I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
4
,
A
u
g
u
s
t
20
2
6
,
p
p
.
2
1
6
9
~
2
1
8
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
4
.
pp
2
1
6
9
-
2
1
8
1
2169
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Intellig
ent
ro
utin
g
-
ba
sed a
tt
a
ck d
e
tect
io
n
i
n
Int
erne
t
o
f
Thin
g
s
networks
usi
ng
artificial in
telligenc
e
H
ud
a
Sa
lo
o
m
Su
lt
a
n
1
,
Ass
ee
l J
a
bb
a
r
Alm
a
hd
i
2
,
M
urt
ez
a
H
a
no
o
n T
ua
m
a
3
,
At
ha
r
H
us
s
ein
M
o
ha
m
m
ed
4
1
C
o
l
l
e
g
e
o
f
P
h
y
s
i
c
a
l
Ed
u
c
a
t
i
o
n
a
n
d
S
p
o
r
t
s Sc
i
e
n
c
e
s,
U
n
i
v
e
r
s
i
t
y
o
f
A
l
-
Q
a
d
i
si
y
a
h
,
Al
-
Q
a
d
i
si
y
a
h
,
I
r
a
q
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
C
o
l
l
e
g
e
o
f
C
o
mp
u
t
e
r
sc
i
e
n
c
e
a
n
d
M
a
t
h
e
mat
i
c
s
,
U
n
i
v
e
r
si
t
y
o
f
T
h
i
Q
a
r
,
T
h
i
-
Q
a
r
,
I
r
a
q
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
Te
c
h
n
i
q
u
e
s
En
g
i
n
e
e
r
i
n
g
,
I
mam
A
l
-
K
a
d
h
u
m
C
o
l
l
e
g
e
(
I
K
C
)
,
B
a
g
h
d
a
d
,
I
r
a
q
4
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
,
C
o
l
l
e
g
e
o
f
E
d
u
c
a
t
i
o
n
,
U
n
i
v
e
r
s
i
t
y
o
f
A
l
-
Q
a
d
i
s
i
y
a
h
,
D
i
w
a
n
i
y
a
h
,
I
r
a
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
1
7
,
2
0
2
6
R
ev
is
ed
Ma
y
1
6
,
2
0
2
6
Acc
ep
ted
J
u
l 2
2
,
2
0
2
6
Th
e
fa
st
-
g
r
o
win
g
I
n
tern
e
t
o
f
Th
i
n
g
s
(Io
T)
n
e
two
rk
s
h
a
v
e
p
o
se
d
c
o
n
sid
e
ra
b
le
se
c
u
rit
y
risk
s b
e
c
a
u
se
o
f
d
e
c
e
n
tra
li
z
e
d
n
e
two
r
k
d
e
sig
n
s,
d
y
n
a
m
ic
to
p
o
lo
g
ies
,
a
n
d
in
a
d
e
q
u
a
te
c
o
m
p
u
tatio
n
c
a
p
a
b
il
it
ies
.
Cu
rre
n
t
in
t
ru
sio
n
d
e
tec
ti
o
n
stra
teg
ies
a
re
p
rima
ril
y
traffic
-
b
a
se
d
,
b
u
t
wit
h
o
u
t
p
a
y
i
n
g
a
tt
e
n
ti
o
n
t
o
r
o
u
t
in
g
-
lay
e
r
d
y
n
a
m
ics
,
wh
ic
h
a
re
p
a
ra
m
o
u
n
t
in
m
u
lt
i
-
h
o
p
Io
T
sy
s
tem
s.
To
o
v
e
rc
o
m
e
th
is
d
ra
wb
a
c
k
,
th
is
p
a
p
e
r
su
g
g
e
sts
a
sm
a
rt
ro
u
ti
n
g
-
c
o
n
sc
io
u
s
a
tt
a
c
k
d
e
tec
ti
o
n
m
o
d
e
l
wh
ich
c
o
m
b
in
e
s
r
o
u
ti
n
g
-
lay
e
r
m
o
n
it
o
r
in
g
with
m
e
th
o
d
s
o
f
a
rt
ifi
c
ial
i
n
telli
g
e
n
c
e
to
imp
r
o
v
e
th
e
se
c
u
rit
y
o
f
Io
T
n
e
two
rk
s.
Th
e
su
g
g
e
ste
d
fra
m
e
wo
rk
c
o
n
st
a
n
tl
y
c
o
m
p
a
re
s
ro
u
ti
n
g
m
e
tri
c
s,
su
c
h
a
s
p
a
c
k
e
t
l
o
ss
,
c
h
a
n
g
e
in
h
o
p
c
o
u
n
t
,
e
n
d
t
o
e
n
d
d
e
lay
a
n
d
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
to
d
e
tec
t
m
a
li
c
io
u
s
r
o
u
ti
n
g
b
e
h
a
v
io
r
i
n
re
a
l
ti
m
e
.
Two
t
y
p
e
s
o
f
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
s,
fe
e
d
fo
rwa
rd
n
e
u
ra
l
n
e
two
rk
(F
F
NN
)
a
n
d
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(CNN
)
a
re
u
se
d
to
c
a
teg
o
rize
ro
u
ti
n
g
a
c
ti
v
it
ies
a
s
n
o
rm
a
l
o
r
m
a
li
c
io
u
s.
T
h
e
e
x
p
e
rime
n
tatio
n
o
n
sim
u
lati
o
n
wa
s
c
a
rried
o
u
t
b
y
u
sin
g
NS
-
2
in
a
d
y
n
a
m
ic
m
u
lt
i
-
h
o
p
Io
T
e
n
v
i
ro
n
m
e
n
t
wh
e
re
r
o
u
ti
n
g
-
b
a
se
d
D
o
S
a
tt
a
c
k
s
we
re
imp
lem
e
n
ted
.
T
h
e
e
x
p
e
rime
n
tal
re
su
lt
s
re
v
e
a
l
t
h
a
t
CNN
m
o
d
e
l
h
a
d
a
h
ig
h
e
r
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
o
f
8
5
.
7
6
%
wit
h
l
o
we
r
e
x
e
c
u
ti
o
n
ti
m
e
o
f
1
7
s
c
o
m
p
a
re
d
to
t
h
e
F
F
NN
m
o
d
e
l
wh
ich
h
a
d
a
n
a
c
c
u
ra
c
y
o
f
8
2
.
7
6
%
a
n
d
a
n
e
x
e
c
u
ti
o
n
ti
m
e
o
f
1
8
s.
M
o
re
o
v
e
r,
th
e
s
u
g
g
e
ste
d
fra
m
e
wo
rk
e
n
h
a
n
c
e
d
re
li
a
b
il
it
y
o
f
ro
u
ti
n
g
b
y
m
i
n
imi
z
in
g
th
e
p
a
c
k
e
t
l
o
ss
a
n
d
c
o
m
m
u
n
ica
ti
o
n
d
e
lay
a
n
d
h
a
v
in
g
l
o
w
ro
u
ti
n
g
o
v
e
rh
e
a
d
.
T
h
e
se
re
su
lt
s
su
p
p
o
rt
t
h
e
h
y
p
o
th
e
sis
th
a
t
ro
u
ti
n
g
-
a
wa
re
in
tell
ig
e
n
c
e
c
a
n
b
e
u
se
d
t
o
e
n
h
a
n
c
e
AI
-
b
a
se
d
in
tr
u
sio
n
d
e
tec
ti
o
n
t
o
c
re
a
te
a
n
a
d
a
p
ti
v
e
,
ro
u
ti
n
g
-
a
wa
re
,
a
n
d
re
so
u
rc
e
-
e
fficie
n
t
se
c
u
rit
y
so
l
u
ti
o
n
to
d
e
c
e
n
tralize
d
n
e
two
rk
s
o
f
I
o
T
d
e
v
ice
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Attack
d
etec
tio
n
I
n
tellig
en
t r
o
u
tin
g
I
n
ter
n
et
o
f
T
h
in
g
s
Netwo
r
k
s
ec
u
r
ity
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ass
ee
l Jab
b
ar
Alm
ah
d
i
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
C
o
lleg
e
o
f
C
o
m
p
u
ter
s
cie
n
ce
an
d
Ma
th
e
m
atics,
Un
iv
er
s
ity
o
f
T
h
iQar
T
h
i
-
Qar
,
I
r
a
q
E
m
ail: a
s
s
ee
lalm
ah
d
i@
u
tq
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
p
r
o
life
r
atio
n
o
f
th
e
I
n
t
er
n
et
o
f
T
h
in
g
s
(
I
o
T
)
h
as
led
to
lar
g
e
s
ca
le,
h
eter
o
g
en
eo
u
s
an
d
d
ec
en
tr
alize
d
n
etwo
r
k
s
co
m
p
r
is
in
g
leg
ac
y
as
well
as
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
d
ev
ices
th
at
co
m
m
u
n
icate
o
v
er
wir
eless
m
ed
ia.
Su
ch
n
etwo
r
k
s
ar
e
n
o
w
wid
ely
u
s
ed
i
n
m
is
s
io
n
-
cr
itical
ap
p
licatio
n
s
,
s
u
ch
as
s
m
ar
t
h
ea
lth
ca
r
e
s
y
s
tem
s
,
in
d
u
s
tr
ial
au
to
m
atio
n
p
r
o
ce
s
s
co
n
tr
o
l,
b
attlef
ield
co
m
m
u
n
icatio
n
an
d
d
is
aster
r
ec
o
v
er
y
r
esp
o
n
s
e.
Mo
s
t
o
f
th
e
I
o
T
d
e
p
lo
y
m
en
ts
m
ak
e
u
s
e
o
f
ad
h
o
c
an
d
m
u
lti
-
h
o
p
co
m
m
u
n
ica
tio
n
,
th
r
o
u
g
h
wh
ich
d
ev
ices
co
o
r
d
in
ate
am
o
n
g
th
em
s
elv
es
to
r
elay
t
h
e
d
ata
i
n
a
d
ec
en
tr
alize
d
m
an
n
e
r
to
th
o
s
e
f
ar
awa
y
as
co
m
p
ar
ed
with
tr
a
n
s
lato
r
n
o
d
es
o
r
g
atew
ay
r
esid
e,
wh
ich
h
av
e
s
im
ilar
ity
with
o
p
er
atio
n
ap
p
r
o
ac
h
m
o
b
ile
ad
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
1
6
9
-
2181
2170
h
o
c
n
etwo
r
k
s
(
MA
NE
T
s
)
[
1
]
,
[
2
]
.
Alth
o
u
g
h
s
u
c
h
d
is
tr
ib
u
ted
n
atu
r
e
o
f
I
o
T
s
y
s
tem
s
b
r
in
g
f
lex
ib
ilit
y
an
d
s
ca
lab
ilit
y
,
it
also
lead
s
to
s
ig
n
if
ican
t
s
ec
u
r
ity
th
r
ea
ts
th
at
u
n
d
er
m
in
e
th
e
d
ep
en
d
ab
ilit
y
an
d
r
o
b
u
s
tn
ess
o
f
I
o
T
in
f
r
astru
ctu
r
es.
R
o
u
tin
g
is
o
n
e
o
f
t
h
e
m
o
s
t
cr
u
cial
co
m
p
o
n
en
ts
in
th
e
d
ec
en
tr
alize
d
I
o
T
en
v
ir
o
n
m
e
n
t,
an
d
it
n
etwo
r
k
s
d
ev
ices
m
ak
e
s
u
r
e
f
o
r
estab
lis
h
in
g
an
d
m
ai
n
tain
in
g
p
ath
s
b
etwe
en
th
em
.
C
o
m
p
ar
ed
with
co
n
v
en
tio
n
al
n
etwo
r
k
s
with
f
ix
ed
in
f
r
astru
ctu
r
e,
I
o
T
r
o
u
ti
n
g
p
r
o
to
c
o
ls
s
h
o
u
l
d
b
e
a
b
le
to
p
er
f
o
r
m
am
o
n
g
d
y
n
am
ic
to
p
o
lo
g
ies,
m
o
b
ile
n
o
d
es,
co
n
s
tr
ain
ed
en
er
g
y
an
d
b
an
d
wid
th
r
eso
u
r
ce
s
[
3
]
.
I
n
t
h
is
co
n
tex
t,
d
u
e
to
th
e
jo
in
t
d
ata
s
o
u
r
ce
an
d
r
o
u
tin
g
in
ter
m
ed
iar
y
r
o
le
p
lay
e
d
b
y
ev
er
y
n
o
d
e
o
f
s
u
c
h
n
etwo
r
k
s
r
o
u
tin
g
d
ec
is
io
n
s
ar
e
to
o
m
u
c
h
v
u
ln
er
ab
le
a
g
ain
s
t th
e
ad
v
er
s
ar
ial
attac
k
.
T
h
er
e
f
o
r
e,
r
o
u
tin
g
attac
k
s
lik
e
d
en
ia
l o
f
s
er
v
ice
(
Do
S),
f
lo
o
d
in
g
,
b
lack
h
o
le
an
d
s
in
k
h
o
le,
im
p
er
s
o
n
atio
n
a
n
d
d
e
p
l
etio
n
o
f
e
n
er
g
y
ca
n
d
is
r
u
p
t
th
e
n
etwo
r
k
t
r
af
f
ic
f
lo
ws
b
ad
ly
[
4
]
,
[
5
]
.
R
ec
en
t
s
tu
d
ies
h
av
e
r
ep
o
r
ted
th
e
e
f
f
ici
en
cy
o
f
t
h
e
in
tellig
en
t
class
if
icatio
n
ap
p
r
o
ac
h
in
g
en
er
alizin
g
a
n
d
en
h
an
cin
g
r
o
b
u
s
tn
ess
in
s
ec
u
r
ity
ap
p
licatio
n
s
ev
en
in
a
d
v
er
s
ar
ial
co
n
d
itio
n
s
[
6
]
,
[
7
]
.
C
o
n
v
en
tio
n
al
s
ec
u
r
ity
tec
h
n
i
q
u
es
s
u
ch
as
en
cr
y
p
tio
n
,
au
t
h
en
ticatio
n
an
d
ac
ce
s
s
co
n
tr
o
l
r
em
ain
in
s
u
f
f
icien
t
to
ef
f
ec
tiv
ely
co
u
n
ter
th
ese
v
u
ln
er
a
b
ilit
ies
in
I
o
T
n
etwo
r
k
s
.
T
h
ese
m
ec
h
an
is
m
s
ar
e
m
ain
l
y
b
ased
o
n
s
tatic/ce
n
tr
alize
d
en
v
ir
o
n
m
en
t
an
d
ca
n
n
o
t
ea
s
ily
a
d
d
r
ess
th
e
d
y
n
am
ic
n
atu
r
e,
s
ca
lab
ilit
y
r
eq
u
ir
e
m
en
ts
,
an
d
r
eso
u
r
ce
c
o
n
s
tr
ain
ts
o
f
I
o
T
s
y
s
tem
s
[
8
]
.
B
esid
es,
tr
ad
itio
n
al
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
(
e.
g
.
,
u
s
in
g
p
r
ed
ef
in
e
d
s
ig
n
atu
r
es
o
r
s
tatic
r
u
les)
h
av
e
l
o
w
ad
ap
ta
b
ilit
y
an
d
a
r
e
d
if
f
ic
u
lt
to
d
etec
t
n
ew
o
r
ev
o
lu
tio
n
a
r
y
attac
k
in
g
b
e
h
av
io
r
s
s
in
ce
r
o
u
tin
g
p
r
o
to
co
ls
c
o
u
ld
b
e
ab
u
s
e
d
b
y
attac
k
er
s
f
o
r
ac
h
iev
i
n
g
s
tealth
ies
[
9
]
.
As
a
co
n
s
eq
u
en
ce
,
m
o
s
t
o
f
th
e
r
o
u
tin
g
-
b
ased
attac
k
s
ar
e
u
n
d
etec
ted
u
n
til
th
e
y
m
ater
i
ally
in
ter
f
er
e
with
p
er
f
o
r
m
an
ce
o
r
co
m
p
letely
c
u
t
o
f
f
co
m
m
u
n
icatio
n
.
As
an
ex
am
p
le
o
f
co
m
p
lex
ity
in
r
o
u
t
in
g
in
ter
ac
tio
n
s
a
n
d
attac
k
s
u
r
f
ac
es
o
n
a
d
ec
en
tr
alize
d
b
asis
,
Fig
u
r
e
1
s
h
o
ws
th
e
g
en
er
ic
ar
ch
itectu
r
e
f
o
r
m
u
lti
-
h
o
p
I
o
T
n
etwo
r
k
s
wh
er
e
ev
er
y
n
o
d
e
is
in
v
o
lv
e
d
in
b
o
th
t
h
e
r
o
u
tin
g
an
d
f
o
r
war
d
in
g
o
f
d
ata.
Fig
u
r
e
1
.
Gen
e
r
ic
m
u
lti
-
h
o
p
n
etwo
r
k
ar
ch
itectu
r
e
h
ig
h
li
g
h
ti
n
g
r
o
u
tin
g
in
te
r
ac
tio
n
s
am
o
n
g
n
o
d
es
R
ec
en
t
ad
v
an
ce
m
en
ts
in
ar
tific
ial
in
tellig
en
ce
(
AI
)
an
d
m
ac
h
in
e
lear
n
in
g
(
ML
)
h
av
e
o
p
en
ed
n
e
w
r
esear
ch
d
ir
ec
tio
n
s
f
o
r
e
n
h
an
c
in
g
s
ec
u
r
ity
in
I
o
T
n
etwo
r
k
s
.
AI
-
d
r
iv
en
a
p
p
r
o
ac
h
es
en
ab
le
i
n
tellig
en
t
an
aly
s
is
o
f
n
etwo
r
k
b
eh
av
i
o
r
b
y
lear
n
in
g
co
m
p
lex
p
atter
n
s
f
r
o
m
tr
af
f
ic
an
d
r
o
u
tin
g
d
ata,
allo
wi
n
g
th
e
d
etec
tio
n
o
f
s
u
b
tle
an
o
m
alies
th
at
ar
e
d
if
f
i
cu
lt
to
ca
p
tu
r
e
u
s
in
g
tr
ad
itio
n
al
m
eth
o
d
s
[
1
0
]
,
[
1
1
]
.
I
n
p
ar
ti
cu
lar
,
in
te
g
r
atin
g
AI
m
o
d
els
with
r
o
u
tin
g
-
la
y
er
i
n
f
o
r
m
atio
n
p
r
o
v
id
es
a
p
r
o
m
is
in
g
o
p
p
o
r
t
u
n
ity
to
d
etec
t
attac
k
s
at
an
e
ar
ly
s
tag
e
b
y
m
o
n
ito
r
in
g
d
e
v
iatio
n
s
in
r
o
u
tin
g
m
etr
ics
s
u
ch
as
p
ac
k
et
f
o
r
war
d
in
g
b
e
h
av
io
r
,
h
o
p
co
u
n
t
v
ar
iatio
n
s
,
d
ela
y
p
atter
n
s
,
an
d
en
e
r
g
y
co
n
s
u
m
p
tio
n
tr
e
n
d
s
[
1
2
]
.
Un
lik
e
s
ta
n
d
alo
n
e
I
DS
s
o
lu
tio
n
s
,
r
o
u
ti
n
g
-
awa
r
e
A
I
-
b
ased
d
etec
tio
n
f
r
am
ewo
r
k
s
ca
n
jo
i
n
tly
o
p
tim
ize
s
ec
u
r
ity
a
n
d
n
etwo
r
k
p
e
r
f
o
r
m
an
ce
b
y
em
b
ed
d
in
g
in
tellig
en
ce
d
ir
ec
tly
in
to
th
e
r
o
u
tin
g
d
ec
is
io
n
p
r
o
ce
s
s
.
I
n
p
ar
ticu
lar
,
in
te
g
r
atin
g
AI
m
o
d
els
with
r
o
u
tin
g
-
lay
er
in
f
o
r
m
atio
n
p
r
o
v
id
es
a
p
r
o
m
is
in
g
o
p
p
o
r
t
u
n
ity
to
d
etec
t
attac
k
s
at
an
ea
r
ly
s
tag
e
b
y
m
o
n
ito
r
i
n
g
d
e
v
iatio
n
s
in
r
o
u
tin
g
m
etr
ics
s
u
ch
as
p
ac
k
et
f
o
r
war
d
in
g
b
e
h
av
io
r
,
h
o
p
c
o
u
n
t
v
a
r
iatio
n
s
,
d
elay
p
atter
n
s
,
an
d
e
n
er
g
y
co
n
s
u
m
p
tio
n
tr
en
d
s
[
1
3
]
,
[
1
4
]
.
Un
lik
e
s
tan
d
alo
n
e
I
DS
s
o
lu
tio
n
s
,
r
o
u
tin
g
-
a
war
e
AI
-
b
ased
d
etec
tio
n
f
r
am
ewo
r
k
s
ca
n
jo
in
tly
o
p
tim
ize
s
ec
u
r
ity
an
d
n
etwo
r
k
p
er
f
o
r
m
an
ce
b
y
em
b
ed
d
in
g
in
tellig
en
ce
d
ir
ec
tly
in
to
t
h
e
r
o
u
tin
g
d
ec
is
io
n
p
r
o
ce
s
s
.
R
ec
en
t
s
tu
d
ies
f
u
r
th
er
co
n
f
i
r
m
th
at
h
y
b
r
i
d
AI
-
d
r
iv
en
s
ec
u
r
ity
f
r
am
ewo
r
k
s
s
ig
n
if
ican
tly
en
h
an
ce
an
o
m
aly
d
etec
tio
n
in
lar
g
e
-
s
ca
le
I
o
T
en
v
ir
o
n
m
e
n
ts
[
1
5
]
.
Alth
o
u
g
h
th
er
e
h
as
b
ee
n
m
u
ch
r
esear
ch
d
o
n
e
o
n
AI
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
f
o
r
I
o
T
n
etwo
r
k
s
,
v
ar
io
u
s
d
r
awb
ac
k
s
s
till
r
em
ai
n
ed
.
So
m
e
r
esear
ch
p
ap
er
s
ei
th
er
tak
e
in
to
ac
c
o
u
n
t
o
n
l
y
tr
af
f
ic
-
lev
el
f
ea
t
u
r
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
n
tellig
en
t ro
u
tin
g
-
b
a
s
ed
a
tta
ck
d
etec
tio
n
in
in
tern
et
o
f th
in
g
s
n
etw
o
r
ks u
s
in
g
…
(
Hu
d
a
S
a
lo
o
m
S
u
lta
n
)
2171
with
o
u
t
in
v
esti
g
atin
g
r
o
u
tin
g
d
y
n
am
ics,
o
r
an
aly
ze
th
e
d
etec
tio
n
p
er
f
o
r
m
an
ce
r
ath
er
t
h
at
d
esig
n
in
g
a
n
d
s
h
o
win
g
th
e
in
f
lu
e
n
ce
o
n
r
o
u
tin
g
ef
f
icien
c
y
an
d
n
etwo
r
k
o
v
er
h
ea
d
[
1
6
]
,
[
1
7
]
.
I
n
a
d
d
i
tio
n
,
m
o
s
t
ex
is
tin
g
s
o
lu
tio
n
s
ar
e
n
o
t
f
u
lly
ev
alu
a
ted
u
n
d
er
d
iv
er
s
e
r
o
u
tin
g
-
b
ased
attac
k
s
ce
n
ar
io
s
an
d
p
r
o
b
l
em
s
ettin
g
s
,
wh
ich
m
ig
h
t h
av
e
an
im
p
ac
t
o
n
th
ei
r
p
r
ac
ticality
in
th
e
I
o
T
.
T
h
u
s
,
th
is
p
ap
er
s
u
g
g
ests
a
n
ew
in
tellig
en
t
r
o
u
tin
g
-
c
o
n
s
cio
u
s
in
tr
u
s
io
n
d
etec
tio
n
m
o
d
el
o
f
d
ec
en
tr
alize
d
I
o
T
n
etwo
r
k
s
th
r
o
u
g
h
th
e
co
m
b
in
atio
n
o
f
r
o
u
tin
g
-
lay
er
-
s
en
s
in
g
with
ar
tific
ial
in
tellig
en
ce
.
I
n
co
n
tr
ast
to
tr
ad
itio
n
al
m
eth
o
d
s
o
f
tr
af
f
ic
-
b
ased
I
DS,
th
e
f
r
am
ewo
r
k
p
r
o
p
o
s
ed
em
p
l
o
y
s
d
y
n
am
ic
r
o
u
tin
g
m
etr
ics,
s
u
ch
as
p
ac
k
et
lo
s
s
,
ch
an
g
e
i
n
h
o
p
c
o
u
n
t,
en
d
-
to
-
en
d
d
ela
y
,
an
d
e
n
er
g
y
co
n
s
u
m
p
tio
n
,
t
o
id
e
n
tify
m
alicio
u
s
r
o
u
tin
g
ac
tiv
ities
in
r
ea
l
-
tim
e.
T
h
e
o
r
i
g
in
ality
o
f
th
e
s
u
g
g
ested
s
o
lu
tio
n
is
th
at
it
in
co
r
p
o
r
ates
AI
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
as
a
p
ar
t
o
f
a
r
o
u
tin
g
m
ec
h
an
is
m
to
co
m
b
in
e
th
e
ef
f
ec
ti
v
en
ess
o
f
d
etec
tin
g
attac
k
s
an
d
th
e
ef
f
icien
cy
o
f
r
o
u
tin
g
in
I
o
T
s
ettin
g
s
with
lim
ited
r
eso
u
r
ce
s
.
Mo
r
eo
v
er
,
th
e
f
r
am
ewo
r
k
in
co
r
p
o
r
ates
r
o
u
tin
g
-
awa
r
e
f
ea
tu
r
e
ex
tr
ac
t
io
n
an
d
d
ee
p
lear
n
in
g
-
b
ased
class
if
icatio
n
to
o
f
f
er
d
y
n
a
m
ic
m
u
lti
-
h
o
p
I
o
T
n
etwo
r
k
ad
a
p
tiv
e
an
d
lig
h
twei
g
h
t a
ttack
d
etec
tio
n
.
T
h
e
p
r
im
ar
y
wo
r
k
f
in
d
i
n
g
s
in
clu
d
e:
a.
Su
g
g
esti
n
g
a
s
m
ar
t
r
o
u
tin
g
-
awa
r
e
AI
s
y
s
tem
t
o
id
e
n
tify
r
o
u
tin
g
-
b
ased
attac
k
s
in
d
e
ce
n
tr
alize
d
I
o
T
n
etwo
r
k
s
.
b.
T
h
e
id
ea
is
to
c
o
m
b
in
e
r
o
u
tin
g
-
lay
er
m
ea
s
u
r
em
e
n
ts
with
AI
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
to
en
h
a
n
ce
th
e
ab
ilit
y
to
d
etec
t a
n
o
m
alies.
c.
T
esti
n
g
th
e
f
r
am
ewo
r
k
with
th
e
FF
NN
an
d
C
NN
m
o
d
els o
n
Do
S a
ttack
s
b
ased
o
n
r
o
u
tin
g
.
d.
E
v
alu
atin
g
attac
k
d
etec
tio
n
p
er
f
o
r
m
an
ce
an
d
r
o
u
tin
g
ef
f
icien
cy
to
d
em
o
n
s
tr
ate
lo
w
-
o
v
er
h
ea
d
s
ec
u
r
e
co
m
m
u
n
icatio
n
in
d
y
n
am
ic
I
o
T
en
v
ir
o
n
m
en
ts
.
2.
RE
L
AT
E
D
WO
RK
I
o
T
n
etwo
r
k
s
s
ec
u
r
ity
r
esear
ch
h
as
attr
ac
ted
in
c
r
ea
s
in
g
atten
tio
n
in
th
e
r
ec
en
t
y
ea
r
s
with
th
e
p
r
o
life
r
atio
n
o
f
d
ec
en
t
r
alize
d
,
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
an
d
m
i
s
s
io
n
cr
itical
I
o
T
s
y
s
tem
s
.
O
v
er
all,
th
e
ex
is
tin
g
wo
r
k
s
ca
n
b
e
ty
p
ically
ca
te
g
o
r
ized
in
to
th
r
ee
class
es:
c
o
n
v
en
tio
n
al
r
o
u
tin
g
-
b
ased
s
e
cu
r
ity
s
ch
em
es,
AI
tech
n
iq
u
es
f
o
r
d
etec
tin
g
I
o
T
in
tr
u
s
io
n
s
an
d
h
y
b
r
i
d
m
eth
o
d
s
wh
ich
co
m
b
in
e
AI
with
r
o
u
tin
g
-
lay
e
r
in
f
o
r
m
atio
n
.
2
.
1
.
T
ra
ditio
na
l
ro
uting
-
ba
s
ed
s
ec
urit
y
in I
o
T
net
wo
rk
s
I
n
itial
r
esear
ch
wo
r
k
s
co
n
ce
r
n
ed
s
ec
u
r
in
g
th
e
I
o
T
an
d
ad
-
h
o
c
n
etwo
r
k
s
u
s
in
g
m
o
d
if
ie
d
r
o
u
tin
g
p
r
o
to
co
ls
o
r
c
r
y
p
t
o
g
r
ap
h
ic
to
o
ls
.
T
ig
h
tly
co
u
p
led
r
o
u
tin
g
p
r
o
to
co
ls
wer
e
p
r
esen
ted
to
co
m
b
at
attac
k
s
lik
e
b
lack
h
o
le,
s
in
k
h
o
le
an
d
f
lo
o
d
in
g
b
y
ad
d
i
n
g
au
th
e
n
ticatio
n
,
tr
u
s
t
m
an
ag
em
e
n
t,
o
r
r
ep
u
tatio
n
-
b
ased
m
ec
h
an
is
m
s
in
to
th
e
r
o
u
te
s
elec
tio
n
p
r
o
ce
s
s
[
1
]
,
[
2
]
,
[
7
]
.
T
h
ese
tech
n
iq
u
es
wer
e
d
esig
n
ed
to
ex
clu
d
e
b
ein
g
ex
p
lo
ited
b
y
m
is
b
eh
av
in
g
n
o
d
es
in
th
e
r
o
u
te
d
is
co
v
er
y
o
r
f
o
r
war
d
in
g
as
th
e
y
v
e
r
if
ied
n
o
d
e
id
en
titi
es
o
r
d
etec
ted
in
co
r
r
ec
t p
ac
k
et
h
an
d
lin
g
.
Ho
wev
er
,
th
e
ab
o
v
e
s
ch
em
e
s
u
s
u
ally
h
av
e
h
ig
h
co
m
m
u
n
icatio
n
an
d
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
s
,
wh
ich
is
n
o
t
s
u
itab
le
to
th
e
I
o
T
en
v
ir
o
n
m
en
ts
with
lim
ited
en
er
g
y
,
m
em
o
r
y
an
d
co
m
p
u
tatio
n
[
3
]
.
Fu
r
th
er
m
o
r
e
,
s
ec
u
r
ity
m
ec
h
a
n
is
m
s
th
at
ar
e
b
ased
o
n
r
o
u
tin
g
g
en
er
ally
r
ely
o
n
k
n
o
wn
atta
ck
m
o
d
els
an
d
lac
k
ag
ilit
y
ag
ain
s
t
n
ew
o
r
ch
an
g
in
g
attac
k
s
,
th
u
s
p
r
o
v
id
i
n
g
s
ca
r
ce
p
r
o
tectio
n
in
a
d
y
n
am
i
ca
lly
ch
an
g
in
g
I
o
T
s
ce
n
ar
io
[
4
]
,
[
5
]
.
Acc
o
r
d
in
g
ly
,
d
ef
en
s
e
m
ec
h
an
is
m
s
b
ased
s
o
lely
o
n
r
u
le
-
b
ased
o
r
cr
y
p
to
g
r
a
p
h
ic
r
o
u
tin
g
m
ec
h
an
is
m
s
lack
th
e
ab
ilit
y
to
o
f
f
er
s
tr
o
n
g
,
s
ca
lab
le
s
ec
u
r
ity
p
r
o
tectio
n
s
.
2
.
2
.
AI
-
ba
s
ed
intr
us
io
n det
e
ct
io
n sy
s
t
em
s
f
o
r
I
o
T
I
n
o
r
d
e
r
to
tack
le
th
e
r
eq
u
i
r
em
en
ts
o
f
co
n
v
en
tio
n
al
s
ec
u
r
ity
s
o
lu
tio
n
s
,
I
o
T
n
etwo
r
k
in
tr
u
s
io
n
d
etec
tio
n
h
as
d
r
awn
in
cr
ea
s
i
n
g
in
ter
est
a
m
o
n
g
r
esear
c
h
er
s
in
ML
a
n
d
DL
tech
n
i
q
u
es
f
o
r
th
is
p
u
r
p
o
s
e.
Var
io
u
s
s
u
p
er
v
is
ed
lear
n
in
g
m
eth
o
d
s
lik
e
SVM,
R
F,
k
-
NN
h
av
e
co
m
m
o
n
ly
b
ee
n
u
s
ed
to
d
is
tin
g
u
is
h
n
o
r
m
al
an
d
an
o
m
alo
u
s
n
etwo
r
k
tr
af
f
i
c
p
atter
n
s
f
r
o
m
n
etwo
r
k
lev
e
l
f
ea
tu
r
es
[
5
]
,
[
8
]
.
Mo
r
e
r
ec
e
n
tly
,
d
ee
p
lea
r
n
in
g
ap
p
r
o
ac
h
es
s
u
ch
as
co
n
v
o
lu
t
io
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs),
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs)
an
d
l
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etwo
r
k
s
h
av
e
s
h
o
wn
an
en
h
an
ce
d
d
etec
tio
n
ac
cu
r
ac
y
an
d
b
e
tter
ad
ap
tab
ilit
y
to
co
m
p
lex
attac
k
i
n
g
b
eh
av
io
r
s
[
9
]
,
[
1
0
]
.
R
ec
en
t
b
en
c
h
m
ar
k
s
in
d
icate
th
at
d
ee
p
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els
an
d
h
y
b
r
id
m
o
d
els
ar
e
b
eg
in
n
in
g
t
o
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
ar
c
h
i
tectu
r
es
in
c
o
m
p
lex
attac
k
s
ce
n
ar
io
s
[
1
8
]
.
E
v
en
wh
en
AI
-
en
ab
led
I
DSs
h
av
e
th
e
ab
ilit
y
to
d
etec
t
g
r
ea
ter
d
is
cr
im
in
atio
n
,
th
e
m
ajo
r
ity
o
f
p
r
ev
io
u
s
wo
r
k
s
co
n
s
id
er
o
n
ly
tr
af
f
ic
o
r
p
ac
k
et
f
ea
tu
r
es,
with
o
u
t
tak
in
g
in
to
co
n
s
id
er
atio
n
h
o
w
f
u
n
d
am
en
tal
ar
e
r
o
u
tin
g
d
y
n
a
m
ics
f
o
r
d
ec
en
tr
alize
d
I
o
T
n
etwo
r
k
s
[
9
]
.
Mo
r
eo
v
er
,
m
a
n
y
m
o
d
els
ar
e
b
ased
o
n
ce
n
tr
alize
d
ar
ch
itectu
r
es,
o
r
r
eq
u
ir
e
lar
g
e
n
u
m
b
e
r
o
f
lab
eled
d
ata
s
et
lear
n
in
g
p
r
o
ce
d
u
r
es,
wh
ich
is
n
o
t
ap
p
licab
le
to
m
ass
iv
e
an
d
r
ea
l
-
tim
e
I
o
T
s
ce
n
ar
io
s
[
1
2
]
.
T
h
e
ab
o
v
e
li
m
itatio
n
s
m
ak
e
s
tan
d
alo
n
e
AI
-
b
ased
I
DSs
less
p
r
ac
tical
in
a
r
o
u
tin
g
-
h
ea
v
y
I
o
T
en
v
ir
o
n
m
en
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
1
6
9
-
2181
2172
2
.
3
.
Ro
uting
-
a
wa
re
AI
-
ba
s
ed
det
ec
t
io
n a
pp
ro
a
ches
T
h
er
e
is
o
th
er
wo
r
k
o
n
co
m
b
in
in
g
r
o
u
ti
n
g
i
n
f
o
r
m
atio
n
with
AI
m
o
d
els
f
o
r
d
etec
tio
n
b
u
t
it
is
r
elativ
ely
less
well
u
n
d
e
r
s
to
o
d
.
T
h
ese
r
esear
ch
es
u
tili
ze
r
o
u
tin
g
m
etr
ics
s
u
c
h
as
p
ac
k
et
f
o
r
war
d
r
atio
s
,
h
o
p
co
u
n
t d
ev
iatio
n
,
r
o
u
te
r
e
q
u
est r
ate
an
d
d
elay
v
ar
iatio
n
to
id
e
n
tify
b
lack
h
o
le
attac
k
s
o
n
r
o
u
tin
g
p
r
o
to
c
o
ls
[
1
6
]
,
[
1
7
]
.
T
h
r
o
u
g
h
s
ee
k
in
g
ir
r
eg
u
lar
ities
in
r
o
u
tin
g
d
ec
is
io
n
s
,
th
ey
ca
n
d
etec
t
attac
k
s
th
at
ar
e
n
o
t
ex
p
o
s
ed
o
n
th
e
tr
af
f
ic
lev
el.
Desp
ite
th
eir
p
r
o
m
is
e,
p
r
ev
i
o
u
s
r
o
u
tin
g
-
awa
r
e
AI
tech
n
iq
u
es
ar
e
lo
o
k
in
g
at
th
e
lim
ited
s
co
p
e
(
e.
g
.
,
o
n
l
y
tar
g
etin
g
o
n
e
attac
k
ty
p
e
o
r
ig
n
o
r
in
g
t
h
e
ef
f
ec
t
o
f
d
etec
tio
n
s
y
s
tem
s
o
n
r
o
u
ti
n
g
p
er
f
o
r
m
an
ce
an
d
n
etwo
r
k
o
v
er
h
ea
d
)
[
1
9
]
.
Mo
r
eo
v
er
,
a
n
u
m
b
e
r
o
f
wo
r
k
s
h
av
e
n
o
t
y
et
ca
r
r
ied
o
u
t
ef
f
ec
tiv
e
co
m
p
ar
ativ
e
an
aly
s
is
with
th
e
ex
i
s
tin
g
ad
v
an
ce
d
m
o
d
el
th
at
m
ak
es
it
alm
o
s
t
im
p
o
s
s
ib
le
to
ev
alu
ate
t
h
eir
ef
f
ec
tiv
en
ess
in
d
if
f
er
en
t
I
o
T
s
ettin
g
s
[
2
0
]
.
T
h
u
s
,
th
er
e
is
a
n
ee
d
f
o
r
an
in
te
g
r
ated
s
o
lu
tio
n
,
c
o
n
s
id
er
in
g
b
o
th
attac
k
-
d
etec
tio
n
ac
cu
r
ac
y
a
n
d
r
o
u
tin
g
ef
f
icien
cy
as
well
as
s
ca
lab
ilit
y
.
T
h
e
co
m
p
ar
is
o
n
is
s
h
o
wn
in
T
ab
l
e
1
f
r
o
m
wh
ich
we
ca
n
s
ee
th
at
cu
r
r
en
t
m
eth
o
d
s
p
ay
m
o
r
e
atten
tio
n
to
r
o
u
tin
g
s
ec
u
r
ity
with
o
u
t
in
tellig
en
c
e
o
r
u
s
e
AI
-
b
ased
d
etec
tio
n
wh
ile
lim
itin
g
in
th
e
in
co
m
p
lete
s
en
s
e
o
f
r
o
u
ti
n
g
.
T
h
e
p
r
o
p
o
s
ed
s
ch
em
e
is
u
n
iq
u
e
b
y
n
o
v
elty
co
m
b
in
in
g
in
tellig
en
t
a
n
aly
s
is
an
d
r
o
u
tin
g
-
lay
er
m
etr
ics,
th
at
ca
n
b
o
th
d
etec
t
ty
p
es
o
f
atta
ck
s
ac
cu
r
ately
with
a
s
ca
lab
le
m
ec
h
an
is
m
in
I
o
T
n
etwo
r
k
s
.
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
ex
is
tin
g
r
o
u
tin
g
an
d
AI
-
b
a
s
ed
attac
k
d
etec
tio
n
ap
p
r
o
ac
h
e
s
in
I
o
T
n
etwo
r
k
s
R
e
f
.
A
p
p
r
o
a
c
h
Ty
p
e
R
o
u
t
i
n
g
I
n
f
o
r
mat
i
o
n
U
t
i
l
i
z
e
d
A
I
Te
c
h
n
i
q
u
e
U
sed
A
t
t
a
c
k
T
y
p
e
s
C
o
n
si
d
e
r
e
d
P
e
r
f
o
r
ma
n
c
e
Ev
a
l
u
a
t
i
o
n
I
d
e
n
t
i
f
i
e
d
L
i
m
i
t
a
t
i
o
n
s
[
1
]
S
e
c
u
r
e
R
o
u
t
i
n
g
P
r
o
t
o
c
o
l
Li
mi
t
e
d
(
R
o
u
t
e
a
u
t
h
e
n
t
i
c
a
t
i
o
n
)
N
o
n
e
B
l
a
c
k
h
o
l
e
,
S
i
n
k
h
o
l
e
P
a
c
k
e
t
d
e
l
i
v
e
r
y
r
a
t
i
o
H
i
g
h
o
v
e
r
h
e
a
d
,
s
t
a
t
i
c
d
e
f
e
n
se
me
c
h
a
n
i
sms
[
2
]
Tr
u
st
-
B
a
se
d
R
o
u
t
i
n
g
Tr
u
st
me
t
r
i
c
s
o
n
l
y
N
o
n
e
F
l
o
o
d
i
n
g
,
I
mp
e
r
so
n
a
t
i
o
n
N
e
t
w
o
r
k
t
h
r
o
u
g
h
p
u
t
P
o
o
r
a
d
a
p
t
a
b
i
l
i
t
y
t
o
d
y
n
a
mi
c
a
t
t
a
c
k
s
[
9
]
ML
-
b
a
se
d
I
D
S
No
S
V
M
,
R
F
D
o
S
,
D
D
o
S
D
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
I
g
n
o
r
e
s r
o
u
t
i
n
g
d
y
n
a
mi
c
s
[
1
0
]
DL
-
b
a
se
d
I
D
S
No
C
N
N
,
LSTM
M
u
l
t
i
p
l
e
t
r
a
f
f
i
c
-
b
a
s
e
d
a
t
t
a
c
k
s
A
c
c
u
r
a
c
y
,
R
e
c
a
l
l
C
e
n
t
r
a
l
i
z
e
d
d
e
s
i
g
n
,
h
i
g
h
t
r
a
i
n
i
n
g
c
o
s
t
[
1
6
]
H
y
b
r
i
d
I
D
S
P
a
r
t
i
a
l
(
t
r
a
f
f
i
c
st
a
t
i
st
i
c
s)
M
L
m
o
d
e
l
s
D
o
S
D
e
t
e
c
t
i
o
n
r
a
t
e
Li
mi
t
e
d
r
o
u
t
i
n
g
a
w
a
r
e
n
e
ss
[
1
9
]
R
o
u
t
i
n
g
-
A
w
a
r
e
A
I
Y
e
s (h
o
p
c
o
u
n
t
,
d
e
l
a
y
)
ML
B
l
a
c
k
h
o
l
e
D
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
S
i
n
g
l
e
a
t
t
a
c
k
s
c
e
n
a
r
i
o
[
2
0
]
R
o
u
t
i
n
g
-
B
a
se
d
I
D
S
Y
e
s (R
R
EQ
f
r
e
q
u
e
n
c
y
)
R
u
l
e
-
b
a
se
d
F
l
o
o
d
i
n
g
F
a
l
se
p
o
si
t
i
v
e
r
a
t
e
P
o
o
r
s
c
a
l
a
b
i
l
i
t
y
Th
i
s
W
o
r
k
I
n
t
e
l
l
i
g
e
n
t
R
o
u
t
i
n
g
-
B
a
se
d
A
I
F
r
a
mew
o
r
k
C
o
m
p
r
e
h
e
n
si
v
e
r
o
u
t
i
n
g
me
t
r
i
c
s
AI
-
b
a
se
d
mo
d
e
l
M
u
l
t
i
p
l
e
r
o
u
t
i
n
g
-
b
a
s
e
d
a
t
t
a
c
k
s
D
e
t
e
c
t
i
o
n
+
r
o
u
t
i
n
g
e
f
f
i
c
i
e
n
c
y
met
r
i
c
s
A
d
d
r
e
ss
e
s
a
d
a
p
t
a
b
i
l
i
t
y
,
sca
l
a
b
i
l
i
t
y
,
a
n
d
p
e
r
f
o
r
m
a
n
c
e
t
r
a
d
e
-
o
f
f
s
Fro
m
th
e
liter
atu
r
es
we
h
av
e
r
ev
iewe
d
,
it
ca
n
b
e
k
n
o
wn
t
h
at
cu
r
r
en
t
m
eth
o
d
s
ad
d
r
ess
th
e
r
o
u
tin
g
s
ec
u
r
ity
b
u
t
with
o
u
t
in
tellig
en
ce
tech
n
i
q
u
es
o
r
ad
o
p
t
A
I
-
b
ased
d
etec
tio
n
b
u
t
ig
n
o
r
e
th
e
r
o
u
tin
g
-
lay
e
r
d
y
n
am
ics.
On
ly
a
f
ew
wo
r
k
s
p
r
esen
t
an
in
teg
r
ated
a
p
p
r
o
ac
h
th
at
u
s
es
th
e
r
o
u
tin
g
m
etr
ic
s
in
a
s
m
ar
t
way
to
p
r
ec
lu
d
e
m
u
lti
-
attac
k
ty
p
es
av
o
id
in
g
s
ac
r
if
icin
g
n
etwo
r
k
'
s
p
er
f
o
r
m
a
n
ce
in
I
o
T
n
etwo
r
k
s
.
T
h
e
co
n
tr
ib
u
tio
n
o
f
th
is
wo
r
k
is
to
clo
s
e
th
i
s
g
ap
b
y
p
r
o
p
o
s
in
g
an
in
tellig
en
t
r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
f
r
am
ewo
r
k
,
wh
ich
lev
er
ag
es AI
an
d
r
o
u
ti
n
g
-
lay
e
r
in
f
o
r
m
atio
n
f
o
r
b
etter
ac
c
u
r
ac
y
an
d
a
d
ap
tab
ilit
y
in
m
u
ltit
r
ac
k
s
ce
n
ar
io
s
.
3.
SYST
E
M
M
O
D
E
L
A
ND
T
H
RE
A
T
ASSU
M
P
T
I
O
NS
3
.
1
.
Sy
s
t
e
m
mo
del
I
n
th
is
p
ap
er
,
th
e
a
u
th
o
r
s
s
tu
d
y
a
d
ec
e
n
tr
alize
d
I
o
T
n
etwo
r
k
in
wh
ich
n
o
d
es
ar
e
lo
ca
t
ed
am
o
n
g
th
em
s
elv
es
an
d
th
er
e
is
n
o
f
i
x
ed
in
f
r
astru
ctu
r
e
to
f
o
r
war
d
p
ac
k
ets
to
war
d
th
eir
d
esti
n
atio
n
s
.
T
h
is
m
o
d
el
f
its
well
with
ty
p
ical
I
o
T
d
ep
lo
y
m
en
ts
in
wh
ich
o
n
-
d
e
m
an
d
o
v
er
MA
NE
T
r
o
u
tin
g
is
p
e
r
f
o
r
m
ed
u
n
d
er
d
y
n
am
ic
co
n
d
itio
n
s
(
e
m
er
g
en
c
y
r
esp
o
n
s
e,
m
o
b
ile
s
en
s
in
g
,
m
ilit
ar
y
/tactica
l
C
2
en
v
ir
o
n
m
e
n
t)
an
d
wh
er
e
r
o
u
tes
ar
e
ac
q
u
ir
ed
in
a
d
is
tr
ib
u
ted
m
an
n
er
an
d
k
ep
t u
p
-
to
-
d
ate
b
ased
o
n
n
etwo
r
k
s
tatu
s
.
Netwo
r
k
to
p
o
lo
g
y
an
d
m
o
b
ili
ty
.
T
h
e
s
y
s
tem
is
co
n
s
id
er
ed
to
b
e
an
I
o
T
n
etwo
r
k
co
n
s
is
t
in
g
o
f
5
0
n
o
d
es
an
d
n
o
d
e
m
o
b
ilit
y
is
m
o
d
eled
with
m
u
lti
-
s
p
ee
d
f
o
r
r
ea
lis
tic
d
y
n
am
ic
c
h
an
g
es.
Du
e
to
th
e
f
ac
t
th
a
t
r
o
u
tin
g
s
tab
ilit
y
is
s
ig
n
if
ican
tly
im
p
ac
ted
b
y
m
o
b
ilit
y
an
d
lin
k
d
y
n
am
ics,
m
o
d
elin
g
v
ar
io
u
s
s
p
ee
d
s
allo
ws
f
o
r
in
v
esti
g
atin
g
th
e
r
o
b
u
s
tn
ess
o
f
r
o
u
tin
g
an
d
attac
k
d
etec
tab
i
lity
u
n
d
e
r
d
i
f
f
er
en
t
n
etwo
r
k
d
y
n
am
ics.
R
o
u
tin
g
an
d
I
DS
in
teg
r
atio
n
.
E
ac
h
n
o
d
e
is
ca
p
ab
le
o
f
b
ein
g
u
s
e
d
as
a
s
en
s
in
g
/co
m
m
u
n
icatio
n
p
o
in
t
an
d
/o
r
a
f
o
r
war
d
in
g
r
elay
.
T
h
e
n
etwo
r
k
also
in
clu
d
es
an
in
tr
u
s
io
n
d
etec
tio
n
f
ac
ilit
y
(
I
DS)
th
at
wo
r
k
s
in
co
o
r
d
in
atio
n
with
r
o
u
tin
g
to
m
o
n
ito
r
th
e
c
h
ar
ac
ter
is
tics
o
f
r
o
u
tin
g
an
d
id
en
tify
m
alicio
u
s
b
eh
a
v
io
r
s
wh
ich
co
n
tr
ib
u
te
to
p
er
f
o
r
m
an
ce
d
r
a
g
s
o
n
th
e
n
etwo
r
k
.
T
h
e
I
DS
ar
e
n
o
t
o
n
ly
b
ased
o
n
p
ay
lo
a
d
in
s
p
ec
tio
n
;
it
o
b
s
er
v
es
r
o
u
tin
g
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
n
tellig
en
t ro
u
tin
g
-
b
a
s
ed
a
tta
ck
d
etec
tio
n
in
in
tern
et
o
f th
in
g
s
n
etw
o
r
ks u
s
in
g
…
(
Hu
d
a
S
a
lo
o
m
S
u
lta
n
)
2173
awa
r
e
ch
ar
ac
ter
is
tics
an
d
co
m
m
u
n
icatio
n
p
atter
n
s
f
o
r
an
o
m
alo
u
s
ev
en
ts
r
elate
d
to
th
e
s
p
ec
if
ics
o
f
r
o
u
tin
g
-
b
ased
attac
k
s
.
R
o
u
tin
g
-
awa
r
e
f
ea
tu
r
es
an
d
p
er
f
o
r
m
an
ce
in
d
icato
r
s
.
A
s
et
o
f
q
u
an
tifia
b
le
in
d
icato
r
s
ar
e
m
o
n
ito
r
ed
to
p
r
o
f
ile
th
e
h
ea
lth
o
f
t
h
e
n
etwo
r
k
a
n
d
id
en
tify
a
n
o
m
alo
u
s
p
atter
n
s
f
r
o
m
wh
ic
h
a
c
h
ar
ac
ter
izatio
n
ca
n
b
e
d
e
v
elo
p
e
d
s
u
ch
as:
a.
E
n
d
-
to
-
e
n
d
d
elay
(
E
2
E
)
: m
ea
s
u
r
es th
e
av
er
a
g
e
laten
cy
f
r
o
m
s
o
u
r
ce
to
d
esti
n
atio
n
.
b.
Pack
et
-
r
elate
d
d
eliv
er
y
in
d
icato
r
(
APR
/d
eliv
er
y
-
r
elat
ed
m
ea
s
u
r
e)
:
u
s
ed
to
r
ef
lect
p
ac
k
et
r
ec
ep
tio
n
/d
eliv
er
y
b
eh
a
v
io
r
(
e.
g
.
,
av
er
a
g
e
p
ac
k
et
r
ec
e
p
tio
n
o
r
d
eliv
er
y
r
atio
b
eh
a
v
io
r
,
d
ep
en
d
in
g
o
n
im
p
lem
en
tatio
n
)
.
c.
Ad
d
itio
n
al
r
o
u
tin
g
-
r
elate
d
o
b
s
er
v
atio
n
s
m
ay
in
clu
d
e
r
o
u
te
r
eq
u
est
f
r
eq
u
en
c
y
,
h
o
p
-
co
u
n
t
ch
an
g
es,
r
etr
an
s
m
is
s
io
n
s
,
an
d
ab
n
o
r
m
al
f
o
r
war
d
i
n
g
p
atter
n
s
wh
en
ap
p
licab
le.
T
o
m
ak
e
th
e
w
o
r
k
-
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
clea
r
(
as
s
h
o
wn
in
Fig
u
r
e
2)
,
we
f
ir
s
t
d
escr
ib
e
th
e
wh
o
le
p
r
o
ce
s
s
f
r
o
m
in
itializatio
n
an
d
f
ea
tu
r
e
m
o
n
ito
r
in
g
to
AI
d
r
iv
en
r
o
u
tin
g
-
awa
r
e
d
etec
tio
n
an
d
r
esp
o
n
s
e
o
p
er
atio
n
s
at
I
DS
lev
el,
we
in
itialize
th
e
n
etwo
r
k
with
p
r
ed
ef
in
ed
n
o
d
e
an
d
m
o
b
ilit
y
p
a
r
a
m
eter
s
f
o
llo
wed
b
y
s
ettin
g
I
DS
r
elate
d
f
ea
tu
r
es
in
p
u
ts
.
T
h
e
s
y
s
tem
s
u
b
s
eq
u
en
tl
y
m
o
n
it
o
r
s
r
o
u
tin
g
/co
m
m
u
n
ic
atio
n
m
etr
ics
(
e.
g
.
,
APR
an
d
E
2
E
)
an
d
r
etain
s
o
b
s
er
v
ed
d
ata
in
to
a
d
ataset
co
n
s
u
m
ed
b
y
AI
al
g
o
r
ith
m
s
.
T
h
e
id
en
tific
atio
n
m
o
d
u
le
u
s
es
AI
d
ec
is
io
n
-
m
ak
in
g
to
id
en
tity
w
h
eth
er
r
o
u
tin
g
b
eh
a
v
io
r
is
b
en
ig
n
o
r
m
alicio
u
s
.
I
f
co
m
m
u
n
icatio
n
is
n
o
r
m
al,
th
e
s
y
s
tem
o
p
er
ates
n
o
r
m
ally
(
r
ewa
r
d
/n
o
r
m
al
d
ata
co
m
m
u
n
i
ca
tio
n
)
.
Oth
er
wis
e,
th
e
m
id
d
lewa
r
e
ca
u
s
es
m
itig
atio
n
to
o
cc
u
r
s
u
c
h
as
b
y
p
ass
in
g
s
u
s
p
icio
u
s
co
m
m
u
n
icatio
n
p
ath
s
in
o
r
d
er
to
r
ed
u
ce
th
e
im
p
ac
t o
f
an
attac
k
an
d
co
n
tin
u
e
to
p
r
o
v
id
e
s
er
v
ic
e.
Fig
u
r
e
2
.
Fra
m
ewo
r
k
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
in
tellig
en
t r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
in
t
eg
r
ated
with
r
o
u
tin
g
a
n
d
I
DS
3
.
2
.
T
hrea
t
m
o
del a
nd
a
s
s
um
ptio
ns
I
n
th
is
p
a
p
er
,
we
ar
e
in
ter
e
s
ted
in
r
o
u
tin
g
-
b
ased
attac
k
s
th
at
lev
er
a
g
e
th
e
d
ec
en
tr
ali
ze
d
r
o
u
te
d
is
co
v
er
y
/m
ain
ten
a
n
ce
p
r
o
to
co
ls
an
d
r
eso
u
r
ce
lim
itatio
n
s
o
f
I
o
T
d
ev
ices.
T
h
e
t
h
r
e
at
m
o
d
el
co
n
s
id
er
s
ex
is
ten
ce
o
f
o
n
e
o
r
m
o
r
e
co
m
p
r
o
m
is
ed
n
o
d
es
th
at
tr
y
to
d
is
r
u
p
t
th
e
r
o
u
tin
g
p
r
o
ce
d
u
r
e,
d
eg
r
ad
e
n
etwo
r
k
p
er
f
o
r
m
an
ce
,
an
d
d
ep
lete
n
o
d
e
r
eso
u
r
ce
s
.
T
ab
le
2
p
r
o
v
i
d
es
an
o
v
er
v
iew
o
f
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
,
th
at
aim
s
to
d
etec
t
r
o
u
tin
g
attac
k
s
b
y
m
o
n
ito
r
in
g
th
e
d
ev
iatio
n
f
r
o
m
r
o
u
tin
g
-
awa
r
e
in
d
icato
r
s
all
wh
ile
en
s
u
r
in
g
n
etwo
r
k
ef
f
icien
cy
an
d
s
ca
lab
i
lity
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
1
6
9
-
2181
2174
T
ab
le
2
.
T
h
r
ea
t m
o
d
el
an
d
ass
u
m
p
tio
n
s
f
o
r
r
o
u
tin
g
-
b
ased
att
ac
k
s
in
I
o
T
n
etwo
r
k
s
N
o
.
Th
r
e
a
t
/
a
ss
u
mp
t
i
o
n
D
e
scri
p
t
i
o
n
I
mp
a
c
t
o
n
I
o
T
r
o
u
t
i
n
g
1
I
n
si
d
e
r
a
t
t
a
c
k
e
r
p
r
e
se
n
c
e
Th
e
a
t
t
a
c
k
e
r
i
s a
ss
u
m
e
d
t
o
o
p
e
r
a
t
e
a
s
a
c
o
m
p
r
o
m
i
se
d
i
n
t
e
r
n
a
l
n
o
d
e
t
h
a
t
a
c
t
i
v
e
l
y
p
a
r
t
i
c
i
p
a
t
e
s
i
n
r
o
u
t
i
n
g
p
r
o
c
e
d
u
r
e
s
a
n
d
e
x
c
h
a
n
g
e
s
c
o
n
t
r
o
l
p
a
c
k
e
t
s,
m
a
k
i
n
g
d
e
t
e
c
t
i
o
n
mo
r
e
c
h
a
l
l
e
n
g
i
n
g
t
h
a
n
e
x
t
e
r
n
a
l
t
h
r
e
a
t
s
[
2
1
]
,
[
2
2
]
.
I
n
c
r
e
a
se
d
d
i
f
f
i
c
u
l
t
y
i
n
d
i
s
t
i
n
g
u
i
sh
i
n
g
mal
i
c
i
o
u
s
b
e
h
a
v
i
o
r
f
r
o
m
l
e
g
i
t
i
ma
t
e
r
o
u
t
i
n
g
a
c
t
i
v
i
t
i
e
s
2
R
o
u
t
i
n
g
ma
n
i
p
u
l
a
t
i
o
n
c
a
p
a
b
i
l
i
t
y
M
a
l
i
c
i
o
u
s
n
o
d
e
s
c
a
n
i
n
j
e
c
t
,
m
o
d
i
f
y
,
o
r
r
e
p
l
a
y
r
o
u
t
i
n
g
c
o
n
t
r
o
l
messa
g
e
s
t
o
a
l
t
e
r
r
o
u
t
e
d
i
s
c
o
v
e
r
y
o
r
mai
n
t
e
n
a
n
c
e
p
r
o
c
e
s
ses,
r
e
su
l
t
i
n
g
i
n
i
n
c
o
r
r
e
c
t
r
o
u
t
i
n
g
p
a
t
h
s
o
r
p
a
c
k
e
t
d
r
o
p
s
[
2
1
]
,
[
2
3
]
.
R
o
u
t
i
n
g
i
n
st
a
b
i
l
i
t
y
,
p
a
c
k
e
t
l
o
ss
,
a
n
d
d
e
g
r
a
d
e
d
n
e
t
w
o
r
k
r
e
l
i
a
b
i
l
i
t
y
3
D
e
n
i
a
l
-
of
-
serv
i
c
e
/
f
l
o
o
d
i
n
g
b
e
h
a
v
i
o
r
A
t
t
a
c
k
e
r
s ma
y
g
e
n
e
r
a
t
e
e
x
c
e
ssi
v
e
r
o
u
t
i
n
g
o
r
d
a
t
a
t
r
a
f
f
i
c
t
o
e
x
h
a
u
st
b
a
n
d
w
i
d
t
h
,
b
u
f
f
e
r
s,
o
r
p
r
o
c
e
ssi
n
g
c
a
p
a
c
i
t
y
,
l
e
a
d
i
n
g
t
o
c
o
n
g
e
st
i
o
n
a
n
d
i
n
c
r
e
a
s
e
d
e
n
d
-
to
-
e
n
d
d
e
l
a
y
[
2
2
]
.
R
e
d
u
c
e
d
t
h
r
o
u
g
h
p
u
t
a
n
d
si
g
n
i
f
i
c
a
n
t
d
e
l
a
y
d
e
g
r
a
d
a
t
i
o
n
4
I
mp
e
r
so
n
a
t
i
o
n
/
s
p
o
o
f
i
n
g
a
t
t
e
m
p
t
s
M
a
l
i
c
i
o
u
s
n
o
d
e
s
ma
y
a
s
su
m
e
f
a
l
se
i
d
e
n
t
i
t
i
e
s
o
r
i
m
p
e
r
s
o
n
a
t
e
l
e
g
i
t
i
m
a
t
e
n
o
d
e
s
t
o
m
i
sl
e
a
d
r
o
u
t
e
d
i
s
c
o
v
e
r
y
o
r
g
a
i
n
u
n
a
u
t
h
o
r
i
z
e
d
r
o
u
t
i
n
g
i
n
f
l
u
e
n
c
e
[
6
]
.
I
n
c
o
r
r
e
c
t
r
o
u
t
i
n
g
d
e
c
i
si
o
n
s
a
n
d
c
o
m
p
r
o
m
i
se
d
t
r
u
s
t
r
e
l
a
t
i
o
n
s
h
i
p
s
5
En
e
r
g
y
d
e
p
l
e
t
i
o
n
i
n
t
e
n
t
G
i
v
e
n
t
h
e
l
i
m
i
t
e
d
b
a
t
t
e
r
y
c
a
p
a
c
i
t
y
o
f
I
o
T
d
e
v
i
c
e
s
,
a
t
t
a
c
k
e
r
s
ma
y
f
o
r
c
e
f
r
e
q
u
e
n
t
r
e
t
r
a
n
sm
i
ssi
o
n
s
o
r
r
o
u
t
e
r
e
p
a
i
r
s
t
o
a
c
c
e
l
e
r
a
t
e
e
n
e
r
g
y
c
o
n
su
mp
t
i
o
n
[
2
3
]
.
P
r
e
mat
u
r
e
n
o
d
e
f
a
i
l
u
r
e
a
n
d
r
e
d
u
c
e
d
n
e
t
w
o
r
k
l
i
f
e
t
i
m
e
6
D
y
n
a
mi
c
a
n
d
i
mp
e
r
f
e
c
t
l
a
b
e
l
a
ss
u
m
p
t
i
o
n
A
l
t
h
o
u
g
h
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
c
a
n
b
e
a
p
p
l
i
e
d
o
f
f
l
i
n
e
,
t
h
e
o
p
e
r
a
t
i
o
n
a
l
e
n
v
i
r
o
n
m
e
n
t
i
s
d
y
n
a
mi
c
,
a
n
d
a
t
t
a
c
k
l
a
b
e
l
s ma
y
n
o
t
b
e
p
e
r
f
e
c
t
l
y
k
n
o
w
n
d
u
r
i
n
g
r
u
n
t
i
m
e
,
r
e
q
u
i
r
i
n
g
r
o
b
u
st
g
e
n
e
r
a
l
i
z
a
t
i
o
n
[
2
1
]
,
[
2
2
]
.
N
e
e
d
f
o
r
a
d
a
p
t
i
v
e
a
n
d
r
e
si
l
i
e
n
t
A
I
-
b
a
sed
d
e
t
e
c
t
i
o
n
m
o
d
e
l
s
4.
P
RO
P
O
SE
D
I
N
T
E
L
L
I
G
E
N
T
RO
UT
I
NG
-
B
A
SE
D
A
T
T
ACK
DE
T
E
C
T
I
O
N
F
RA
M
E
WO
RK
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
p
r
o
p
o
s
ed
in
tellig
en
t
r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
f
r
a
m
ewo
r
k
f
o
r
r
o
u
tin
g
-
awa
r
e
b
ased
m
o
n
ito
r
i
n
g
co
m
b
in
ed
with
AI
tech
n
iq
u
es
th
at
d
etec
ts
m
alicio
u
s
b
eh
av
io
r
s
in
I
o
T
n
etwo
r
k
s
.
T
h
e
f
r
am
ewo
r
k
is
in
te
n
d
ed
to
ta
k
e
ad
v
an
tag
e
o
f
an
o
m
alies
i
n
r
o
u
tin
g
f
ea
tu
r
es
in
d
u
ce
d
b
y
an
attac
k
,
wh
ile
p
r
eser
v
in
g
e
f
f
ec
tiv
e
n
etwo
r
k
in
g
o
p
er
atio
n
wh
en
th
e
n
etwo
r
k
to
p
o
lo
g
y
ch
a
n
g
es a
n
d
th
e
r
es
o
u
r
ce
s
ar
e
lim
ited
.
4
.
1
.
F
r
a
m
ewo
r
k
o
v
er
v
iew
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
o
p
er
ates
in
a
d
ec
e
n
tr
alize
d
m
u
lti
-
h
o
p
I
o
T
en
v
ir
o
n
m
en
t
wh
er
e
n
o
d
es
co
m
m
u
n
icate
wir
eless
ly
an
d
c
o
o
p
er
ate
to
f
o
r
war
d
d
ata
p
ac
k
ets
u
s
in
g
an
o
n
-
d
em
an
d
r
o
u
tin
g
p
r
o
to
c
o
l.
Du
e
to
th
e
ab
s
en
ce
o
f
ce
n
tr
alize
d
co
n
tr
o
l
an
d
th
e
d
y
n
am
ic
n
atu
r
e
o
f
n
o
d
e
m
o
b
ilit
y
,
r
o
u
tin
g
b
eh
av
io
r
b
ec
o
m
es
a
cr
itical
in
d
icato
r
o
f
n
etwo
r
k
in
teg
r
ity
an
d
s
ec
u
r
ity
.
T
h
e
f
r
am
ew
o
r
k
in
te
g
r
ates
I
DS
in
to
th
e
r
o
u
tin
g
p
r
o
c
ess
,
th
er
ef
o
r
e,
th
at
th
e
r
o
u
tin
g
an
d
co
m
m
u
n
icatio
n
b
eh
av
i
o
r
ca
n
b
e
m
o
n
ito
r
ed
th
r
o
u
g
h
o
u
t.
Du
r
in
g
n
o
r
m
al
an
d
attac
k
s
ce
n
ar
io
s
,
n
etwo
r
k
o
p
er
atio
n
al
d
ata
ar
e
lo
g
g
ed
f
r
o
m
wh
ich
a
r
o
u
tin
g
-
awa
r
e
d
ataset
is
b
u
ilt.
Ar
tific
ial
in
tellig
en
ce
m
o
d
els
ar
e
th
en
u
s
ed
to
lear
n
p
atter
n
s
o
f
n
o
r
m
al
an
d
m
alicio
u
s
r
o
u
tin
g
b
eh
av
io
r
.
W
h
en
e
v
er
a
b
n
o
r
m
al
ity
is
d
etec
ted
,
th
e
f
r
am
ewo
r
k
tak
es
co
r
r
ec
tiv
e
ac
tio
n
s
to
b
y
p
ass
s
u
s
p
icio
u
s
p
ath
s
o
r
is
o
late
m
alicio
u
s
n
o
d
es
an
d
d
ec
r
ea
s
e
attac
k
th
r
ea
ts
an
d
k
ee
p
n
etwo
r
k
co
n
n
ec
tiv
ity
an
d
p
e
r
f
o
r
m
an
ce
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
f
r
am
ew
o
r
k
.
4
.
2
.
Ro
uting
m
et
rics e
x
t
r
a
ct
io
n
I
n
o
r
d
er
to
ac
h
ie
v
e
ef
f
icien
t
r
o
u
tin
g
attac
k
d
etec
tio
n
in
I
o
T
n
etwo
r
k
s
,
t
h
e
f
r
am
ewo
r
k
u
s
e
s
a
well
-
ch
o
s
en
s
et
o
f
r
o
u
tin
g
an
d
n
o
d
e
-
f
ea
tu
r
e,
wh
ich
a
r
e
d
esig
n
ed
to
ca
p
tu
r
e
v
ar
iatio
n
s
in
co
m
m
u
n
icatio
n
b
e
h
av
io
r
an
d
r
eso
u
r
ce
co
n
s
u
m
p
tio
n
.
T
h
e
f
ea
tu
r
es
ar
e
co
n
s
tan
tly
m
o
n
ito
r
ed
wh
ile
in
o
p
e
r
atio
n
,
a
n
d
th
ey
a
r
e
ess
en
tial
to
d
etec
t
th
e
an
o
m
alo
u
s
r
o
u
ti
n
g
ac
tiv
ities
im
p
o
s
ed
b
y
th
e
m
alicio
u
s
n
o
d
es.
B
y
m
o
n
ito
r
i
n
g
th
e
c
h
an
g
es
in
p
ac
k
et
p
ass
in
g
,
r
o
u
tin
g
p
ath
,
tr
an
s
m
is
s
io
n
tim
e
an
d
e
n
e
r
g
y
c
o
n
s
u
m
p
tio
n
,
a
f
ea
tu
r
e
s
et
is
co
m
p
iled
to
r
ep
r
esen
t
Qo
S
d
eter
io
r
atio
n
a
s
well
as
s
ec
u
r
ity
r
is
k
s
.
T
h
e
r
o
u
tin
g
-
awa
r
e
m
etr
ics
u
s
ed
a
s
th
e
in
p
u
ts
o
f
AI
-
b
ased
d
etec
tio
n
m
o
d
els ar
e
s
h
o
wn
in
T
ab
le
3
.
T
ab
le
3
.
R
o
u
tin
g
-
awa
r
e
f
ea
tu
r
e
s
et
u
s
ed
f
o
r
attac
k
d
etec
tio
n
F
e
a
t
u
r
e
D
e
scri
p
t
i
o
n
S
e
c
u
r
i
t
y
R
e
l
e
v
a
n
c
e
P
a
c
k
e
t
L
o
ss
R
a
t
i
o
o
f
l
o
st
p
a
c
k
e
t
s
d
u
r
i
n
g
t
r
a
n
smiss
i
o
n
H
i
g
h
p
a
c
k
e
t
l
o
ss i
n
d
i
c
a
t
e
s
b
l
a
c
k
h
o
l
e
o
r
f
l
o
o
d
i
n
g
a
t
t
a
c
k
s
H
o
p
C
o
u
n
t
N
u
mb
e
r
o
f
i
n
t
e
r
me
d
i
a
t
e
f
o
r
w
a
r
d
i
n
g
n
o
d
e
s
A
b
n
o
r
ma
l
h
o
p
c
o
u
n
t
s
su
g
g
e
s
t
r
o
u
t
i
n
g
man
i
p
u
l
a
t
i
o
n
En
d
-
to
-
En
d
D
e
l
a
y
A
v
e
r
a
g
e
p
a
c
k
e
t
d
e
l
i
v
e
r
y
l
a
t
e
n
c
y
I
n
c
r
e
a
se
d
d
e
l
a
y
r
e
f
l
e
c
t
s c
o
n
g
e
st
i
o
n
o
r
mal
i
c
i
o
u
s r
e
r
o
u
t
i
n
g
En
e
r
g
y
C
o
n
su
mp
t
i
o
n
En
e
r
g
y
u
sa
g
e
d
u
r
i
n
g
r
o
u
t
i
n
g
a
n
d
f
o
r
w
a
r
d
i
n
g
R
a
p
i
d
d
e
p
l
e
t
i
o
n
i
n
d
i
c
a
t
e
s
e
n
e
r
g
y
e
x
h
a
u
st
i
o
n
a
t
t
a
c
k
s
4
.
3
.
AI
mo
del descript
io
n
T
o
e
f
f
e
cti
v
el
y
a
n
al
y
ze
r
o
u
t
in
g
-
aw
ar
e
f
ea
t
u
r
es
a
n
d
d
ete
ct
c
o
m
p
le
x
att
ac
k
p
att
er
n
s
,
tw
o
n
eu
r
al
n
et
wo
r
k
m
o
d
els
ar
e
em
p
l
o
y
e
d
:
f
ee
d
f
o
r
war
d
n
e
u
r
al
n
etw
o
r
k
(
FF
NN
)
an
d
C
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
et
wo
r
k
(
C
NN
)
.
T
h
es
e
m
o
d
els
c
o
m
p
l
em
en
t
ea
c
h
o
t
h
e
r
in
h
a
n
d
li
n
g
s
t
r
u
ct
u
r
e
d
r
o
u
ti
n
g
m
e
tr
ics
a
n
d
l
ea
r
n
i
n
g
n
o
n
-
li
n
ea
r
r
el
ati
o
n
s
h
i
p
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
n
tellig
en
t ro
u
tin
g
-
b
a
s
ed
a
tta
ck
d
etec
tio
n
in
in
tern
et
o
f th
in
g
s
n
etw
o
r
ks u
s
in
g
…
(
Hu
d
a
S
a
lo
o
m
S
u
lta
n
)
2175
4
.
3
.
1
.
M
o
del
a
rc
hite
ct
ure
a
nd
f
ea
t
ure
s
elec
t
io
n
T
o
m
o
d
el
I
o
T
r
o
u
tin
g
b
eh
av
i
o
r
,
wh
ich
is
d
y
n
am
ic
an
d
n
o
n
-
lin
ea
r
,
we
em
p
l
o
y
two
n
eu
r
a
l
n
etwo
r
k
m
o
d
els:
th
e
FF
NN
an
d
C
NN
.
T
h
e
FF
NN
m
o
d
el
ca
n
h
elp
lea
r
n
s
tr
u
ctu
r
e
d
r
o
u
tin
g
m
etr
ics,
wh
ile
C
NN
s
er
v
es
to
en
h
an
ce
th
e
f
ea
tu
r
e
ab
s
tr
ac
t
io
n
an
d
g
en
er
atio
n
in
o
r
d
er
to
en
co
d
e
c
o
m
p
lex
r
elatio
n
s
o
f
r
o
u
tin
g
f
ea
t
u
r
es.
T
h
e
FF
NN
o
v
er
all
is
co
m
p
o
s
ed
o
f
an
in
p
u
t
lay
er
co
n
s
is
tin
g
o
f
th
e
e
x
tr
ac
ted
r
o
u
tin
g
m
et
r
ics,
a
f
ew
h
id
d
en
lay
er
s
f
o
r
f
ea
t
u
r
e
tr
a
n
s
f
o
r
m
atio
n
an
d
co
n
clu
s
io
n
a
b
in
ar
y
class
if
icatio
n
(
n
o
r
m
al/m
alicio
u
s
)
o
u
tp
u
t
lay
er
.
T
h
e
C
NN
Mo
d
el
is
b
u
ilt
b
y
co
n
ca
ten
atin
g
th
e
c
o
n
v
o
lu
tio
n
al
lay
e
r
s
with
th
e
f
u
ll
y
co
n
n
ec
ted
la
y
er
wh
ich
ca
n
lea
r
n
t
h
e
h
ig
h
-
lev
el
f
ea
tu
r
es
o
f
d
ata
p
atter
n
in
d
ig
ital
r
o
u
tin
g
.
T
h
e
s
elec
ted
r
o
u
tin
g
f
ea
tu
r
es
ar
e
n
o
r
m
alize
d
a
n
d
p
r
ep
r
o
ce
s
s
ed
p
r
io
r
to
th
e
tr
ain
i
n
g
in
o
r
d
er
t
o
im
p
r
o
v
e
co
n
v
er
g
en
ce
a
n
d
m
itig
ate
s
o
m
e
b
iases
.
Featu
r
e
s
elec
tio
n
f
o
c
u
s
es
o
n
t
r
an
s
it
-
lev
el
au
g
m
e
n
ted
f
ea
tu
r
e
s
th
at
ar
e
d
i
r
ec
tly
af
f
ec
te
d
b
y
m
alicio
u
s
b
eh
av
i
o
r
an
d
r
em
ain
v
is
ib
le
o
v
er
en
cr
y
p
ted
tr
af
f
ic.
4
.
3
.
2
.
T
ra
ini
ng
pro
ce
s
s
T
r
ain
in
g
is
p
e
r
f
o
r
m
ed
in
an
o
f
f
lin
e
m
a
n
n
er
o
n
d
atasets
o
b
tain
ed
f
r
o
m
th
e
s
im
u
lated
I
o
T
n
etwo
r
k
en
v
ir
o
n
m
en
ts
with
n
o
r
m
al
an
d
r
o
u
tin
g
-
b
ased
attac
k
s
ce
n
ar
i
o
s
.
Su
p
er
v
is
ed
lear
n
in
g
is
u
s
ed
h
er
e
th
e
r
o
u
tin
g
b
eh
av
io
r
s
am
p
les
a
r
e
lab
ele
d
with
o
b
s
er
v
e
d
attac
k
f
ea
t
u
r
es.
T
h
e
m
o
d
els
ar
e
tr
ain
e
d
b
y
g
r
ad
ien
t
-
b
ased
o
p
tim
izatio
n
to
m
in
im
ize
th
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
b
etwe
en
p
r
ed
icted
an
d
tar
g
et
o
u
tp
u
t.
T
h
e
n
eu
r
al
n
etwo
r
k
co
m
p
u
tatio
n
is
ex
p
r
e
s
s
ed
as:
=
(
)
(
1
)
=
×
+
(
2
)
=
−
(
3
)
=
∑
=
1
(
)
2
(
4
)
Dete
ctio
n
ac
cu
r
ac
y
is
ca
lcu
lat
ed
as:
=
+
+
+
+
×
100%
(
5
)
4
.
3
.
3
.
Alg
o
rit
hm
w
o
rkf
lo
w
T
h
e
o
p
er
atio
n
al
wo
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
is
s
u
m
m
ar
ized
in
alg
o
r
ith
m
.
T
h
e
alg
o
r
ith
m
o
u
tlin
es
th
e
s
tep
s
f
r
o
m
n
et
wo
r
k
in
itializatio
n
an
d
r
o
u
ti
n
g
d
ata
co
llectio
n
to
AI
-
b
a
s
ed
d
etec
tio
n
an
d
m
itig
atio
n
.
Alg
o
r
ith
m
1
.
I
n
tellig
en
t r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
Input: IoT network parameters, routing metrics
Output: Attack detection decision and routing mitigation
1: Initialize IoT network with (N) mobile nodes and routing protocol (AODV).
2: Configure IDS parameters and enable routing monitoring.
3: Collect routing metrics (packet loss, hop count, E2E delay, energy consumption).
4: Preprocess collected data and construct feature vectors.
5: Apply trained AI models (FFNN/CNN) to classify routing behavior.
6: If behavior = normal then
7: Continue data transmission.
8: Else
9: Bypass suspicious routes
10: Isolate malicious nodes.
11: end if
12: Update routing tables and continue monitoring.
5.
RE
SU
L
T
S AN
D
P
E
RF
O
RM
ANCE
E
VA
L
UAT
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
e
x
p
er
im
en
tal
r
esu
lts
an
d
p
er
f
o
r
m
an
ce
e
v
alu
atio
n
o
f
th
e
p
r
o
p
o
s
e
d
in
tellig
en
t
r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
f
r
am
ewo
r
k
.
T
h
e
ev
alu
atio
n
f
o
c
u
s
es
o
n
ass
ess
in
g
b
o
th
attac
k
d
etec
tio
n
ef
f
ec
tiv
e
n
ess
an
d
r
o
u
tin
g
p
er
f
o
r
m
a
n
ce
p
r
eser
v
atio
n
u
n
d
e
r
d
y
n
am
ic
I
o
T
n
etwo
r
k
co
n
d
itio
n
s
.
5
.
1
.
E
x
perim
ent
a
l set
up
a
nd
s
im
ula
t
io
n pa
ra
m
et
er
s
T
h
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
test
ed
u
s
in
g
NS
-
2
.
4
also
u
tili
ze
n
etwo
r
k
s
im
u
latio
n
s
to
s
im
u
late
an
I
o
T
s
p
ac
e
with
m
u
lti
-
h
o
p
wir
eless
co
m
m
u
n
icat
io
n
.
T
h
e
n
etwo
r
k
co
n
s
is
ted
o
f
m
o
b
ile
I
o
T
n
o
d
es
wh
ich
wer
e
eq
u
ip
p
ed
with
A
ODV
r
o
u
tin
g
th
at
is
a
p
o
p
u
lar
r
o
u
tin
g
p
r
o
to
co
l
i
n
d
is
tr
ib
u
te
d
I
o
T
an
d
MA
NE
T
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
1
6
9
-
2181
2176
co
n
tex
ts
.
T
h
e
em
u
latio
n
o
f
a
b
lack
h
o
le
Do
S
was
co
n
d
u
ct
ed
b
y
ad
d
i
n
g
f
o
u
r
m
alicio
u
s
n
o
d
es
(
th
ey
we
r
e
ac
tiv
ated
with
I
P
tab
les
r
u
les
th
at
m
o
d
if
ied
t
h
e
r
o
u
tin
g
,
p
r
ev
en
tin
g
t
h
e
p
ac
k
et
f
o
r
war
d
)
.
Sev
er
al
n
etwo
r
k
s
izes
an
d
d
if
f
er
en
t
m
o
b
ilit
y
r
ates
wer
e
ex
p
lo
ited
to
in
v
esti
g
ate
r
o
b
u
s
tn
ess
u
n
d
er
v
ar
io
u
s
o
p
er
atio
n
al
s
ce
n
ar
io
s
.
Fo
r
r
ep
r
o
d
u
cib
ilit
y
r
ea
s
o
n
s
an
d
ex
p
licit
s
p
ec
if
ica
tio
n
,
th
e
m
ain
s
im
u
latio
n
p
ar
a
m
eter
s
u
s
ed
in
th
is
wo
r
k
ar
e
lis
ted
in
T
a
b
le
4
.
T
ab
le
4
.
Simu
latio
n
p
ar
am
eter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
N
e
t
w
o
r
k
T
y
p
e
W
i
r
e
l
e
ss Se
n
s
o
r
/
I
o
T
N
e
t
w
o
r
k
N
u
mb
e
r
o
f
N
o
d
e
s
2
0
,
3
0
,
5
0
S
i
mu
l
a
t
i
o
n
A
r
e
a
3
0
0
0
m
×
3
0
0
0
m
R
o
u
t
i
n
g
P
r
o
t
o
c
o
l
AODV
A
t
t
a
c
k
T
y
p
e
D
o
S
(
B
l
a
c
k
h
o
l
e
)
I
D
S
Ty
p
e
C
o
o
p
e
r
a
t
i
v
e
Tr
a
n
sm
i
ssi
o
n
R
a
n
g
e
5
0
0
m
P
a
c
k
e
t
S
i
z
e
1
0
2
4
b
y
t
e
s
B
a
n
d
w
i
d
t
h
4
M
b
p
s
Tr
a
f
f
i
c
Ty
p
e
TC
P
M
o
b
i
l
i
t
y
M
o
d
e
l
R
a
n
d
o
m
N
o
d
e
S
p
e
e
d
s
1
0
,
2
0
,
3
0
,
4
0
,
5
0
S
i
mu
l
a
t
i
o
n
Ti
me
3
0
0
s
C
h
a
n
n
e
l
F
r
e
q
u
e
n
c
y
2
.
4
G
H
z
5
.
2
.
AI
mo
del t
ra
ini
ng
co
nfi
g
ura
t
io
n
T
h
e
s
im
u
latio
n
r
esu
lts
s
h
o
w
t
h
at
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
was
ab
le
to
d
etec
t
k
n
o
wn
attac
k
s
with
h
ig
h
ac
cu
r
ac
y
,
a
n
d
to
p
r
o
v
i
d
e
in
ter
esti
n
g
in
s
ig
h
ts
wh
en
test
ed
ag
ain
s
t
ar
tific
ial
n
eu
r
al
n
etwo
r
k
m
o
d
els
n
am
ely
FF
NN
an
d
C
N
N
tr
ain
ed
o
n
r
o
u
tin
g
-
awa
r
e
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
s
im
u
lated
I
o
T
tr
af
f
ic.
T
h
e
ab
o
v
e
in
f
o
r
m
atio
n
r
e
p
r
esen
ts
th
e
t
r
a
in
in
g
p
h
ase
u
s
in
g
MA
T
L
AB
,
wh
er
e
s
u
p
er
v
is
ed
lear
n
in
g
is
u
s
ed
with
K
-
Fo
ld
cr
o
s
s
-
v
alid
atio
n
to
av
o
id
o
v
e
r
-
f
itti
n
g
an
d
im
p
r
o
v
e
g
e
n
er
aliza
tio
n
.
T
h
e
s
ettin
g
o
f
tr
ain
in
g
an
d
v
alid
atio
n
A
I
m
o
d
els is
s
h
o
wn
in
T
ab
le
5
.
T
ab
le
5
.
AI
m
o
d
el
tr
ain
i
n
g
co
n
f
ig
u
r
atio
n
P
a
r
a
me
t
e
r
F
F
N
N
c
o
n
f
i
g
u
r
a
t
i
o
n
C
N
N
c
o
n
f
i
g
u
r
a
t
i
o
n
I
n
p
u
t
f
e
a
t
u
r
e
s
R
o
u
t
i
n
g
-
a
w
a
r
e
m
e
t
r
i
c
s
R
o
u
t
i
n
g
-
a
w
a
r
e
m
e
t
r
i
c
s
H
i
d
d
e
n
l
a
y
e
r
s
2
D
e
n
se
La
y
e
r
s
2
C
o
n
v
o
l
u
t
i
o
n
L
a
y
e
r
s +
F
u
l
l
y
C
o
n
n
e
c
t
e
d
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
R
e
LU
R
e
LU
O
p
t
i
mi
z
e
r
A
d
a
m
A
d
a
m
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
0
1
0
.
0
0
1
B
a
t
c
h
si
z
e
32
32
Ep
o
c
h
s
1
0
0
1
0
0
V
a
l
i
d
a
t
i
o
n
me
t
h
o
d
K
-
F
o
l
d
C
r
o
ss V
a
l
i
d
a
t
i
o
n
K
-
F
o
l
d
C
r
o
ss V
a
l
i
d
a
t
i
o
n
O
u
t
p
u
t
l
a
y
e
r
S
i
g
m
o
i
d
S
o
f
t
ma
x
Tr
a
i
n
i
n
g
e
n
v
i
r
o
n
m
e
n
t
M
A
TLA
B
M
A
TLA
B
T
h
e
AI
m
o
d
el
s
ettin
g
s
wer
e
ch
o
s
en
th
o
u
g
h
tf
u
lly
to
ac
h
i
ev
e
a
b
alan
ce
b
etwe
en
th
e
a
cc
u
r
ac
y
o
f
d
etec
tio
n
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
in
d
y
n
am
ic
I
o
T
r
o
u
ti
n
g
.
T
h
e
R
eL
U
ac
tiv
atio
n
f
u
n
c
tio
n
was
u
tili
ze
d
to
en
h
an
ce
co
n
v
er
g
en
ce
p
er
f
o
r
m
an
ce
an
d
th
e
Ad
am
o
p
tim
izer
was
u
tili
ze
d
to
en
h
an
ce
th
e
tr
ain
in
g
s
tab
ilit
y
an
d
m
in
im
ize
co
m
p
le
x
ity
in
o
p
tim
izatio
n
.
K
-
Fo
ld
cr
o
s
s
v
alid
atio
n
was
u
s
ed
to
r
ed
u
ce
o
v
er
f
itti
n
g
an
d
en
h
an
ce
th
e
ab
ilit
y
o
f
th
e
tr
ai
n
ed
m
o
d
els to
g
en
er
alize
.
5
.
3
.
At
t
a
c
k
det
ec
t
io
n per
f
o
r
m
a
nce
T
h
is
s
u
b
s
ec
tio
n
a
n
aly
s
es
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
f
o
r
d
etec
tio
n
o
f
r
o
u
ti
n
g
attac
k
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
d
etec
tio
n
was
m
ea
s
u
r
ed
with
s
tan
d
ar
d
class
if
icatio
n
m
ea
s
u
r
es
s
u
ch
as
Acc
u
r
ac
y
,
MSE
,
MA
E
,
R
MSE
an
d
ex
ec
u
tio
n
tim
e.
FF
NN
an
d
C
NN
m
o
d
els
wer
e
tr
ain
e
d
to
q
u
an
tify
th
e
d
etec
tio
n
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
T
h
e
class
if
icatio
n
r
esu
lts
with
th
e
ac
cu
r
ac
y
r
ate
s
,
er
r
o
r
m
etr
ics an
d
tim
e
elap
s
ed
ar
e
p
r
o
v
id
ed
in
T
ab
le
6
.
T
ab
le
6
.
Dete
ctio
n
p
er
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
b
etwe
en
FF
NN
an
d
C
NN
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%)
M
S
E
M
A
E
R
M
S
E
Ex
e
c
u
t
i
o
n
T
i
me
(
s)
F
F
N
N
8
2
.
7
6
0
.
7
0
6
9
0
.
3
2
7
6
0
.
8
4
0
8
18
C
N
N
8
5
.
7
6
0
.
9
8
2
8
0
.
3
2
7
6
0
.
9
9
1
3
17
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
I
n
tellig
en
t ro
u
tin
g
-
b
a
s
ed
a
tta
ck
d
etec
tio
n
in
in
tern
et
o
f th
in
g
s
n
etw
o
r
ks u
s
in
g
…
(
Hu
d
a
S
a
lo
o
m
S
u
lta
n
)
2177
R
esu
lts
s
h
o
w
th
at
b
o
th
m
o
d
e
ls
ar
e
ca
p
ab
le
o
f
d
etec
tin
g
r
o
u
tin
g
-
b
ased
attac
k
s
;
h
o
wev
e
r
,
th
e
C
NN
m
o
d
el
o
u
tp
er
f
o
r
m
e
d
th
e
FF
NN
m
o
d
el
in
ter
m
s
o
f
d
etec
tio
n
ac
cu
r
ac
y
an
d
e
x
ec
u
tio
n
tim
e.
T
h
e
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
f
th
e
C
NN
m
o
d
el
is
attr
ib
u
ted
to
its
ab
ilit
y
t
o
lear
n
m
o
r
e
d
is
cr
im
in
ativ
e
an
d
in
v
ar
ia
n
t
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
,
as
well
a
s
ca
p
tu
r
in
g
co
m
p
lex
co
r
r
elatio
n
s
am
o
n
g
r
o
u
tin
g
-
awa
r
e
m
etr
ics.
Fig
u
r
e
3
illu
s
tr
ates
th
e
d
etec
tio
n
ac
cu
r
ac
y
c
o
m
p
ar
is
o
n
b
etwe
e
n
th
e
FF
NN
an
d
C
NN
m
o
d
els
o
v
er
t
h
e
s
im
u
latio
n
tim
e,
h
ig
h
lig
h
tin
g
th
e
f
aster
co
n
v
er
g
en
ce
an
d
im
p
r
o
v
ed
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
t
h
e
C
NN
m
o
d
el.
Alth
o
u
g
h
t
h
e
C
NN
m
o
d
el
p
r
o
d
u
ce
d
s
lig
h
tly
h
ig
h
er
MSE
an
d
R
MSE
v
alu
es
co
m
p
a
r
ed
with
th
e
FF
NN
m
o
d
el,
it a
ch
iev
ed
s
u
p
er
io
r
class
if
icatio
n
ac
cu
r
ac
y
an
d
lo
wer
ex
ec
u
tio
n
tim
e.
T
h
is
b
eh
av
io
r
m
ay
o
cc
u
r
b
ec
au
s
e
MSE
r
e
f
lects
th
e
m
ag
n
itu
d
e
o
f
p
r
e
d
ictio
n
er
r
o
r
s
,
wh
er
ea
s
class
if
icatio
n
ac
c
u
r
ac
y
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
tly
class
if
ied
s
am
p
les.
T
h
er
ef
o
r
e,
d
es
p
ite
th
e
s
lig
h
tly
h
ig
h
er
er
r
o
r
m
etr
ics,
th
e
C
NN
m
o
d
el
was
co
n
s
id
er
ed
m
o
r
e
e
f
f
ec
tiv
e
f
o
r
r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
d
u
e
to
its
s
tr
o
n
g
e
r
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
p
ab
ilit
y
an
d
im
p
r
o
v
e
d
a
d
ap
t
ab
ilit
y
u
n
d
er
d
y
n
a
m
ic
I
o
T
r
o
u
tin
g
co
n
d
itio
n
s
.
T
h
e
s
lig
h
tly
h
ig
h
er
MSE
v
alu
es
m
ay
b
e
attr
ib
u
ted
to
th
e
s
en
s
itiv
ity
o
f
C
NN
f
ea
tu
r
e
r
ep
r
e
s
en
tatio
n
s
to
a
lim
ited
n
u
m
b
er
o
f
m
is
class
if
ied
s
am
p
les with
lar
g
er
p
r
ed
ictio
n
d
ev
iatio
n
s
.
Fig
u
r
e
3
.
Dete
ctio
n
ac
c
u
r
ac
y
c
o
m
p
ar
is
o
n
b
etwe
en
FF
NN
an
d
C
NN
m
o
d
els o
v
er
s
im
u
latio
n
tim
e
5
.
4
.
Ro
uting
perf
o
rma
nce
a
na
ly
s
i
s
B
ey
o
n
d
d
etec
tio
n
ac
c
u
r
ac
y
,
i
t
is
es
s
en
tial
to
an
aly
ze
th
e
im
p
ac
t
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
o
n
r
o
u
tin
g
p
er
f
o
r
m
a
n
ce
.
T
h
is
s
u
b
s
ec
tio
n
ex
am
i
n
es
en
d
-
to
-
en
d
d
elay
an
d
p
ac
k
et
l
o
s
s
r
ate,
wh
ich
ar
e
c
r
itical
in
d
icato
r
s
o
f
n
etwo
r
k
ef
f
icien
cy
an
d
r
elia
b
ilit
y
.
T
h
e
q
u
an
tit
ativ
e
r
o
u
tin
g
p
er
f
o
r
m
an
ce
m
et
r
ics
o
b
tain
ed
b
e
f
o
r
e
an
d
af
ter
ap
p
l
y
in
g
t
h
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
ar
e
s
u
m
m
ar
ized
in
T
ab
le
7
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
s
ig
n
if
ican
tly
r
ed
u
ce
d
e
n
d
-
to
-
en
d
d
elay
an
d
p
ac
k
et
lo
s
s
wh
ile
im
p
r
o
v
in
g
en
er
g
y
ef
f
icie
n
cy
u
n
d
e
r
r
o
u
tin
g
-
b
ased
attac
k
s
ce
n
ar
io
s
.
T
ab
le
7
.
R
o
u
tin
g
p
er
f
o
r
m
a
n
ce
with
an
d
with
o
u
t
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
M
e
t
r
i
c
W
i
t
h
o
u
t
D
e
t
e
c
t
i
o
n
P
r
o
p
o
se
d
F
r
a
m
e
w
o
r
k
En
d
-
to
-
En
d
D
e
l
a
y
(
ms)
2
4
5
1
4
8
P
a
c
k
e
t
L
o
ss
R
a
t
e
(
%)
29
8
En
e
r
g
y
C
o
n
su
mp
t
i
o
n
(
J)
1
.
1
2
0
.
6
4
T
h
e
r
esu
lts
o
b
tain
ed
r
ev
ea
l
th
at
attac
k
s
b
ased
o
n
r
o
u
tin
g
h
a
v
e
a
s
er
io
u
s
im
p
ac
t
o
n
th
e
r
el
iab
ilit
y
o
f
co
m
m
u
n
icatio
n
s
an
d
t
h
e
co
n
s
u
m
p
tio
n
o
f
r
eso
u
r
ce
s
in
d
ec
e
n
tr
alize
d
I
o
T
n
etwo
r
k
s
.
Up
o
n
th
e
im
p
lem
en
tatio
n
o
f
th
e
p
r
o
p
o
s
ed
r
o
u
tin
g
-
awa
r
e
AI
-
b
ased
d
etec
tio
n
f
r
am
ewo
r
k
,
th
e
r
ate
o
f
p
ac
k
et
lo
s
s
d
r
o
p
p
ed
to
8
p
er
ce
n
t,
as
co
m
p
ar
ed
t
o
2
9
p
er
ce
n
t,
a
n
d
t
h
e
o
v
er
all
en
d
-
to
-
e
n
d
d
elay
d
r
o
p
p
ed
to
1
4
8
m
s
,
co
m
p
ar
e
d
to
2
4
5
m
s
.
Mo
r
e
o
v
er
,
it
also
g
r
ea
tly
en
h
an
ce
d
th
e
co
n
s
u
m
p
tio
n
o
f
en
er
g
y
b
ec
au
s
e
o
f
th
e
m
in
im
izatio
n
o
f
m
alicio
u
s
r
o
u
tin
g
p
r
o
ce
s
s
es
an
d
u
n
n
ec
ess
ar
y
r
etr
an
s
m
is
s
io
n
.
T
h
ese
r
esu
lts
p
r
o
v
e
th
at
th
e
s
u
g
g
ested
f
r
am
ewo
r
k
ca
n
b
e
s
u
cc
ess
f
u
lly
u
s
ed
to
b
alan
c
e
th
e
attac
k
d
etec
tio
n
ca
p
ab
ilit
i
es
with
th
e
r
o
u
tin
g
p
e
r
f
o
r
m
a
n
ce
m
ain
ten
a
n
ce
in
d
y
n
am
ic
I
o
T
s
y
s
tem
s
.
T
o
ev
alu
ate
th
e
im
p
ac
t
o
f
n
o
d
e
m
o
b
ilit
y
o
n
r
o
u
tin
g
p
er
f
o
r
m
an
ce
in
I
o
T
n
etwo
r
k
s
,
th
e
ef
f
ec
ts
o
f
v
ar
y
in
g
n
o
d
e
m
o
b
ilit
y
s
p
ee
d
s
o
n
en
d
-
to
-
en
d
d
elay
an
d
p
ac
k
et
lo
s
s
r
ate
wer
e
an
aly
ze
d
.
T
h
ese
m
etr
ics
p
r
o
v
id
e
cr
itical
in
s
ig
h
t
in
to
n
etwo
r
k
s
tab
ilit
y
an
d
co
m
m
u
n
icati
o
n
r
eliab
ilit
y
u
n
d
e
r
d
y
n
am
i
c
co
n
d
itio
n
s
.
T
h
e
co
r
r
esp
o
n
d
in
g
p
er
f
o
r
m
an
ce
tr
en
d
s
ar
e
illu
s
tr
ated
in
Fig
u
r
es
4
an
d
5
,
r
esp
ec
tiv
ely
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
2
1
6
9
-
2181
2178
Fig
u
r
e
4
.
E
n
d
-
to
-
en
d
d
elay
v
e
r
s
u
s
n
o
d
e
m
o
b
ilit
y
s
p
ee
d
Fig
u
r
e
5
.
Pack
et
lo
s
s
r
ate
v
e
r
s
u
s
n
o
d
e
m
o
b
ilit
y
s
p
ee
d
5
.
5
.
Co
m
pa
ra
t
iv
e
ev
a
lua
t
io
n wit
h sta
t
e
-
of
-
t
he
-
a
rt
met
ho
ds
T
o
f
u
r
th
er
v
alid
ate
th
e
ef
f
ec
ti
v
en
ess
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
e
wo
r
k
,
a
co
m
p
ar
is
o
n
was
co
n
d
u
cted
with
ex
is
tin
g
AI
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
ap
p
r
o
ac
h
es
r
ep
o
r
te
d
in
t
h
e
liter
atu
r
e.
T
h
e
co
m
p
ar
is
o
n
f
o
cu
s
es
o
n
d
etec
tio
n
ac
cu
r
ac
y
,
f
alse
p
o
s
itiv
e
r
ate,
an
d
d
etec
tio
n
r
ate
u
n
d
er
s
im
ilar
attac
k
s
ce
n
ar
io
s
.
Var
io
u
s
d
ee
p
lear
n
in
g
ar
c
h
itectu
r
es
h
av
e
b
ee
n
in
v
esti
g
ated
to
d
etec
t
att
ac
k
s
in
I
o
T
s
y
s
tem
s
.
Fo
r
in
s
tan
ce
,
R
NN
-
b
ased
m
o
d
els
[
2
4
]
,
B
L
STM
ap
p
r
o
ac
h
es
[
1
3
]
,
DB
M
m
o
d
els
[
1
4
]
,
a
n
d
C
NN
-
b
ased
m
eth
o
d
s
[
7
]
h
a
v
e
all
b
ee
n
u
tili
ze
d
f
o
r
id
en
tify
in
g
DDo
S
attac
k
s
,
ea
ch
d
em
o
n
s
tr
atin
g
d
if
f
e
r
en
t
lev
els
o
f
ef
f
ec
tiv
en
ess
.
Ad
d
i
tio
n
ally
,
in
tellig
en
t
r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
h
as a
ls
o
b
ee
n
co
n
s
id
er
ed
.
T
h
e
co
m
p
ar
ativ
e
r
esu
lts
ar
e
p
r
ese
n
ted
in
T
ab
le
8
.
T
ab
le
8
.
C
o
m
p
a
r
is
o
n
with
ex
i
s
tin
g
AI
-
b
ased
attac
k
d
etec
tio
n
m
eth
o
d
s
R
e
f
.
A
I
A
l
g
o
r
i
t
h
m
A
t
t
a
c
k
T
y
p
e
A
c
c
u
r
a
c
y
(
%)
F
P
R
(
%)
D
e
t
e
c
t
i
o
n
R
a
t
e
(
%)
[
2
4
]
R
N
N
D
D
o
S
68
2
.
0
83
[
1
3
]
B
LST
M
D
D
o
S
75
19
67
[
1
4
]
D
B
M
D
D
o
S
66
22
54
[
7
]
C
N
N
D
D
o
S
77
16
80
P
r
o
p
o
se
d
M
e
t
h
o
d
C
N
N
D
D
o
S
82
2
.
0
99
Fo
r
f
u
r
th
er
p
r
o
o
f
o
f
t
h
e
ef
f
icien
cy
o
f
th
e
d
ev
elo
p
ed
in
t
ellig
en
t
r
o
u
tin
g
-
b
ased
attac
k
d
etec
tio
n
f
r
am
ewo
r
k
,
a
co
m
p
ar
is
o
n
was
m
ad
e
with
b
o
t
h
AI
-
b
ased
d
etec
tio
n
m
eth
o
d
s
tak
e
n
f
r
o
m
r
esear
ch
liter
atu
r
e.
T
h
e
co
m
p
ar
is
o
n
em
p
h
asizes
o
n
d
etec
tio
n
ac
cu
r
ac
y
o
n
e
o
f
th
e
m
ain
p
e
r
f
o
r
m
an
ce
i
n
d
ex
e
s
,
as
it
r
ef
lects
h
o
w
well
th
e
m
o
d
el
to
co
r
r
ec
tly
id
en
tify
m
alicio
u
s
r
o
u
tin
g
b
e
h
av
io
r
f
r
o
m
n
o
r
m
al
o
p
e
r
atio
n
o
f
n
etwo
r
k
in
s
am
e
attac
k
s
ce
n
ar
io
s
.
C
o
m
p
r
eh
en
s
iv
e
an
aly
s
is
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
c
o
m
p
ar
is
o
n
to
o
th
er
d
ee
p
lea
r
n
in
g
ap
p
r
o
ac
h
es
wo
u
ld
lik
e
to
b
e
a
g
o
o
d
ap
p
r
o
ac
h
f
o
r
ass
ess
in
g
th
e
p
er
f
o
r
m
a
n
ce
g
ain
s
r
elativ
ely
g
ain
ed
th
r
o
u
g
h
r
o
u
tin
g
-
awa
r
e
f
ea
tu
r
e
f
u
s
io
n
an
d
s
m
ar
t
d
etec
tio
n
.
T
h
e
c
o
m
p
ar
is
o
n
o
n
ac
cu
r
ac
y
b
et
wee
n
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
an
d
ty
p
ical
s
tate
-
of
-
th
e
-
ar
t a
lg
o
r
ith
m
s
h
as b
ee
n
d
em
o
n
s
tr
ated
b
y
Fig
u
r
e
6
.
Fig
u
r
e
6
.
Acc
u
r
ac
y
c
o
m
p
ar
is
o
n
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
s
tate
-
of
-
th
e
-
ar
t a
p
p
r
o
ac
h
es
Evaluation Warning : The document was created with Spire.PDF for Python.