Long-Text Keystroke Biometric Applications over the Internet Gary Bartolacci, Mary Curtin, Marc Katzenberg, Ngozi Nwana, Sung-Hyuk Cha, and Charles Tappert.

Slides:



Advertisements
Similar presentations
Allegory An allegory is a form of extended metaphor in which objects, persons, and actions are made to represent something outside the story itself. In.
Advertisements

Touch-Screen Mobile- Device Data Collection for Biometrics Studies W. Ciaurro, B. Major, D. Martinez, D. Panchal, G. Perez, M. Rana, R. Rana, R. Reyes,
Team Members: Ana Caicedo Escobar Sandeep Indukuri Deepthi Tulasi Kevin Chan Under Esteemed Guidance of: Prof. Charles C Tappert Robert Zack.
Biometric Products Michael Isola John Granger, Wojciech Hojdysz, Arthur Gadayev.
Keystroke Biometrics Study Software Engineering Project Team + DPS Student.
Long Text Keystroke Biometrics Study Gary Bartolacci, Mary Curtin, Marc Katzenberg, Ngozi Nwana Sung-Hyuk Cha, Charles Tappert (Software Engineering Project.
CS Team 5 Alex Wong Raheel Khan Rumeiz Hasseem Swati Bharati Biometric Authentication System.
Keystroke Biometric Studies Security Research at Pace Keystroke Biometric Drs. Charles Tappert and Allen Stix Seidenberg School of CSIS.
Keystroke Biometric Studies Assignment 2 – Review of the Literature Case Study – Keystroke Biometric Describe problem investigated (intro + abstract) Developed.
Keystroke Biometric Studies Keystroke Biometric Identification and Authentication on Long-Text Input Book chapter in Behavioral Biometrics for Human Identification.
Robert S. Zack, Charles C. Tappert, and Sung-Hyuk Cha Pace University, New York Performance of a Long-Text-Input Keystroke Biometric Authentication System.
Keystroke Biometric Studies Assignment 2 – Review of the Literature Case Study – Keystroke Biometric Describe the problem being investigated Build a case.
Handwriting Copybook Style Analysis Of Pseudo-Online Data Student and Faculty Research Day Mary L. Manfredi, Dr. Sung-Hyuk Cha, Dr. Charles Tappert, Dr.
Working with Worksheet
Pattern Recognition: Baysian Decision Theory Charles Tappert Seidenberg School of CSIS, Pace University.
Keystroke Dynamics Etem DENİZ, Buğra KOCATÜRK, Gülşah YILDIZOĞLU, Ömer UZUN Boğaziçi University, CMPE, May 2010.
Get to Know Your Keyboard. Operational Keys Escape (Esc) – allows you to exit unwanted menus and dialog boxes Tab – used to indent; moves the cursor 5.
Keystroke Biometric System Client: Dr. Mary Villani Instructor: Dr. Charles Tappert Team 4 Members: Michael Wuench ; Mingfei Bi ; Evelin Urbaez ; Shaji.
User Authentication Using Keystroke Dynamics Jeff Hieb & Kunal Pharas ECE 614 Spring 2005 University of Louisville.
Downloading and Installing Autodesk Revit 2016
Unit 1. Alternate Key Also called ALT key Executes commands with other key(s)
Downloading and Installing Autodesk Inventor Professional 2015 This is a 4 step process 1.Register with the Autodesk Student Community 2.Downloading the.
Validation final steps Stopping gaps being entered in an input.
Copy of the from the secure website - click on the AccoridaLife.zip link.
Microsoft Excel 2002—The Basics Presented by: Kyle Kuehler Instructional Technology Specialist (806)
Instructions As the slides are displayed, discuss each slide to promote the correct keyboarding position and the proper use of various keys on the keyboard.
1. 2 Living Spaces 3 4 template
COMPUTER INPUT DEVICE Keyboard. Keyboard cont…… Print Screen Print contents of screen Pause/Break Terminate/Interrupt Scroll Lock Modify behavior of the.
Standard Input Devices
1.4 Keyboard Training.
3.3 Fundamentals of data representation
Computer Literacy BASICS
Keyboarding Slideshow
CSCE 3110 Data Structures & Algorithm Analysis
Keystroke Biometric Studies
Computer-User-Input Behavioral Biometrics The Biometrics we focus on at Pace University Dr. Charles C. Tappert Seidenberg School of CSIS, Pace University.
Keystroke Biometric Studies with Short Numeric Input on Smartphones
A Seminar Report On Face Recognition Technology
Microsoft Excel A Spreadsheet Program.
FACE RECOGNITION TECHNOLOGY
MANIPULATING TEXT WITHIN AND BETWEEN DOCUMENTS
GETTING TO KNOW YOUR KEYBOARD
How I can save keystrokes?
Basic Computing for Teachers
Document Processing Part 2
Creating a Worksheet and an Embedded Chart
Keystroke Biometric Studies with Short Numeric Input on Smartphones
1.4 Keyboard Training Keyboard Training.
An Introduction to Word Processing
Introduction to C++ Programming
Keystroke Biometric System
Benchmark Series Microsoft Word 2016 Level 2
Formatting and Editing Skills
Dynamic Authentication of Typing Patterns
Using Access More Efficiently
Moving the Insertion Point
Word Lesson 1 Word Basics
Microsoft Excel 2007 – Level 1
Year 9 Entry Level Computing
1 Word Processing Part I.
Keyboarding Vocabulary
University of Warith AL-Anbiya’a
ASCII LP1.
Microsoft Excel 2007 – Level 2
ASCII and Unicode.
Day 2: Improving the Appearance of Document and Using Myanmar Fonts
KEYBOARDING KEY TERMS.
Keyboarding Vocabulary
Keystroke Biometric Studies with Short Numeric Input on Smartphones
Presentation transcript:

Long-Text Keystroke Biometric Applications over the Internet Gary Bartolacci, Mary Curtin, Marc Katzenberg, Ngozi Nwana, Sung-Hyuk Cha, and Charles Tappert Pace University, New York

2 Keystroke Biometric As with other biometrics, the keystroke one is becoming important for security apps As with other biometrics, the keystroke one is becoming important for security apps Advantage - inexpensive and easy to implement, the only hardware needed is a keyboard Advantage - inexpensive and easy to implement, the only hardware needed is a keyboard Disadvantage - behavioral rather than physiological biometric, easy to disguise Disadvantage - behavioral rather than physiological biometric, easy to disguise One of the least studied biometrics One of the least studied biometrics

3 Focus of Study Previous studies mostly concerned short character string input Previous studies mostly concerned short character string input Password hardening Password hardening Short name strings Short name strings We focus on large text input We focus on large text input 200 or more characters per sample 200 or more characters per sample

4 Focus of Study (cont) Applications of interest Applications of interest Identification Identification 1-of-n classification problem 1-of-n classification problem e.g., sender of inappropriate in a business environment with a limited number of employees e.g., sender of inappropriate in a business environment with a limited number of employees Verification Verification Binary classification problem, yes/no Binary classification problem, yes/no e.g., student taking online exam e.g., student taking online exam

5 Software Components Raw Keystroke Data Capture over the Internet (Java applet) Raw Keystroke Data Capture over the Internet (Java applet) Feature Extraction Feature Extraction Classification Classification Training Training Testing Testing

6 Keystroke Data Capture (Java Applet) Raw data recorded for each entry Key’s character Key’s character Key’s code text equivalent Key’s code text equivalent Key’s location on keyboard Key’s location on keyboard 1 = standard, 2 = left, 3 = right 1 = standard, 2 = left, 3 = right Time key was pressed (msec) Time key was pressed (msec) Time key was released (msec) Time key was released (msec) Number of left, right, double mouse clicks Number of left, right, double mouse clicks

7 Keystroke Data Capture (Java Applet)

8 Example of Aligned Raw Data File (Hello World!)

9 Feature Measurements 10 Mean and 10 Std of key press durations 10 Mean and 10 Std of key press durations 8 most frequent alphabet letters (e, a, r, i, o, t, n, s) 8 most frequent alphabet letters (e, a, r, i, o, t, n, s) Space & shift keys Space & shift keys 10 Mean and 10 Std of key transitions 10 Mean and 10 Std of key transitions 8 most common digrams (in, th, ti, on, an, he, al, er) 8 most common digrams (in, th, ti, on, an, he, al, er) Space-to-any-letter & any-letter-to-space Space-to-any-letter & any-letter-to-space 15 Total number of keypresses for 15 Total number of keypresses for Space, backspace, delete, insert, home, end, enter, ctrl, 4 arrow keys combined, shift (left), shift (right), total entry time, left, right, & double mouse clicks Space, backspace, delete, insert, home, end, enter, ctrl, 4 arrow keys combined, shift (left), shift (right), total entry time, left, right, & double mouse clicks

10 Feature Measurement Sample

11 Feature Extraction Preprocessing Outlier removal Outlier removal Remove samples > 2 std from mean Remove samples > 2 std from mean Prevents skewing of features caused by pausing of the keystroker Prevents skewing of features caused by pausing of the keystroker Standardization Standardization x’ = (x - xmin) / (xmax - xmin) x’ = (x - xmin) / (xmax - xmin) Scales to range 0-1 to give roughly equal weight to each feature Scales to range 0-1 to give roughly equal weight to each feature

12 Classification Identification Identification Nearest neighbor classifier using Euclidean distance Nearest neighbor classifier using Euclidean distance Input sample compared to every training sample Input sample compared to every training sample

13 Experimental Design: Identification Experiment 10 subjects (8 completed) that know the purpose of the input data 10 subjects (8 completed) that know the purpose of the input data Training – 10 reps of text a (approx. 600 char) Training – 10 reps of text a (approx. 600 char) Testing Testing Leave-one-out method on text a, 1 versus 9 Leave-one-out method on text a, 1 versus 9 10 reps of text b (same length as text a) 10 reps of text b (same length as text a) 10 reps of text c (half length of text a) 10 reps of text c (half length of text a) 28 subjects that don’t know purpose of the input data 28 subjects that don’t know purpose of the input data Subset of above training/testing data Subset of above training/testing data Also, arbitrary text input of reasonable length Also, arbitrary text input of reasonable length

14 Experimental Design: Instructions for Subjects Make any necessary corrections to the input data Make any necessary corrections to the input data Leave at least a day between entering samples Leave at least a day between entering samples Input the data using your normal keystroke dynamics (only for subjects that know purpose of the input data) Input the data using your normal keystroke dynamics (only for subjects that know purpose of the input data)

15 Experimental Design: Text a – about 600 characters This is an Aesop fable about the bat and the weasels. A bat who fell upon the ground and was caught by a weasel pleaded to be spared his life. The weasel refused, saying that he was by nature the enemy of all birds. The bat assured him that he was not a bird, but a mouse, and thus was set free. Shortly afterwards the bat again fell to the ground and was caught by another weasel, whom he likewise entreated not to eat him. The weasel said that he had a special hostility to mice. The bat assured him that he was not a mouse, but a bat, and thus a second time escaped. The moral of the story: it is wise to turn circumstances to good account. This is an Aesop fable about the bat and the weasels. A bat who fell upon the ground and was caught by a weasel pleaded to be spared his life. The weasel refused, saying that he was by nature the enemy of all birds. The bat assured him that he was not a bird, but a mouse, and thus was set free. Shortly afterwards the bat again fell to the ground and was caught by another weasel, whom he likewise entreated not to eat him. The weasel said that he had a special hostility to mice. The bat assured him that he was not a mouse, but a bat, and thus a second time escaped. The moral of the story: it is wise to turn circumstances to good account.

16 Results: Different Samples of the Same Text Predicted Actual 100 % accuracy (76 out of 76) Confusion Matrix of Results (leave-one- out method) 

17 Results: Different Text of Equal Length (text b) Predicted Actual 98.5 % accuracy (65 out of 66) Confusion Matrix of Results 

18 Results: Different Text of Shorter Length (text c) Predicted Actual 97% accuracy (74 out of 76) Confusion Matrix of Results 

19 Analysis of Results Accuracy on text a > that on text b Accuracy on text a > that on text b text a is the training text text a is the training text Accuracy on text b > that on text c Accuracy on text b > that on text c text b is longer than text c text b is longer than text c

20 Conclusions System is a viable means of differentiating between individuals based on typing patterns System is a viable means of differentiating between individuals based on typing patterns It is likely that the shorter the text used for verification, the lower the accuracy It is likely that the shorter the text used for verification, the lower the accuracy Decreasing the number of measurements used also decreases accuracy Decreasing the number of measurements used also decreases accuracy

21 Experiments in Progress Identification experiment with subjects that don’t know the purpose of the input data Identification experiment with subjects that don’t know the purpose of the input data Verification experiments Verification experiments

22 Questions/Comments?