Computational Intelligence - February 2017 - 18

watchlist technologies, this paper suggests a novel model and
criteria for the evaluation of watchlists for e-borders, and a
technology for assessing the risks of watchlists using Bayesian
inference. Conceptually, this paper contributes to developing
a next generation of biometric-enabled watchlists for mass
public hubs, such as e-borders. Our results are introduced as
follows. After specifying the objectives and providing a brief
background (Section II), we introduce a taxonomy and a
model of watchlist technology (Section III). The single- and
double-phase inference are explained in Sections IV and V.
II. Background

There is a close relationship between forensic expertise and
automated border control tasks such as checking the document
authenticity and verifying the biometric templates stored in the
traveler's e-passport/ID. The proper technology must account
for age progression in recognition [15], [16], ensure the certainty of the traveler's biometric appearance (an individual can
change his/her evidence using plastic surgery [17], [18], color
lenses [19], or/and make-up [20]), and check the trustworthiness of the Advanced Passenger Information (API) which is
provided by the traveler about him/herself. This is enabled via a
search in government databases using the watchlist concept.
The watchlist is a mandatory component of e-borders
(Table 1). Legacy (non-biometric) watchlist practices are generally ineffective and have failed to counter contemporary terrorist threats [4], [5]. For example, in a real-world scenario, a
non-biometric watchlist, such as the Terrorist Identities Datamart Environment (TIDE) [12], is used. The e-border aims at
employing biometric-enabled technologies, and thus has to
deal with its efficiency. The problem addresses traveler authentication (in both identification and verification modes) using
facial images of insufficient-quality, such as legacy photos of
persons of interest stored in a watchlist, and traveler probe
images taken using mobile hand-held devices [12], [24], [25].
Ideally, the watchlist should contain synthetic facial images of
persons of interest constructed by composite machines [26].
The principles of watchlist design are formulated in each
country; an example is the U.S. Privacy Act (1974) [27] and
Canada's national security framework. Observance of these
principles and their particular interpretation is the focus of
governments and private institutions [5], [6], [28]. The three
elements of identity are distinguished: attributed identity
(name, date and place of birth), biometric identity (such as
face, iris, fingerprint, retina, DNA profile, gait, and dynamic
signature), and biographical identity (life events and how a
person interacts with structured society including details of
education and qualifications, employment history, registration
of marriage, mortgage account, and property ownership) [29].
When combining biometrics with other technologies, additional threats need to be analyzed and countered by appropriate security measures.
In automated border control machines, watchlist technologies are radically different from those known in homeland
security such as Entry-Exit systems for visitors, like U.S. VISIT

18

Ieee ComputatIonal IntellIgenCe magazIne | February 2017

[6], [30] and the European Union (EU) SmartBorders [7], [13],
[31], or those used in forensics [1], as well as in other applications [28]. The fundamental difference is the time constraints
for traveler risk assessment:
❏ Given a visitor to the country, his/her personal data for risk
profiling, including facial and fingerprint traits, is known to
the Entry-Exit system, including the data provided in the
visa application in the past.
❏ Given a traveler in an airport, his/her personal data for
authentication are provided only via scanning the passport,
thus limiting the possibilities for risk assessment (several
minutes for border crossing).
Biometric-enabled watchlists which have been explored for
a long time in Entry-Exit homeland security and visa technologies, are still not integrated in the automated border control
machines except for a few pilot projects in some countries.
This is due to a number of challenges such as the need of
enabling infrastructure, biometric-enabled passports/IDs, the
reliability of biometric traits, as well as privacy issues. If
matched against a watchlist, a traveler is directed to a special
control and may not be permitted to board a commercial
aircraft. For example, the Interpol Terrorism Watch List, a list
of fugitives and suspected terrorists, No Fly List contains people suspected of some involvement with terrorism. A watchlist
in e-borders is implemented as a specific purpose database
which includes selected personal data from national and international resources; this data is periodically updated. The primary goal of watchlist technology is to span national and
international institutions with varying terrorist countermeasures, policies, trust, and legal restrictions. A traveler can be
stopped at the phase of watchlist check for the following reasons: (a) watchlist matches, (b) misidentified as a person of
interest, or (c) someone mistakenly included him/her on the
watchlist. Misidentification may not only offend and hurt travelers (wrongly suspected as terrorists), but can also create a
bottleneck situation favorable for terrorist attacks. As a result of
the watchlist screening process, the travelers may complain that
they were adversely affected and seek relief. In mass-applications such as e-borders, government agencies involved in
watchlist screening have a redress process to resolve the complaint and respond to the complainant. The Redress Complaint Disposition (RCD) metric was developed by the U.S.
Terrorist Screening Center (TSC) [12], it is well suited for performance evaluation of the master-watchlist.
The key challenge of the contemporary watchlist architecture is that there is no centrally managed, host-oriented
watchlist system. Sharing unclassified biometric data with
other agencies having a counter-terrorism mission is a high
priority task [32]. This architecture was already proven, in particular, in military applications [5], [32], [33]. Contemporary
watchlist technological developments include, in particular, the
DHS's (Department of Homeland Security) ADVISE machine
[5], CAPPS, and Secure Flight, IDENT [34], FBI's IAFIS
(search capabilities for fingerprints, faces, irises, and palms, as
well as scars, marks, and tattoos [32]), DoD's ABIS, as well as



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