Engineering Technology & Applied Science Research,
Год журнала:
2024,
Номер
14(6), С. 19001 - 19008
Опубликована: Дек. 2, 2024
Most
traditional
IP
networks
face
serious
security
and
management
challenges
due
to
their
rapid
increase
in
complexity.
SDN
resolves
these
issues
by
the
separation
of
control
data
planes,
hence
enabling
programmability
for
centralized
with
flexibility.
On
other
hand,
its
architecture
makes
very
prone
DDoS
attacks,
necessitating
use
advanced
efficient
IDSs.
This
study
focuses
on
improving
IDS
performance
environments
through
integration
deep
learning
techniques
novel
feature
selection
methods.
presents
an
Enhanced
Maximum
Relevance
Minimum
Redundancy
(EMRMR)
approach
that
incorporates
a
Mutual
Information
Feature
Selection
(MIFS)
strategy
new
Contextual
Coefficient
Upweighting
(CRCU)
optimize
early
attack
detection.
Experiments
inSDN
dataset
showed
EMRMR
achieved
better
precision,
recall,
F1-score,
accuracy
compared
state-of-the-art
approaches,
especially
when
fewer
features
are
selected.
These
results
highlight
efficiency
proposed
relevant
minimal
computational
overhead,
which
enhances
real-time
capability
environments.
Automatika,
Год журнала:
2024,
Номер
65(4), С. 1364 - 1378
Опубликована: Июль 11, 2024
The
advancements
made
in
Software-Defined
Networking
(SDN)
technology
seem
quite
promising,
with
potential
wide
application
managing
and
controlling
the
latest
network
infrastructures.
SDN
decouples
control
plane
from
data
plane,
enabling
effective
flexible
management.
However,
this
dynamic
phenomenon
brings
new
security
challenges.
With
increasing
dynamism
programmable
nature
of
networks,
conventional
protocols
may
not
sufficient
to
protect
against
advanced
sophisticated
attacks.
Although
Intrusion
Detection
Systems
(IDSs)
have
been
extensively
applied
for
identifying
preventing
threats
traditional
environments,
IDS
models
designed
specifically
requirements
be
adequate
environments.
These
issues
stem
static
contrasting
dynamicity
IDS's
inability
adapt
SDN.
To
address
these
challenges,
current
research
proposes
a
novel
Deep
Hybrid
model
enhance
environments
prevent
attacks
using
Scapy.
proposed
detects
signature-based
by
integrating
Gated
Recurrent
Units
(GRU)
Long
Short-Term
Memory
(LSTM)
real-time
simulated
datasets,
achieving
an
accuracy
97.8%,
which
is
comparatively
better
than
existing
models.
RADIOELECTRONIC AND COMPUTER SYSTEMS,
Год журнала:
2024,
Номер
2024(2), С. 136 - 146
Опубликована: Апрель 23, 2024
Software-Defined
Networking
(SDN)
has
emerged
as
a
transformative
paradigm
for
network
management,
offering
centralized
control
and
programmability.
However,
with
the
proliferation
of
Distributed
Denial
Service
(DDoS)
attacks
that
pose
significant
threats
to
infrastructures,
effective
mitigation
strategies
are
needed.
The
subject
matter
this
study
is
explore
importance
datasets
in
DDoS
SDN
environments.
paper
discusses
significance
training
machine
learning
models,
evaluating
detection
mechanisms,
enhancing
resilience
SDN-based
defense
systems.
Goal
assist
researchers
effectively
selecting
usage
SDN,
thereby
maximizing
benefits
overcoming
challenges
involved
dataset
selection.
This
outlines
associated
collection,
labeling,
along
potential
solutions
address
these
challenges.
Effective
require
robust
capture
diverse
evolving
nature
attack
scenarios.
Characterization
tasks
each
section
follows:
Importance
utilization
Guidelines
selection,
comparison
used
their
results
different
according
need.
Methodology
involves
collecting
tabular
form
based
on
prior
research
analyze
characteristics
existing
datasets,
techniques
augmentation
enhancement,
effectiveness
detecting
mitigating
through
comprehensive
experimentation.
Results
our
findings
indicate
Our
provide
valuable
insights
into
infrastructures
against
attacks.
In
conclusion,
highlight
need
further
critical
area.
Thorough
guidelines
selection
impacts
recent
studies,
future
directions
Egyptian Informatics Journal,
Год журнала:
2024,
Номер
27, С. 100517 - 100517
Опубликована: Авг. 26, 2024
This
comprehensive
study
examines
cutting-edge
strategies
for
combating
Distributed
Denial
of
Service
(DDoS)
attacks
in
cloud
environments,
addressing
a
critical
gap
recent
literature.
Through
systematic
review
the
latest
advancements,
we
propose
framework
identifying,
preventing,
and
mitigating
DDoS
threats
specifically
tailored
to
infrastructures.
Our
research
highlights
urgent
need
robust
defense
mechanisms
enhance
security,
minimize
service
disruptions,
safeguard
against
data
breaches.
By
analyzing
strengths
limitations
current
models,
underscore
importance
continued
innovation
this
rapidly
evolving
field.
provides
essential
insights
academics
industry
professionals
aiming
resilience
infrastructure
ongoing
adaptive
menace
attacks.
