IEEE Computational Intelligence Magazine - February 2023 - 19

in VR only than VR supported or nonVR),
general platform popularity (e.g.,
VR only received less positive ratings
than VR supported and non-VR), and
which content types are associated with
higher user ratings across platforms (e.g.,
Action and Music/Rhythm are most
positively rated in VR only). Our findings
ultimately provide a foundational
framework for future theoretical constructions
of classification systems based
on content, market, interactivity, sociality,
and service dependencies, which
underlay how consumer VR is currently
categorized. "
IEEE Transactions on Cognitive and
Developmental Systems
An End-to-End Spiking Neural Network
Platform for Edge Robotics: From
Event-Cameras to Central Pattern Generation,
by A. Lele, Y. Fang, J. Ting,
and A. Raychowdhury, IEEE Transactions
on Cognitive and Developmental
Systems, Vol. 14, No. 3, Sep. 2022,
pp. 1092-1103.
Digital Object Identifier: 10.1109/
TCDS.2021.3097675
" Learning to adapt one'sgaitwith
environmental changes plays an essential
role in the locomotion of legged robots
which remains challenging for constrained
computing resources and energy
budget, as in the case of edge-robots.
Recent advances in bio-inspired vision
with dynamic vision sensors (DVSs) and
associated neuromorphic processing can
provide promising solutions for end-toend
sensing, cognition, and control tasks.
However, such bio-mimetic closed-loop
robotic systems based on event-based
visual sensing and actuation in the form of
spiking neural networks (SNNs) have not
been well explored. In this work, we program
the weights ofa bio-mimetic multigait
central pattern generator (CPG) and
couple it with DVS-based visual data
processing to show a spike-only closedloop
robotic system for a prey-tracking
scenario. We first propose a supervised
learning rule based on stochastic weight
updates to produce a multigait producing
spiking-CPG (SCPG) for hexapod robot
locomotion. We then actuate the SCPG
to seamlessly transition between the gaits
for a nearest prey tracking task by incorporating
SNN-based visual processing for
input event-data generated by the DVS.
This for the first time, demonstrates the
natural coupling ofevent data flow from
event-camera through SNN and neuromorphic
locomotion. Thus, we exploit
bio-mimetic dynamics and energy advantages
ofspike-based processing for autonomous
edge-robotics. "
IEEE Transactions on Emerging
Topics in Computational
Intelligence
ES Attack: Model Stealing Against
Deep Neural Networks Without Data
Hurdles, by X. Yuan, L. Ding, L.
Zhang, X. Li, and D. O. Wu, IEEE
Transactions on Emerging Topics in
Computational Intelligence, Vol. 6,
No. 5, Oct. 2022, pp. 1258-1270.
Digital Object Identifier: 10.1109/
TETCI.2022.3147508
" Deep neural networks (DNNs)
have become the essential components
for various commercialized machine
learning services, such as Machine
Learning as a Service (MLaaS). Recent
studies show that machine learning
services face severe privacy threats -
well-trained DNNs owned by MLaaS
providers can be stolen through public
APIs, namely model stealing attacks.
However, most existing works undervalued
the impact of such attacks,
where a successful attack has to
acquire confidential training data or
auxiliary data regarding the victim
DNN. In this paper, we propose ES
Attack, a novel model stealing attack
without any data hurdles. By using
heuristically generated synthetic data,
ES Attack iteratively trains a substitute
model and eventually achieves a functionally
equivalent copy of the victim
DNN. The experimental results reveal
the severity of ES Attack: i) ES Attack
successfully steals the victim model
without data hurdles, and ES Attack
even outperforms most existing model
stealing attacks using auxiliary data in
terms of model accuracy; ii) most
countermeasures are ineffective in
defending ES Attack; iii) ES Attack
facilitates further attacks relying on
the stolen model. "
IEEE Transactions on Artificial
Intelligence
Smoothed Generalized Dirichlet: A
Novel Count-Data Model for Detecting
Emotional States, by F. Najar and N.
Bouguila, IEEE Transactions on Artificial
Intelligence, Vol. 3, No. 5, Oct.
2022, pp. 685-698.
Digital Object Identifier: 10.1109/
TAI.2021.3120043
" In this article, we propose novel
approaches to deal with the problem of
burstiness, the challenge of count-data
sparseness, and the curse ofdimensionality.
We introduce a smoothed generalized
Dirichletdistributionthatisasmoothed
variant of the generalized Dirichlet distribution
and a generalization of the
smoothed Dirichlet. We provide different
learning methods based on mixture models
and agglomerative clustering-based
geometrical information: Kullback-Leibler
divergence, Fishermetric, and Bhattacharyya
distance.Moreover, we show that
the new smoothed generalized Dirichlet
could be considered as a prior to themultinomial,
which generates a new distribution
for count data that we call the
smoothed generalized Dirichlet multinomial.
In particular, we present an approximation
based on Taylor series expansion
forbetterperformance andoptimized running
time in the case ofhigh-dimensional
count data. The proposedmodels are evaluated
through two emotion detection
applications: disaster-tweet-related emotions
and pain intensity estimation.
Experiments show the efficiency and the
robustness of our approaches when dealingwith
texts, videos, and images. "
FEBRUARY 2023 | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 19
IEEE Computational Intelligence Magazine - February 2023

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - February 2023
