude Determination Algorithm Based on Quaternion Nonlinear Filter for Spacecraft[D]. Harbin Engineering University, 2011.
[11]	KOWNACKI C . Optimization approach to adapt Kalman filters for the real-time application of accelerometer and gyroscope signals' filtering[J]. Digital Signal Processing, 2011,21(1): 131-140.
[12]	TRAWNY N , ROUMELIOTIS S I . Indirect Kalman filter for 3D pose estimation[J]. University of Minnesota,Dept.of Comp.Sci.＆ Eng.,Tech.Rep, 2005,2.
[13]	张春莹, 潘荣江 . 由整体到局部的平面曲线部分匹配算法[J]. 计算机辅助设计与图形学学报, 2008,(7): 894-899. ZHANG C Y , PAN R J . A global to local partial matching algorithm for planar curves[J]. Journal of Computer-Aided Design ＆ Computer Graphics, 2008,(7): 894-899.
[14]	CHEN F S , FU C M , HUANG C L . Hand gesture recognition using a real-time tracking method and hidden Markov models[J]. Image and vision computing, 2003,21(8): 745-758.
[15]	ZHOU S , SHAN Q , FEI F , et al. Gesture recognition for interactive controllers using MEMS motion sensors[A]. Nano/Micro Engineered and Molecular Systems,NEMS 2009.4th IEEE International Conference[C]. IEEE, 2009. 935-940.
[16]	FINK G A . Markov Models for Pattern Recognition:from Theory to Applications[M]. Springer Science ＆ Business Media, 2014.
[17]	KRIZHEVSKY A , SUTSKEVER I , HINTON G E . Imagenet classification with deep convolutional neural networks[A]. Advances in Neural Information Processing Systems[C]. 2012. 1097-1105.
[18]	高鹏毅 . BP 神经网络分类器优化技术研究[D]. 武汉:华中科技大学, 2012. GAO P Y . Study on the Optimization of Backpropagation Neural Network Classifier[D]. Wuhan:Huazhong University of Science and Technology, 2012.
[19]	SHIRAKAWA K , SHIMIZ M , OKUBO N , et al. A large-signal characterization of an HEMT using a multilayered neural network[J]. Journal of Henan University, 2011,45(9): 1630-1633.
[20]	张毅 . 静态手势识别的神经网络方法研究[D]. 成都:电子科技大学, 2011. ZHANG Y . Study on Neural Network for Static Gesture Recogni-tion[D]. Chengdu:University of Electronic Science and Technology of China, 2011.
[21]	Google. Android Motion sensors[EB/OL]. , 2015.
[22]	InvenSense. 6-Axis Motion Sensors[EB/OL]. . 2015.

分类	设备型号	传感器型号
智能手机	MI Note	MPU-6050
	Galaxy S6	MPU-6500
智能手表	Apple Watch	MPU-6700
	Moto 360	MPU-6051

轨迹图	10.11959/j.issn.1000-436x.2015304.F011	10.11959/j.issn.1000-436x.2015304.F012	10.11959/j.issn.1000-436x.2015304.F013
真实输入	1321	1992	2468
识别结果	1321 4654 7987	1992	2468
轨迹图	10.11959/j.issn.1000-436x.2015304.F014	10.11959/j.issn.1000-436x.2015304.F015	10.11959/j.issn.1000-436x.2015304.F016
真实输入	3741	4239	5732
识别结果	3741	4236 7539 7569	5721
轨迹图	10.11959/j.issn.1000-436x.2015304.F017	10.11959/j.issn.1000-436x.2015304.F018	10.11959/j.issn.1000-436x.2015304.F019
真实输入	6865	7623	9731
识别结果	6865 5754 2421 3532	7623	9731

基于智能手表运动传感器的新型攻击及其防范

New attack based on smartwatch motion sensors and the protection method research

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 22

相关文章 0

Metrics

推荐阅读 0