Continuous Authentication Using Writing Style

The reinforcement of traditional static authentication by performing continuous authentication (CA) while the system is being used ensures that the user is legitimate throughout the computer usage. Stylometry can be a good candidate for CA since writing style can be acquired in a nonintrusive way and also is a good indicator of authorship. In using stylometry, the authentication process consists of comparing sample writing of an individual against the model or profile associated with the identity claimed by that individual at login time (i.e., one-to-one identity matching). Effective CA requires reauthenticating the user over a short period of time, which equates using a short text. Analyzing short texts is challenging since decision-making occurs on a limited amount of available information. High accuracy and resilience to forgery are other key challenges faced by CA. In this chapter, we discuss the key research challenges faced in using stylometry for CA, and we introduce an approach to tackle some of those challenges. Different classification techniques are investigated and evaluated using different public datasets, yielding encouraging performance results.

[1]  Justin Zobel,et al.  Searching With Style: Authorship Attribution in Classic Literature , 2007, ACSC.

[2]  Isaac Woungang,et al.  Toward a Framework for Continuous Authentication Using Stylometry , 2014, 2014 IEEE 28th International Conference on Advanced Information Networking and Applications.

[3]  Ophir Frieder,et al.  Repeatable evaluation of search services in dynamic environments , 2007, TOIS.

[4]  D. Holmes.  The Evolution of Stylometry in Humanities Scholarship , 1998 .

[5]  Charles C. Tappert,et al.  A Stylometry System for Authenticating Students Taking Online Tests , 2011 .

[6]  Rajarathnam Chandramouli,et al.  Gender identification from E-mails , 2009, 2009 IEEE Symposium on Computational Intelligence and Data Mining.

[7]  Ahmed Awad E. Ahmed,et al.  A New Biometric Technology Based on Mouse Dynamics , 2007, IEEE Transactions on Dependable and Secure Computing.

[8]  T C Mendenhall,et al.  THE CHARACTERISTIC CURVES OF COMPOSITION. , 1887, Science.

[9]  Moshe Koppel,et al.  Exploiting Stylistic Idiosyncrasies for Authorship Attribution , 2003 .

[10]  Eric Backer,et al.  On musical stylometry - a pattern recognition approac , 2005, Pattern Recognit. Lett..

[11]  Yuezhong Tang,et al.  Spam Filter for Short Messages Using Winnow , 2008, 2008 International Conference on Advanced Language Processing and Web Information Technology.

[12]  Isaac Woungang,et al.  Authorship verification for short messages using stylometry , 2013, 2013 International Conference on Computer, Information and Telecommunication Systems (CITS).

[13]  Hsinchun Chen,et al.  Applying authorship analysis to extremist-group Web forum messages , 2005, IEEE Intelligent Systems.

[14]  Yejin Choi,et al.  Gender Attribution: Tracing Stylometric Evidence Beyond Topic and Genre , 2011, CoNLL.

[15]  Benjamin C. M. Fung,et al.  A unified data mining solution for authorship analysis in anonymous textual communications , 2013, Inf. Sci..

[16]  Naomie Salim,et al.  Understanding Plagiarism Linguistic Patterns, Textual Features, and Detection Methods , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[17]  Hong Peng,et al.  Research on a Naive Bayesian Based Short Message Filtering System , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[18]  Angela Orebaugh,et al.  Classification of Instant Messaging Communications for Forensics Analysis , 2009 .

[19]  Daniel P. Lopresti,et al.  Biometric Authentication Revisited: Understanding the Impact of Wolves in Sheep's Clothing , 2006, USENIX Security Symposium.

[20]  Issa Traore,et al.  Continuous Authentication Using Biometrics: Data, Models, and Metrics , 2011 .

[21]  Peng Hao,et al.  Authorship Similarity Detection from Email Messages , 2011, MLDM.

[22]  Hsinchun Chen,et al.  Writeprints: A stylometric approach to identity-level identification and similarity detection in cyberspace , 2008, TOIS.

[23]  John Burrows,et al.  'Delta': a Measure of Stylistic Difference and a Guide to Likely Authorship , 2002, Lit. Linguistic Comput..

[24]  Yiming Yang,et al.  The Enron Corpus: A New Dataset for Email Classi(cid:12)cation Research , 2004 .

[25]  F. Mosteller,et al.  Inference in an Authorship Problem , 1963 .

[26]  Efstathios Stamatatos.  A survey of modern authorship attribution methods , 2009 .

[27]  George M. Mohay,et al.  Mining e-mail content for author identification forensics , 2001, SGMD.

[28]  Dale Schuurmans,et al.  Language independent authorship attribution using character level language models , 2003, Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - EACL '03.

[29]  Hans Van Halteren,et al.  Author verification by linguistic profiling: An exploration of the parameter space , 2007, TSLP.

[30]  Norman Shapiro,et al.  Authentication by Keystroke Timing: Some Preliminary Results , 1980 .

[31]  J. P. Carvalho,et al.  Authorship identification and author fuzzy “fingerprints” , 2011, 2011 Annual Meeting of the North American Fuzzy Information Processing Society.

[32]  Issa Traoré,et al.  Continuous authentication using micro-messages , 2014, 2014 Twelfth Annual International Conference on Privacy, Security and Trust.

[33]  Patrick Juola,et al.  A Controlled-corpus Experiment in Authorship Identification by Cross-entropy , 2003 .

[34]  Shlomo Argamon,et al.  Style mining of electronic messages for multiple authorship discrimination: first results , 2003, KDD '03.

[35]  Issa Traoré,et al.  Dynamic sample size detection in continuous authentication using sequential sampling , 2011, ACSAC '11.

[36]  R. Harald Baayen,et al.  How Variable May a Constant be? Measures of Lexical Richness in Perspective , 1998, Comput. Humanit..

[37]  Moshe Koppel,et al.  Authorship verification as a one-class classification problem , 2004, ICML.

[38]  H. van Halteren,et al.  Outside the cave of shadows: using syntactic annotation to enhance authorship attribution , 1996 .

[39]  John Burrows,et al.  Word-Patterns and Story-Shapes: The Statistical Analysis of Narrative Style , 1987 .

[40]  Benno Stein,et al.  Overview of the Author Profiling Task at PAN 2013 , 2013, CLEF.

[41]  Carole E. Chaski,et al.  Who's At The Keyboard? Authorship Attribution in Digital Evidence Investigations , 2005, Int. J. Digit. EVid..

[42]  Mohammad S. Obaidat,et al.  Authorship verification using deep belief network systems , 2017, Int. J. Commun. Syst..

[43]  Rajarathnam Chandramouli,et al.  Author gender identification from text , 2011, Digit. Investig..

[44]  Patrick Juola,et al.  Authorship Attribution for Electronic Documents , 2006, IFIP Int. Conf. Digital Forensics.

[45]  Martha E. Crosby,et al.  Continuous identity authentication using multimodal physiological sensors , 2004, SPIE Defense + Commercial Sensing.

[46]  Rachel Greenstadt,et al.  Practical Attacks Against Authorship Recognition Techniques , 2009, IAAI.

[47]  Hsinchun Chen,et al.  A framework for authorship identification of online messages: Writing-style features and classification techniques , 2006 .

[48]  Ophir Frieder,et al.  Discrimination of Authorship Using Visualization , 1994, Inf. Process. Manag..

[49]  Shlomo Argamon,et al.  Authorship attribution in the wild , 2010, Lang. Resour. Evaluation.

[50]  Benjamin C. M. Fung,et al.  e-mail authorship verification for forensic investigation , 2010, SAC '10.

[51]  Benjamin C. M. Fung,et al.  A novel approach of mining write-prints for authorship attribution in e-mail forensics , 2008, Digit. Investig..

[52]  Mourad Debbabi,et al.  Towards an integrated e-mail forensic analysis framework , 2009, Digit. Investig..