Mobile Behaviometrics: Behavior Modeling from Heterogeneous Sensor Time-Series

In the era of ubiquitous and mobile computing, the penetration of mobile devices equipped with various embedded sensors makes it possible to capture the physical and virtual context of the user and his/her surrounding environment. There is also an increasing demand to model human behaviors based on those data to enable context-aware computing and people-centric applications, which utilize users’ behavior pattern to improve the existing services or develop new services. Over the decades, we have seen tremendous success in biometrics technologies being used in all types of applications based on the physical attributes of the individual such as face, fingerprints, voice and iris. Inspired by this, we introduce a new concept Mobile Behaviometrics, which uses algorithms and models to measure and quantify unique human behavioral patterns in place of human bio-attributes. Behaviometrics algorithms take multiple data from various sensors as input and fuse them to build behavioral models which are capable of producing application specific quantitative analysis on the unique individuals that were the originators of the data. We have three main challenges: statistical modeling of the sensor data, difficulty of multidimensional sensor fusion and structural activity recognition. Based on our observation of the similarity between human behavior and natural language, we apply natural language processing (NLP) techniques to statistically model heterogeneous sensor data and investigate various applications based on the derived models. We also investigate adapting conventional machine learning techniques to human behavioral modeling for non time-sensitive behavior sequences. To overcome the difficulty of multi-dimensional sensor fusion, we develop a hybrid approach to first learn behavioral factors for feature dimension reduction and then infer optimal way of fusing models from different factors. We study a novel Helix algorithm to induce the underlying grammar of human activities and ultimately solve the structural activity recognition. Our analytical work has been incorporated into a mobile security application SenSec, which

[1]  Ian Oakley,et al.  CASA: context-aware scalable authentication , 2013, SOUPS.

[2]  Eamonn J. Keogh,et al.  Exact Discovery of Time Series Motifs , 2009, SDM.

[3]  Adam J. Aviv,et al.  Practicality of accelerometer side channels on smartphones , 2012, ACSAC '12.

[4]  Katayoun Farrahi,et al.  Extracting Mobile Behavioral Patterns with the Distant N-Gram Topic Model , 2012, 2012 16th International Symposium on Wearable Computers.

[5]  Ying Zhang,et al.  Towards Accountable Mobility Model: A Language Approach on User Behavior Modeling in Office WLAN , 2011, 2011 Proceedings of 20th International Conference on Computer Communications and Networks (ICCCN).

[6]  CHENGXIANG ZHAI,et al.  A study of smoothing methods for language models applied to information retrieval , 2004, TOIS.

[7]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[8]  Alessandro Neri,et al.  Keystroke dynamics authentication for mobile phones , 2011, SAC.

[9]  Ying Zhang,et al.  n-Gram Geo-trace Modeling , 2011, Pervasive.

[10]  Branislav Kveton,et al.  Inferring Identity Using Accelerometers in Television Remote Controls , 2009, Pervasive.

[11]  Peng-Wen Chen,et al.  A Language Approach to Modeling Human Behaviors , 2010, LREC.

[12]  Matthias Baldauf,et al.  A survey on context-aware systems , 2007, Int. J. Ad Hoc Ubiquitous Comput..

[13]  Ying Zhang,et al.  PnLUM : System for Prediction of Next Location for Users with Mobility , 2012 .

[14]  Xian Ke,et al.  Typing patterns: a key to user identification , 2004, IEEE Security & Privacy Magazine.

[15]  Jun Yang,et al.  SenGuard: Passive user identification on smartphones using multiple sensors , 2011, 2011 IEEE 7th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob).

[16]  Kirsi Helkala,et al.  Biometric Gait Authentication Using Accelerometer Sensor , 2006, J. Comput..

[17]  Indranil Gupta,et al.  Joint bluetooth/wifi scanning framework for characterizing and leveraging people movement in university campus , 2010, MSWIM '10.

[18]  Günther Retscher,et al.  Location determination using WiFi fingerprinting versus WiFi trilateration , 2007, J. Locat. Based Serv..

[19]  Gregory D. Abowd,et al.  The smart floor: a mechanism for natural user identification and tracking , 2000, CHI Extended Abstracts.

[20]  K. Burke,et al.  Language as symbolic action : essays on life, literature, and method , 1966 .

[21]  Guy W. Mineau,et al.  Beyond TFIDF Weighting for Text Categorization in the Vector Space Model , 2005, IJCAI.

[22]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[23]  Zhigang Liu,et al.  The Jigsaw continuous sensing engine for mobile phone applications , 2010, SenSys '10.

[24]  Jennifer Healey,et al.  A Long-Term Evaluation of Sensing Modalities for Activity Recognition , 2007, UbiComp.

[25]  Hao Hu,et al.  Privacy-Preserved Mobile Sensing through Hybrid Cloud Trust Framework , 2013, 2013 IEEE Sixth International Conference on Cloud Computing.

[26]  Xiao Wang,et al.  SenSec: Mobile security through passive sensing , 2013, 2013 International Conference on Computing, Networking and Communications (ICNC).

[27]  Philipp Bolliger,et al.  Redpin - adaptive, zero-configuration indoor localization through user collaboration , 2008, MELT '08.

[28]  Michael Beigl,et al.  Activity recognition for creatures of habit , 2014, Pers. Ubiquitous Comput..

[29]  Ying Zhang,et al.  WASP: An Enhanced Indoor Locationing Algorithm for a Congested Wi-Fi Environment , 2009, MELT.

[30]  J. D. Tygar,et al.  Usability of Security: A Case Study, , 1998 .

[31]  Ying Zhang,et al.  A language-based approach to indexing heterogeneous multimedia lifelog , 2010, ICMI-MLMI '10.

[32]  David Kotz,et al.  Extracting a Mobility Model from Real User Traces , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[33]  Hao Chen,et al.  On the Practicality of Motion Based Keystroke Inference Attack , 2012, TRUST.

[34]  John F. Canny,et al.  Modeling Human Behavior from Simple Sensors in the Home , 2006, Pervasive.

[35]  Liang Wang,et al.  Behavioral Biometrics For Human Identification: Intelligent Applications , 2009 .

[36]  Farzad Pourboghrat.  Multi-layer neural networks for robot control , 1989 .

[37]  Roy A. Maxion,et al.  Comparing anomaly-detection algorithms for keystroke dynamics , 2009, 2009 IEEE/IFIP International Conference on Dependable Systems & Networks.

[38]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[39]  Jennifer C. Hou,et al.  Modeling steady-state and transient behaviors of user mobility: formulation, analysis, and application , 2006, MobiHoc '06.

[40]  William A. Arbaugh,et al.  Improving the latency of 802.11 hand-offs using neighbor graphs , 2004, MobiSys '04.

[41]  Gerald Q. Maguire,et al.  A class of mobile motion prediction algorithms for wireless mobile computing and communications , 1996, Mob. Networks Appl..

[42]  Ravi Jain,et al.  Predictability of WLAN Mobility and Its Effects on Bandwidth Provisioning , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[43]  Jun Han,et al.  ACCessory: password inference using accelerometers on smartphones , 2012, HotMobile '12.

[44]  Sahin Albayrak,et al.  Monitoring Smartphones for Anomaly Detection , 2008, Mob. Networks Appl..

[45]  Jiang Zhu,et al.  Mobile Lifelogger - Recording, Indexing, and Understanding a Mobile User's Life , 2010, MobiCASE.

[46]  Muddassar Farooq,et al.  Keystroke-Based User Identification on Smart Phones , 2009, RAID.

[47]  Markus Jakobsson,et al.  Implicit authentication for mobile devices , 2009 .

[48]  Markus Jakobsson,et al.  Implicit Authentication through Learning User Behavior , 2010, ISC.

[49]  Damon L. Woodard,et al.  Biometric Authentication and Identification using Keystroke Dynamics: A Survey , 2012 .

[50]  Ying Zhang,et al.  SensCare: Semi-automatic Activity Summarization System for Elderly Care , 2011, MobiCASE.

[51]  T. Gilovich,et al.  The Perceiver as Perceived: Everyday Intuitions About the Correspondence Bias , 1999 .

[52]  Jun Han,et al.  ACComplice: Location inference using accelerometers on smartphones , 2012, 2012 Fourth International Conference on Communication Systems and Networks (COMSNETS 2012).

[53]  Claudia Picardi,et al.  User authentication through keystroke dynamics , 2002, TSEC.