Deep Motion Masking for Secure, Usable, and Scalable Real-Time Anonymization of Ecological Virtual Reality Motion Data
2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW),
Год журнала:
2024,
Номер
unknown, С. 493 - 500
Опубликована: Март 16, 2024
Virtual
reality
(VR)
and
"metaverse"
systems
have
recently
seen
a
resurgence
in
interest
investment
as
major
technology
companies
continue
to
enter
the
space.
However,
recent
studies
demonstrated
that
motion
tracking
"telemetry"
data
used
by
nearly
all
VR
applications
is
uniquely
identifiable
fingerprint
scan,
raising
significant
privacy
concerns
surrounding
metaverse
technologies.
In
this
paper,
we
propose
new
"deep
masking"
approach
scalably
facilitates
real-time
anonymization
of
telemetry
data.
Through
large-scale
user
study
$(N=182)$
,
demonstrate
our
method
significantly
more
usable
private
than
existing
anonymity
systems.
Язык: Английский
Anonymization Techniques for Behavioral Biometric Data: A Survey
ACM Computing Surveys,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 18, 2025
Our
behavior
—the
way
we
talk,
walk,
act,
or
think—
is
unique
and
can
be
used
as
a
biometric
trait.
It
also
correlates
with
sensitive
attributes
like
emotions
health
conditions.
With
more
tracking
techniques
(e.g.
fitness
trackers,
mixed
reality)
entering
our
everyday
lives
of
captured
processed.
Hence,
to
protect
individuals’
privacy
against
unwanted
inferences
are
required,
before
such
data
To
consolidate
knowledge
in
this
area,
the
first
systematically
review
suggested
anonymization
for
behavioral
data.
We
taxonomize
compare
existing
solutions
regarding
goals,
conceptual
operation,
advantages,
limitations.
categorization
allows
comparison
across
different
traits.
traits
voice,
gait,
hand
motions,
eye
gaze,
heartbeat
(ECG),
brain
activity
(EEG).
analysis
shows
that
some
(e.g.,
voice)
have
received
much
attention,
while
others
activity)
mostly
neglected.
find
evaluation
methodology
further
improved.
Язык: Английский
CLOVR: Collecting and Logging OpenVR Data from SteamVR Applications
2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW),
Год журнала:
2024,
Номер
unknown, С. 485 - 492
Опубликована: Март 16, 2024
Due
to
the
growing
popularity
of
consumer
virtual
reality
(VR)
systems
and
applications,
researchers
have
been
investigating
how
tracking
interaction
data
from
VR
applications
can
be
used
for
a
wide
variety
purposes,
including
user
authentication,
predicting
cybersickness,
estimating
cognitive
processing
capabilities.
In
many
cases,
develop
their
own
collect
such
data.
some
prior
provided
open
datasets
custom
applications.
this
paper,
we
present
CLOVR,
tool
Capturing
Logging
OpenVR
any
application
built
with
API,
closed-source
games
experiences.
CLOVR
provides
an
easy-to-use
interface
collecting
OpenVR-based
It
supports
capturing
logging
device
poses,
actions,
microphone
audio,
views,
videos,
in-VR
questionnaires.
To
demonstrate
CLOVR's
capabilities,
also
six
single
experiencing
different
SteamVR
Язык: Английский
Effect of Data Degradation on Motion Re-Identification
Опубликована: Июнь 4, 2024
The
use
of
virtual
and
augmented
reality
devices
is
increasing,
but
these
sensor-rich
pose
risks
to
privacy.
ability
track
a
user's
motion
infer
the
identity
or
characteristics
user
poses
privacy
risk
that
has
received
significant
attention.
Existing
deep-network-based
defenses
against
this
risk,
however,
require
amounts
training
data
have
not
yet
been
shown
generalize
beyond
specific
applications.
In
work,
we
study
effect
signal
degradation
on
identifiability,
specifically
through
added
noise,
reduced
framerate,
precision,
dimensionality
data.
Our
experiment
shows
state-of-the-art
identification
attacks
still
achieve
near-perfect
accuracy
for
each
degradations.
This
negative
result
demonstrates
difficulty
anonymizing
gives
some
justification
existing
data-
compute-intensive
deep-network
based
methods.
Язык: Английский