Answered step by step
Verified Expert Solution
Link Copied!

Question

1 Approved Answer

Exercise 4 Evaluating performance of a mock biometric - based authentication system Imagine you are using a biometrics - based user authentication system and would

Exercise 4 Evaluating performance of a mock biometric-based authentication system
Imagine you are using a biometrics-based user authentication system and would like to evaluate its performance for a specific user (lets say, Alice). Below are some data you obtained from some earlier experiments:
For 100 biometric templates Alice produces for login attempts, the distance between those templates and the enrolled template of Alice is as follows:
[0.27,0.079,0.27,0.36,0.25,0.3,0.27,0.17,0.23,0.12,0.29,0.085,0.093,0.12,0,0.34,0.23,0.12,0.34,0.029,0.19,0.18,0.23,0.23,0.11,0.2,0.18,0.26,0.31,0.31,0.11,0.21,0.079,0.089,0.2,0.35,0.12,0.24,0.18,0.31,0.091,0.2,0.26,0.31,0.35,0.21,0.051,0.13,0.094,0.44,0.14,0.27,0.18,0.29,0.12,0.06,0.058,0.25,0.18,0.18,0.34,0.23,0.22,0.36,0.12,0.27,0.28,0.18,0.22,0.083,0.085,0.21,0.27,0.46,0.13,0.22,0.19,0.0067,0.16,0.021,0.28,0.11,0.21,0.15,0.23,0.14,0.25,0.27,0.37,0.18,0,0.12,0.34,0.093,0.3,0.21,0.34,0.0039,0.18,0.079]
For 100 biometric templates Eve (a mock attacker who pretended to impersonate Alice) produced, the distance between those templates and the enrolled template of Alice is as follows:
[1.2,0.77,0.88,0.39,0.51,0.55,0.82,0.54,0.74,0.19,0.53,0.44,0.28,0.7,0.66,0.61,0.33,0.83,0.67,0.54,0.6,0.55,0.25,0.54,0.43,0.4,0.37,0.49,0.2,0.79,0.7,0.6,0.59,0.44,0.8,0.57,0.46,0.87,0.56,0.48,0.54,0.43,0.38,1.1,0.93,0.66,0.35,0.43,0.56,0.76,0.33,0.13,0.31,0.67,0.68,0.69,0.57,0.64,0.5,0.77,0.33,0.69,0.43,0.53,0.71,0.81,0.38,0.85,0.73,0.59,0.56,0.56,0.54,0.6,0.61,0.77,0.91,0.69,0.56,0.73,0.64,0.39,0.79,0.66,0.63,0.7,0.65,0.41,0.57,0.57,0.49,0.94,0.42,0.5,0.46,0.37,0.56,0.55,0.91,0.55]
Based on these data, now you need to calculate how to set a threshold to accept Alice with a small false reject rate (FRR) and reject Eve with a small (if not zero) false accept rate (FAR).
Pick up a number of typical threshold values between the means of Alices and Eves distance values, write a programme to calculate the FAR and FRR. Observe how they change with respect to the value of the threshold. A recommended set of thresholds are [0.25,0.3,0.35,0.4,0.45,0.5,0.55].
2
Hint 1: A smaller distance means two templates being more similar. Assume a user will be accepted if the distance is smaller (<) than the threshold, but will be rejected if greater than or equal to (>=) the threshold. Moving the equal to(=) to the former will change the results to some extent but not significantly.
Hint 2: If you are really struck with writing a program to do this exercise, use Excel to do the calculation instead.

Step by Step Solution

There are 3 Steps involved in it

Step: 1

blur-text-image

Get Instant Access to Expert-Tailored Solutions

See step-by-step solutions with expert insights and AI powered tools for academic success

Step: 2

blur-text-image

Step: 3

blur-text-image

Ace Your Homework with AI

Get the answers you need in no time with our AI-driven, step-by-step assistance

Get Started

Recommended Textbook for

Select Healthcare Classification Systems And Databases

Authors: Katherine S. Rowell, Ann Cutrell

1st Edition

0615909760, 978-0615909769

More Books

Students also viewed these Databases questions

Question

11.13. Derive Eq. (11.55).

Answered: 1 week ago

Question

What is the average age of members of your key public?

Answered: 1 week ago

Question

How likely is this public to act on information it receives?

Answered: 1 week ago

Question

What does this public think about your organization?

Answered: 1 week ago