Computational Intelligence - February 2017 - 19

IATA's strategic vision [35] and technology provider horizon,
such as [36]. For example, ADVISE aims at finding and tracking relationships in data available about the traveler [5]. It
refers to adapting the screening process to particular attributes
of the traveler.
Identification of a person of interest in social media is studied in [37]. E-personation is defined as the impersonation of
another person or entity through electronic means. E-personation leads to serious national threats. Practice suggested that
the efficiency of watchlists can be improved by adding the context information to the biometric template.
The increasing role of behavior biometrics defines a current
trend in e-borders. This includes the AVATAR interview supporting machine [38]. The core of these machines is known in
forensics such as the Concealed Information Test (CIT) that
uses eye tracking, vocalic, and face expressions [39].
III. Taxonomy of Watchlist Technology

In order to build a detailed watchlist model, we need to create a technological model and taxonomical description of
the watchlist.
A. Model

The concept of the watchlist is implemented by various techniques such as evidence accumulation from physical and virtual sources, an updating mechanism, a watchlist check for a
given traveler, and a policy for risk assessment (Table 1).
Figure 1 provides a graphical interpretation of these functions.
In this model, available information about the person of interest is gathered from the physical and digital world, analyzed,
processed, and distributed between government institutions.
For example, agency A1 initiates the gathering of information
about an individual of interest using both physical (biometric
templates of real persons) and virtual sources (information
from social networks). This information can be extended and
corrected by agencies A2 and A3 before sending it to the
database of border agency A4. This information is now called
the watchlist. The number of agencies (databases) is called the
depth of embedding of the watchlist in social infrastructure.
Given a traveler, the mobile authentication station checks
his/her physical evidence via handheld devices and makes a
decision: either continue to the border passage (OUT) or
direct to the manual control (STOP). In the case of manual
control, information about the traveler on a watchlist can be
updated on the request of a border officer.
B. Taxonomy Criteria

Conceptually, a watchlist is a specific-purpose technology for
traveler risk assessment which should be analyzed and evaluated
using the following criteria: (a) sources of information, their
reliability and credibility, (b) biases including vulnerability, and
(c) performance metrics. The proposed taxonomical view is
characterized by:
a) Sources of personal information, such as national and
international databases [4], and virtual sources (media and

social networks). An example of source evaluation methodology is the Admiralty Code metric [40].
b) Biases and vulnerabilities of the watchlist including
impersonation bias, social bias (e-borders is an integrated
part of the country), and the risks of service degradation,
are called service bias. Vulnerabilities are caused by technological factors [41], attacks, such as enforced impersonation [42], plastic surgery [18], spoofing [43], as well
as the leakage of information due to a Trojan or electromagnetic attack.
c) Performance metrics that characterize the operational
purposes of the watchlists using the notion of interoperability, response time, life cycle (theoretical, predicted or
vendor reported, and operational or real performance) [9],
as well as the reliability and credibility of sources and
information. For example, the RCD performance metric
is based on the paradigm of traveler offense [12].
The number of transactions per day is a system characteristic for a watchlist. For example, the DHS managed over
160,000 search queries a day (for visas, visitors, naturalization,
etc.) [32]. In addition to the known RCD measures of watchlist efficiency, we defined the following performance metrics:
the throughput (the number of served travelers per hour), the
operational reject rate (expressed as "one in N travelers (1: N )
is wrongly directed to special control"), and the life-cycle performance assessment which combines the theoretical (algorithmic limit), the predicted (vendor-reported), and the operational
(real) performance assessments.
In biometric-enabled technologies, performance is also
affected by the chosen biometrics which are defined as physiological or behavioral traits of humans. In e-borders, the
preferable traits include face, fingerprint, and iris biometrics
[44], [45]. In this paper, we use facial biometrics for conducting our experiments.
Contemporary techniques for face recognition in controlled conditions and cooperative users provide acceptable
results for e-borders. Useful statistics for face recognition in
authentication gates are introduced in [46]. However, many
challenges for face recognition exist, such as uncontrolled
environments [24], [33], [37]. Ideally, watchlists should include
various biometric modalities and supporting identity information [1], [32], and mechanisms for age progression and regression [15], [16].
IV. Single-Phase Watchlist Inference

Watchlist inference can be implemented as a single-phase and
two-phase process. Single-phase inference assumes a cooperative traveler who follows the regulations when biometric traits
are acquisitioned. In this section, we show that even in the ideal
conditions of a cooperative traveler, there are also risks of the
watchlist check being wrong.
A. Inference Engine

The core of watchlist technology is to establish the relationship
among a set of unobservable causes of the traveler (risk factors)

February 2017 | Ieee ComputatIonal IntellIgenCe magazIne

19



Table of Contents for the Digital Edition of Computational Intelligence - February 2017

Computational Intelligence - February 2017 - Cover1
Computational Intelligence - February 2017 - Cover2
Computational Intelligence - February 2017 - 1
Computational Intelligence - February 2017 - 2
Computational Intelligence - February 2017 - 3
Computational Intelligence - February 2017 - 4
Computational Intelligence - February 2017 - 5
Computational Intelligence - February 2017 - 6
Computational Intelligence - February 2017 - 7
Computational Intelligence - February 2017 - 8
Computational Intelligence - February 2017 - 9
Computational Intelligence - February 2017 - 10
Computational Intelligence - February 2017 - 11
Computational Intelligence - February 2017 - 12
Computational Intelligence - February 2017 - 13
Computational Intelligence - February 2017 - 14
Computational Intelligence - February 2017 - 15
Computational Intelligence - February 2017 - 16
Computational Intelligence - February 2017 - 17
Computational Intelligence - February 2017 - 18
Computational Intelligence - February 2017 - 19
Computational Intelligence - February 2017 - 20
Computational Intelligence - February 2017 - 21
Computational Intelligence - February 2017 - 22
Computational Intelligence - February 2017 - 23
Computational Intelligence - February 2017 - 24
Computational Intelligence - February 2017 - 25
Computational Intelligence - February 2017 - 26
Computational Intelligence - February 2017 - 27
Computational Intelligence - February 2017 - 28
Computational Intelligence - February 2017 - 29
Computational Intelligence - February 2017 - 30
Computational Intelligence - February 2017 - 31
Computational Intelligence - February 2017 - 32
Computational Intelligence - February 2017 - 33
Computational Intelligence - February 2017 - 34
Computational Intelligence - February 2017 - 35
Computational Intelligence - February 2017 - 36
Computational Intelligence - February 2017 - 37
Computational Intelligence - February 2017 - 38
Computational Intelligence - February 2017 - 39
Computational Intelligence - February 2017 - 40
Computational Intelligence - February 2017 - 41
Computational Intelligence - February 2017 - 42
Computational Intelligence - February 2017 - 43
Computational Intelligence - February 2017 - 44
Computational Intelligence - February 2017 - 45
Computational Intelligence - February 2017 - 46
Computational Intelligence - February 2017 - 47
Computational Intelligence - February 2017 - 48
Computational Intelligence - February 2017 - 49
Computational Intelligence - February 2017 - 50
Computational Intelligence - February 2017 - 51
Computational Intelligence - February 2017 - 52
Computational Intelligence - February 2017 - 53
Computational Intelligence - February 2017 - 54
Computational Intelligence - February 2017 - 55
Computational Intelligence - February 2017 - 56
Computational Intelligence - February 2017 - Cover3
Computational Intelligence - February 2017 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202311
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202308
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202305
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202302
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202211
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202208
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202205
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202202
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202111
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202108
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202105
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202102
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202011
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202008
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202005
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202002
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201911
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201908
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201905
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201902
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201811
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201808
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201805
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201802
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter12
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall12
https://www.nxtbookmedia.com