Chapter 9 Creating and Maintaining Database

1
Chapter 9Creating and Maintaining Database

• Presented by Zhiming Liu
• Instructor Dr. Bebis

2
Outline

• Introduction
• Enrollment Policies
• The Zoo
• Biometric Sample Quality Control
• Training
• Enrollment Is System Training

3
Introduction

• Biometric enrollment asks an individual to give
  out private information.
• Enrollment is a process directed by some
  enrollment policy, which needs to be acceptable
  to the public.
• Positive enrollment under enrollment policy EM,
  select trusted individuals and store machine
  representation of these m enrolled members in a
  verification database M.

4
Introduction

• Negative enrollment for criminal identification
  systems, under enrollment policy EN, determine
  the undesirable individuals and store machine
  representations of the n selected individuals in
  the screening database N.
• Because of error and fraud, there are fake and
  duplicate identities in legacy databases.

5
Introduction

• - A fake identity can be one of two cases,
  created and stolen identities
• 1. Created identity some subject d enrolls in
  M as dK using documents for a nonexistent
  identity, either fake documents or fake ID.
• 2. Stolen identity a fake identity can also
  be a falsely enrolled subject dK as subject dK,
  the stolen identity.
• - A duplicate identity
  IB
• 
  Subject A duplicate
• 
  IA

6
Enrollment policies

• Positive enrollment this is a process of the
  registration of M trusted subjects dm in database
  M. The enrollment could be based on some already
  enrolled population W.
• Negative enrollment is a process of
  registration of N questionable subjects dn by
  storing machine descriptions of these subjects in
  database N, which contains much more specific and
  detailed descriptions.

7
Enrollment policies

• Social issues
• - How to make biometric authentication work
  without creating additional security loopholes,
  and without damaging civil liberties?
• - Who will administer and maintain databases
  of authorized subjects?
• - How will the data integrity of these
  databases be protected?

8
The zoo

• Apply animals to subject categories, depend on
  whether one subject is easy to authenticate or
  not.
• - Sheep The group of subjects that dominate
  the population are easy to authenticate because
  their real-world biometric is very distinctive
  and stable.
• - Goats The group of subjects that are
  particularly difficult to authenticate because of
  a poor real-world biometric that is not
  distinctive, perhaps due to physical damage to
  body parts or due to large spurious variability
  in the biometric measurements over time.
• This is the portion of the population that
  generates the majority of False Rejects.

9
The zoo

• - Lambs These are the enrolled subjects who
  are easy to imitate.
• Lambs are the cause of most
  False Accepts because they
• are imitated by wolves.
• - Wolves These are subjects that are
  particularly good at imitating,
• impersonating, or forging a
  particular biometric.
• - Chameleons These are the subjects who are
  both easy to imitate
• and good at imitating
  others.
• They are a source of
  passive False Accepts when enrolled
• and of active False Accepts
  when being authenticated.

10
The zoo
11
Biometric sample quality control

• Many random False Rejects/Accepts occur because
  of adverse signal acquisition situations.
• - two solutions

12
Biometric sample quality control

• - for example, apply image enhancement or
  suggest subjects
• present the biometric in a different,
  better way.
• - Failure to Enroll (FTE)
• Input quality control
  higher FTE rates
• Low-quality samples lower
  FTE rates
• - Relationship with ROC
• lower FTE higher FAR and FRR
  

13
Biometric sample quality control
14
Training

• Why does a biometric system need to be trained?
• - Compute match score s(B, B).
• - The goal is to make the average difference
  between these match
• scores and mismatch scores as high as
  possible.
• There are two aspects to training
• - Enrollment policies and authentication
  protocols

15
Training

• 1. Enrollment of subjects During enrollment one
  or more samples B of a subjects biometric ß are
  acquired and biometric samples or templates
  derived from the samples B are stored in some
  database M.
• 2. Protocols A biometric authentication system
  itself needs to be trained, by refining and
  enhancing the signal or image to match the user
  population characteristics and incrementally
  improving the match engine.

16
Training
17
Enrollment is system training

• Build database M by selecting subjects d from the
  world population W and assigning an identifier ID
  to each subject.

18
Enrollment is system training

• Three possibilities
• 1. Correctly linked, ID k
• 2. Subject dk is in reality a subject dj, with j
  lt k, i.e., dk is duplicate of subject dj. As a
  result, IDj and IDk are duplicates, representing
  the same individual.
• 3. Subject dk is in reality a subject dj, with j
  gt k, i.e., dk is faking unenrolled subject dj. As
  a result, IDk corresponds to a fake identity.

19
Enrollment is system training

• We have non-zero probabilities
• - PD is the probability that some subject d ? M
  is also enrolled under a different ID number
• - PF is the probability that subject d ? M
  is a fake identity
• Database integrity
• - Integrity how well the database reflects the
  truth data of the seed documents (birth
  certification, proofs of citizenship, and
  passports) used for enrollment

20
Enrollment is system training

• The database integrity when it comes to
  duplicates is determined by PD , the probability
  of duplicates
• - PDEA (Double Enroll Attack) refers to the
  probability that an already enrolled subject dj
  wishes to re-enroll in the database as a
  different identity dk.
• - FNMRE is the probability that a match between
  two samples of the same biometric is not
  detected, i.e., is missed.
• - The number of duplicates in M is PD m, with
  m the number of entities in M

21
Enrollment is system training

• The enrollment integrity is further determined by
  PF, the probability of a fake enroll as dk
• - FMRE is the probability that a match between
  two different biometric samples is falsely
  declared during enrollment
• - PIA is the probability of impersonation attack
• - The number of fake identities in M equals PF
  m

22
Enrollment is system training

• Probabilistic enrollment
• - build an access control list of subjects di, i
  1,,m of some database M.
• - association between di and the
  corresponding biometric ßi
• - compute likelihood
• it expresses how well a subjects
  biometric ßi match his template Bi
• - probability can only be computed if there
  exist some machine representation of real word
  biometrics ßi , let these representations be
  another set of templates and write

23
Enrollment is system training

• where, for simplicity, we assume that the
  match score
• is the likelihood that di is the true subject,
  given Bi
• Modeling the world
• - Prob (di Bi) can be approximated by match
  score si only under very unrealistic
  circumstances.
• - more realistic approximations will have to
  involve the modeling of other subjects dk
  enrolled in M, more generally, compute Prob (di
  O)
• the likelihood of subject di given the
  biometric data O collected at enrollment time

24
Enrollment is system training

• - Prob (O) is the prior probability that this
  particular observation will occur (which cannot
  be computed exactly)
• - assume Prob (di) Pd is constant
• - evaluate Prob (Odi) is a matter of
  fitting model di to the data O and determine how
  well this can be done.
• - evaluating the rest of this expression Prob
  (Odk) k j1,, m is impossible, because these
  subjects are not available upon dj enrollment

25
Enrollment is system training

• Modeling the rest of the world cohorts
• - the most difficult issue in training a
  biometric authentication system is the modeling
  of data from unknown people.
• - voice verification methods not only use a
  model describing the speakers biometric machine
  representation, but also a model describing all
  other speakers.
• - two techniques to approximate the denominator
  of (9.7)

26
Enrollment is system training
1. World modeling

• - reduce the set M to one fictitious model
  subject D, trained on a pool of data from many
  different speakers, who represent the world W
  of possible speakers.
• - factor , so that the
  denominator reflects the whole population D di
  

27
Enrollment is system training
2. Cohort modeling

• - approximate the set M by a subset Mi that
  resemble subject di . for each subject di , a set
  of approximate forgeries is computed and stored.
  We denote this set by Di the set is called the
  set of cohorts of speaker i.
• - factor ?i ci, the number of cohorts for di

28
Enrollment is system training

• Updating the probabilities
• - denote Prob (di O) with Pi
• - during operation of the authentication system,
  data from subjects is collected and likelihood Pi
  could be updated.
• - upon authentication of subject di , a
  biometric sample is acquired that we denote here
  as ?O.
• - compute Prob (di O, ?O)

29
Enrollment is system training

• - what needs to be evaluated is the denominator
  Prob (?O)
• - set Prob (di) Pi

30
Enrollment is system training