Deepfake Detection in Super-Recognizers and Police Officers
IEEE Security & Privacy,
Journal Year:
2024,
Volume and Issue:
22(3), P. 68 - 76
Published: March 26, 2024
We
examined
human
deepfake
detection
performance
(DDP)
in
relation
to
face
identity
processing
ability
among
Berlin
Police
officers,
including
Super-Recognizers
(SRs).
While
we
find
no
relationship,
further
research
into
DDP
using
state-of-the-art
static
deepfakes
is
needed
establish
the
potential
value
of
SR-deployment.
Language: Английский
The role of expansion and adaptability of face-space for individual differences in face identity processing
Royal Society Open Science,
Journal Year:
2025,
Volume and Issue:
12(1)
Published: Jan. 1, 2025
Individuals
can
strongly
vary
in
their
ability
to
process
face
identity.
Understanding
the
mechanisms
driving
these
differences
is
important
for
theoretical
development,
and
clinical
applied
contexts.
Here
we
investigate
role
of
face-space
properties
relation
individual
identity
processing
skills.
We
consider
two
fundamental
face-space:
expansion
(how
distant
from
each
other
similar
faces
are
located
such
space)
adaptability
(the
degree
which
distances
change
over
time).
Fifty-two
participants
performed
a
detection
task,
with
systematically
varying
location
face-space,
comprehensive
test
battery.
replicate
previous
results
indicating
advantage
typical,
as
compared
distinctive
faces.
Critically,
find
that
neither
our
measure
nor
related
abilities.
While
future
studies
might
benefit
use
more
sensitive
measures
properties,
suggest
examined
here
do
not
contribute
abilities
suggest.
Language: Английский
Deepfake Detection in Super-Recognizers and Police Officers
Published: Jan. 13, 2024
The
present
study
is
the
first
empirical
investigation
of
relationshion
between
human
deepfake
detection
performance
(DDP)
and
individuals'
face
identity
processing
ability.
Using
videos
from
Deepfake
Detection
Challenge,
we
investigated
DDP
in
two
unique
observer
groups:
Super-Recognizers
(SRs)
"normal"
officers
within
18K
members
Berlin
Police.
SRs
were
identified
either
via
previously
proposed
lab-based
procedures
or
only
existing
tool
for
SR
identification
involving
increasingly
challenging,
authentic
forensic
material:
Test
For
Super-Recognizer
Identification
(beSure®).
Participants
judged
pairs
videos,
single
a
2-alternative
forced-choice
decision
setting
(i.e.,
which
pair,
whether
video
was
not).
We
explored
speed-accuracy
trade-offs,
compared
lab-identified
non-SRs,
police
as
function
their
independently
measured
(FIP)
Interestingly,
found
no
relationship
FIP
Further
work
using
static
deepfakes
created
with
current
state-of-the-art
generative
models
needed
to
determine
value
deployment
law
enforcement.
Language: Английский
The role of expansion and adaptability of face-space for individual differences in face identity processing
Published: Feb. 2, 2024
Individuals
can
strongly
vary
in
their
ability
to
process
face
identity.
Understanding
the
mechanisms
driving
these
differences
is
important
for
theoretical
development,
and
clinical
applied
contexts.
Here
we
investigate
role
of
face-space
properties
relation
individual
identity
processing
skills.
We
consider
two
fundamental
face-space:
expansion
(how
distant
from
each
other
similar
faces
are
located
such
space)
adaptability
(the
degree
which
distances
change
over
time).
Fifty-two
participants
performed
a
detection
task,
with
systematically
varying
location
face-space,
comprehensive
test
battery.
replicate
previous
results
indicating
advantage
typical,
as
compared
distinctive
faces.
Critically,
find
that
our
measure
not
related
abilities.
However,
one
revealed
medium
performers
exhibit
larger
adaptation
than
high
or
low
performers.
This
pattern
seems
be
especially
driven
by
tapping
into
long-term
memory
While
future
studies
might
benefit
use
more
sensitive
measures
properties,
suggest
perceptual
adaptation,
rather
expansion,
may
contributor
memory.
Language: Английский
Unique traits, computational insights: studying Super-Recognizers for societal applications
Published: Nov. 29, 2023
Nearly
fifteen
years
ago,
the
term
Super-Recognizer
(SR)
was
introduced
in
scientific
literature
as
a
result
of
an
accidental
finding.
Since
then,
there
has
been
surging
interest
topic
—
both
from
within
research
community,
well
international
media
and
(mostly
European)
law
enforcement.
Given
hype
hope
around
SRs,
review
our
current
understanding
their
ability
is
needed.
I
findings
outline
future
avenues
for
SR
work,
which
extend
beyond
advancing
human
cognition.
The
“face
recognition”
attracts
attention
various
stakeholders,
often
with
opposing
views
interests,
including
e.g.
NGOs,
policy
makers,
media,
industry,
who
are
mostly
not
involved
fundamental
research.
Therefore,
science
SRs
can
serve
entry
point
to
facilitate
societally
relevant
discussions,
neurodiversity,
right
privacy
security.
This
opportunity
comes
responsibility
adopt
highest
standards
terms
rigor
transparency,
ensure
that
high
quality,
participatory
inclusive
disseminated
honestly
broadly.
Language: Английский