Keystroke Biometric Recognition Studies on Long-Text Input Under Ideal and Application-Oriented Conditions

1
Keystroke Biometric Recognition Studies on
Long-Text Input Under Ideal andApplication-Orient
ed Conditions

• Mary Villani, Charles Tappert, and Sung-Hyuk Cha

2
Objective

• For long-text input of 600 keystrokes
• Determine the viability of the keystroke
  biometric two independent variables
• Different entry modes copy and free text
• Different keyboards desktop and laptop

3
Advantages of Keystroke Biometric

• Keyboards commonly used
• Not intrusive
• Inexpensive
• Can Frequently Re-authenticate the User

4
Keystroke Biometric System Components

• Data Capture Applet
• Feature Extractor
• Pattern Classifier

5
Data Capture Applet
6
Sample Raw Feature Data
Sample Raw Feature Data File Hello World
7
239 Feature Measurements

• 78 Key Press Duration Measures
• (39 means and 39 standard deviations)
• 70 Key Transition Type 1 Measures
• (35 means and 35 standard deviations)
• 70 Key Transition Type 2 Measures
• (35 means and 35 standard deviations)
• 21 Other Measures (percentages and rates)

8
Type 1 and 2 Transition Measures
9
Key Press Duration Features and Fallback
Hierarchy
Hierarchy tree for the 39 duration features (each
oval), each represented by a mean and a standard
deviation.
10
Key Transition Featuresand Fallback Hierarchy
Hierarchy tree for the 35 transition features
(each oval), each represented by a mean and a
standard deviation for each of the type 1 and
type 2 transitions.
11
Fallback for Few Samples

• Mean and Standard Deviation Computation when
  number of samples n(i) is less than
  kfallback-threshold
• Similar to NLP backoff statistics for n-grams

12
Two Preprocessing Steps

• Outlier removal
• Remove samples gt 2s from µ
• Prevents feature skewing from pauses
• Standardization
• Scales to range 0-1 to give roughly equal weight
  to each measure

13
Pattern Classifier

• Nearest Neighbor Classifier using Euclidean
  Distance

14
Experimental DesignSix Main Experiments per Six
Arrows
15
Experimental DesignKeyboards (independent
variable 1)

• Desktop Keyboards mostly (100) Dell desktops
  in a classroom environment
• Laptop Keyboards about 90 Dell laptops, some
  IBM, HP, Apple
• (greater variety of laptop
• than desktop keyboards)

16
Experimental DesignInput Modes (independent
variable 2)

• Copy Task Input specified text of about 600
  keystrokes corrections
• Free Text Input creation of arbitrary emails
  (at least 600 keystrokes)

17
Subject Participation
18
Participation By Experiment Each subject entered
5 texts in at least two quadrants A total of 36
participated in all four quadrants
Desktop
Laptop





1
52 Subjects
Copy
4
3
5
40 Subjects
47 Subjects
93 Subjects
Free Text
41 Subjects
6






2
40 Subjects
19
Five Sub Experiments for Each of the Six Arrows
d e
b
a
c

• a. Training testing on data in quadrant at
  first end of arrow (leave-one-out procedure)
• b. Training testing on data in quadrant at
  second end of arrow (leave-one-out procedure)
• c. Combining data at each arrow end
  (leave-one-out procedure)
• d. Training on first end testing on second
• e. Training on second end testing on first

20
Results Experiment 1 36 subjects participated in
all quadrants
21
Results Experiment 2 36 subjects participated in
all quadrants
22
Results Experiment 3 36 subjects participated in
all quadrants
23
Results Experiment 4 36 subjects participated in
all quadrants
24
Results Experiment 5 36 subjects participated in
all quadrants
25
Results Experiment 6 36 subjects participated in
all quadrants
26
36 Subject Summary
27
All Subject SummarySupports 36 Subject Results
28
Conclusions

• Best accuracies for same keyboard and same input
  mode
• Accuracy dropped significantly for different
  keyboards or for different input modes
• Accuracy for different input modes better than
  accuracy for different keyboards
• Accuracy for copy mode somewhat better than
  accuracy for free-text mode
• Accuracy decreased as the number of subjects
  increased

29
Long-Text Input Applications

• Identify the author of inappropriate email and
  possibly even IM
• Authenticate the student taking online exams

30
Future Work

• Try more sophisticated classifiers
• Neural Networks
• Support Vector Machines
• Explore the data with data mining

31
Questions?

• Thank you