I
n
d
on
e
s
ian
Jou
r
n
al
o
f
E
lec
t
r
ica
l
E
n
gin
e
e
r
in
g
a
n
d
Com
p
u
t
e
r
S
c
ience
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
,
pp.
1
098
~
1
105
I
S
S
N:
2
502
-
4
7
52
,
DO
I
:
10
.
11591/i
j
e
e
cs
.v
3
8
.
i
2
.
pp
1
098
-
1
105
1098
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
e
e
cs
.
iaes
c
or
e
.
c
om
A
GRU
-
b
ase
d
ap
p
r
oac
h
f
or
b
ot
n
e
t
d
e
t
e
c
t
io
n
u
si
n
g d
e
e
p
le
ar
n
in
g t
e
c
h
n
iq
u
e
S
u
c
h
e
t
h
a
G
.
1
,
P
u
s
h
p
al
at
h
a
K
.
2
1
D
e
pa
r
tm
e
nt
of
I
n
f
or
ma
ti
o
n S
c
i
e
nc
e
a
nd
E
ngi
n
e
e
r
in
g,
S
a
h
y
a
dr
i
C
o
ll
e
ge
of
E
ngi
n
e
e
r
in
g
a
nd
M
a
na
ge
m
e
nt
,
V
is
v
e
s
v
a
r
a
y
a
T
e
c
hn
ol
o
g
ic
a
l
U
ni
ve
r
s
it
y
,
B
e
la
ga
v
i
,
I
ndi
a
2
D
e
pa
r
tm
e
nt
of
C
S
E
(
A
r
ti
f
i
c
ia
l
I
nt
e
ll
ig
e
n
c
e
a
nd
M
a
c
hi
ne
L
e
a
r
n
in
g)
, S
a
h
y
a
d
r
i
C
o
l
le
g
e
of
E
ngi
n
e
e
r
in
g
a
nd
M
a
na
ge
me
nt
,
V
is
v
e
s
v
a
r
a
y
a
T
e
c
hn
ol
o
g
ic
a
l
U
ni
ve
r
s
it
y
,
B
e
la
ga
v
i
,
I
ndi
a
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
Ju
n
22
,
202
4
R
e
vi
s
e
d
Oc
t
29
,
202
4
A
c
c
e
pt
e
d
N
o
v
11
,
202
4
T
h
e
i
n
c
r
e
as
i
n
g
v
o
l
u
me
o
f
n
e
t
w
o
rk
t
raffi
c
d
at
a
e
x
c
h
a
n
g
ed
a
mo
n
g
i
n
t
e
r
co
n
n
ec
t
ed
d
ev
i
ce
s
o
n
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T
)
p
o
s
e
s
a
s
i
g
n
i
fi
c
an
t
c
h
a
l
l
en
g
e
f
o
r
c
o
n
v
en
t
i
o
n
al
i
n
t
ru
s
i
o
n
d
e
t
ec
t
i
o
n
s
y
s
t
em
s
(
ID
S),
e
s
p
ec
i
a
l
l
y
i
n
t
h
e
face
o
f
e
v
o
l
v
i
n
g
an
d
u
n
p
red
i
c
t
ab
l
e
s
ec
u
r
i
t
y
t
h
r
e
at
s
.
I
t
i
s
c
r
u
c
i
a
l
t
o
d
e
v
el
o
p
ad
ap
t
i
v
e
a
n
d
e
ff
e
c
t
i
v
e
I
D
S
fo
r
I
o
T
t
o
m
i
t
i
g
at
e
fal
s
e
al
a
rm
s
a
n
d
e
n
s
u
r
e
h
i
g
h
d
e
t
ec
t
i
o
n
a
cc
u
ra
cy
,
p
art
i
cu
l
arl
y
w
i
t
h
t
h
e
s
u
rg
e
i
n
b
o
t
n
e
t
a
t
t
ac
k
s
.
T
h
e
s
e
at
t
ack
s
h
av
e
t
h
e
p
o
t
en
t
i
al
t
o
t
u
r
n
s
eemi
n
g
l
y
h
ar
m
l
e
s
s
d
ev
i
ce
s
i
n
t
o
z
o
m
b
i
e
s
,
g
en
e
rat
i
n
g
m
a
l
i
ci
o
u
s
t
raffi
c
t
h
at
d
i
s
ru
p
t
s
n
e
t
w
o
rk
o
p
e
rat
i
o
n
s
.
T
h
i
s
p
ap
e
r
i
n
t
ro
d
u
ce
s
a
n
o
v
e
l
ap
p
ro
ach
t
o
Io
T
i
n
t
ru
s
i
o
n
d
e
t
ec
t
i
o
n
,
l
e
v
e
ra
g
i
n
g
m
a
c
h
i
n
e
l
e
ar
n
i
n
g
t
ech
n
i
q
u
e
s
an
d
t
h
e
e
x
t
e
n
s
i
v
e
U
N
SW
-
N
B1
5
d
at
as
e
t
.
O
u
r
p
ri
m
ar
y
fo
cu
s
l
i
e
s
i
n
d
e
s
i
g
n
i
n
g
,
i
m
p
l
emen
t
i
n
g
,
an
d
ev
al
u
at
i
n
g
mac
h
i
n
e
l
e
arn
i
n
g
(ML
)
mo
d
e
l
s
,
i
n
c
l
u
d
i
n
g
K
-
n
e
ar
e
s
t
n
e
i
g
h
b
o
rs
(
K
N
N
),
r
a
n
d
o
m
f
o
r
e
s
t
(RF),
l
o
n
g
s
h
o
rt
-
t
e
rm
m
emo
r
y
(L
ST
M),
an
d
g
at
e
d
r
ecu
rr
e
n
t
u
n
i
t
(G
RU
),
ag
a
i
n
s
t
p
re
v
al
en
t
b
o
t
n
e
t
at
t
ac
k
s
.
T
h
e
s
u
cce
s
s
fu
l
t
e
s
t
i
n
g
ag
a
i
n
s
t
p
ro
m
i
n
e
n
t
Bo
t
-
n
e
t
at
t
ac
k
s
u
s
i
n
g
a
d
e
d
i
c
at
ed
d
at
as
e
t
fu
rt
h
e
r
v
al
i
d
at
e
s
i
t
s
p
o
t
e
n
t
i
al
f
o
r
e
n
h
an
ci
n
g
i
n
t
ru
s
i
o
n
d
e
t
ec
t
i
o
n
a
ccu
ra
cy
i
n
d
y
n
a
mi
c
an
d
ev
o
l
v
i
n
g
I
o
T
l
an
d
s
c
ap
e
s
.
K
e
y
w
o
r
d
s
:
B
ot
n
e
t
Ga
t
e
d
r
e
c
ur
r
e
n
t
uni
t
K
-
n
e
a
r
e
s
t
n
e
i
g
hb
o
r
s
L
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
R
a
n
do
m
f
o
r
e
s
t
S
e
l
e
c
t
KB
e
s
t
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
S
uc
h
e
t
h
a
G
.
De
pa
r
t
m
e
n
t
o
f
I
nf
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
ne
e
r
in
g,
S
a
hy
a
dr
i
C
o
l
l
e
ge
o
f
E
n
g
i
ne
e
r
i
ng
a
n
d
M
a
n
a
ge
m
e
n
t
V
i
s
ve
s
v
a
r
a
y
a
T
e
c
hn
o
l
o
g
i
c
a
l
U
ni
ve
r
s
i
t
y
B
e
l
a
ga
vi
-
590018,
I
n
d
i
a
E
m
a
i
l
:
s
uc
he
t
h
a
g87
@
g
m
a
il
.
c
o
m
1.
I
NT
RODU
C
T
I
ON
T
h
e
r
i
s
e
o
f
b
o
t
n
e
t
s
p
o
s
e
s
o
n
e
o
f
t
h
e
m
o
s
t
s
i
g
nif
i
c
a
nt
c
h
a
l
l
e
n
g
e
s
to
c
y
b
e
r
s
e
c
ur
i
t
y
,
e
s
pe
c
i
a
ll
y
w
i
t
hi
n
t
h
e
r
a
p
i
d
ly
e
x
pa
n
d
i
ng
i
n
t
e
r
n
e
t
o
f
t
h
i
n
gs
(
I
oT
)
e
c
o
s
y
s
te
m
[
1]
.
T
h
e
s
e
n
e
t
wo
r
ks
o
f
c
o
m
pr
o
m
i
s
e
d
de
vi
c
e
s
e
n
a
bl
e
a
w
i
de
r
a
n
ge
o
f
c
y
b
e
r
c
r
im
e
s
,
i
n
c
l
ud
i
ng
d
i
s
t
r
i
b
ut
e
d
de
ni
a
l
o
f
s
e
r
vi
c
e
(
DD
o
S
)
a
tt
a
c
ks
,
da
t
a
b
r
e
a
c
h
e
s
,
a
n
d
s
pa
m
c
a
m
pa
i
g
ns
.
T
r
a
di
t
i
o
n
a
l
c
y
be
r
s
e
c
ur
i
t
y
m
e
a
s
ur
e
s
ha
v
e
pr
o
v
e
n
i
ns
u
f
f
i
c
i
e
n
t
,
e
s
pe
c
i
a
ll
y
g
i
ve
n
t
h
e
v
o
l
u
m
e
a
n
d
d
i
v
e
r
s
i
t
y
o
f
I
o
T
de
vi
c
e
s
,
m
a
ny
o
f
w
hi
c
h
h
a
v
e
li
mi
t
e
d
s
e
c
ur
i
t
y
,
m
a
k
i
ng
t
h
e
m
pr
i
m
e
t
a
r
ge
t
s
f
o
r
b
ot
n
e
t
i
nf
e
c
t
i
o
ns
.
I
n
r
e
s
po
n
s
e
to
t
h
e
s
e
c
ha
l
l
e
nge
s
,
t
h
e
c
y
b
e
r
s
e
c
ur
i
t
y
c
o
m
m
u
ni
t
y
h
a
s
i
nc
r
e
a
s
i
ng
ly
a
do
p
t
e
d
m
a
c
hi
ne
l
e
a
r
nin
g
(
M
L
)
a
n
d
de
e
p
l
e
a
r
ni
ng
(
DL
)
t
e
c
hni
que
s
,
s
uc
h
a
s
K
-
n
e
a
r
e
s
t
n
e
i
g
hb
o
r
s
(
K
NN
)
,
r
a
n
do
m
f
o
r
e
s
t
(
R
F
)
[
2]
,
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
(
L
S
T
M
)
[
3]
,
a
n
d
ga
t
e
d
r
e
c
ur
r
e
n
t
u
ni
t
(
GR
U)
.
W
hi
l
e
t
h
e
s
e
m
o
de
l
s
s
h
o
w
pot
e
n
t
i
a
l
,
t
h
e
y
f
a
c
e
s
i
g
nif
i
c
a
n
t
l
im
i
t
a
t
i
o
ns
.
T
r
a
d
i
t
i
o
na
l
M
L
m
o
de
l
s
o
f
t
e
n
s
t
r
ugg
l
e
w
i
t
h
t
h
e
v
a
r
i
a
bil
i
t
y
o
f
I
o
T
n
e
t
w
o
r
k
tr
a
f
f
i
c
,
l
e
a
d
i
ng
to
r
e
duc
e
d
a
c
c
ur
a
c
y
.
M
e
a
n
w
hil
e
,
e
xi
s
t
i
n
g
DL
mo
de
l
s
,
t
h
o
ugh
p
o
we
r
f
u
l
,
r
e
qu
i
r
e
s
u
b
s
t
a
n
t
i
a
l
c
o
m
p
ut
a
t
i
o
n
a
l
r
e
s
o
ur
c
e
s
,
m
a
k
i
ng
t
h
e
m
l
e
s
s
f
e
a
s
i
b
l
e
f
o
r
r
e
a
l
-
t
i
m
e
a
pp
l
i
c
a
t
i
o
ns
i
n
r
e
s
o
ur
c
e
-
c
o
n
s
t
r
a
i
n
e
d
I
o
T
e
n
vi
r
o
nmen
t
s
[
4]
.
I
m
pr
o
vi
n
g
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
i
s
c
r
uc
i
a
l
f
o
r
e
n
ha
n
c
i
n
g
m
o
de
l
pe
r
f
o
r
m
a
n
c
e
.
A
ddr
e
s
s
i
ng
t
h
e
s
e
c
ha
l
l
e
nge
s
i
s
e
s
s
e
n
t
i
a
l
f
o
r
a
dva
n
c
i
ng
b
o
t
n
e
t
de
t
e
c
t
i
o
n
s
y
s
t
e
m
s
.
T
hi
s
r
e
s
e
a
r
c
h
a
im
s
t
o
c
l
o
s
e
t
h
e
s
e
ga
ps
by
de
v
e
l
o
p
i
ng
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
A
G
R
U
-
bas
e
d
appr
oac
h
f
or
botnet
de
tec
ti
on
us
ing
de
e
p
lear
ning
tec
hnique
(
Suc
he
tha
G.
)
1099
s
c
a
l
a
bl
e
b
o
t
n
e
t
de
t
e
c
t
i
o
n
f
r
a
m
e
wo
r
k
t
h
a
t
i
n
t
e
gr
a
t
e
s
GR
U
f
o
r
s
e
que
n
t
i
a
l
da
t
a
pr
o
c
e
s
s
i
ng
w
i
t
h
o
p
t
i
mi
z
e
d
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
.
B
y
f
o
c
us
i
n
g
o
n
i
m
pr
o
vi
ng
t
h
e
s
c
a
l
a
bil
i
t
y
a
n
d
a
c
c
ur
a
c
y
o
f
i
n
t
r
us
i
o
n
de
t
e
c
t
i
o
n
s
y
s
t
e
m
s
(
I
DS)
in
I
oT
e
nvi
r
o
nm
e
n
t
s
,
t
hi
s
s
t
ud
y
c
o
n
t
r
i
b
ut
e
s
to
t
h
e
b
r
o
a
de
r
e
f
f
o
r
t
to
e
n
h
a
n
c
e
c
y
be
r
s
e
c
ur
i
t
y
m
e
a
s
ur
e
s
a
g
a
i
ns
t
t
h
e
e
v
o
l
vi
ng
t
h
r
e
a
t
o
f
b
ot
n
e
t
s
.
De
s
p
i
t
e
a
dv
a
n
c
e
m
e
n
t
s
,
c
h
a
ll
e
n
ge
s
s
uc
h
a
s
s
c
a
l
a
bil
i
t
y
,
c
o
m
put
a
t
i
o
n
a
l
e
f
f
i
c
i
e
n
c
y
,
a
n
d
r
e
a
l
-
t
i
m
e
a
pp
li
c
a
bil
i
t
y
i
n
d
i
ve
r
s
e
I
oT
e
n
vi
r
o
nm
e
nt
s
pe
r
s
i
s
t
.
Ou
r
s
t
udy
b
u
il
ds
o
n
pr
i
o
r
r
e
s
e
a
r
c
h
[
5]
,
[
6
]
by
a
ddr
e
s
s
i
ng
t
h
e
s
e
c
o
n
s
t
r
a
i
n
t
s
,
ul
t
i
m
a
t
e
l
y
a
i
mi
ng
to
de
v
e
l
o
p
a
m
o
r
e
r
o
b
us
t
a
n
d
s
c
a
l
a
bl
e
b
o
t
n
e
t
de
t
e
c
t
i
o
n
m
o
de
l
t
h
a
t
c
a
n
be
e
f
f
e
c
t
i
v
e
ly
de
p
l
o
y
e
d
i
n
r
e
a
l
-
wo
r
l
d
I
oT
s
c
e
n
a
r
i
o
s
.
T
h
e
UN
S
W
-
NB
15
[
7]
da
t
a
s
e
t
i
s
us
e
d
i
n
t
h
e
p
r
o
p
o
s
e
d
a
pp
r
o
a
c
h
to
de
t
e
c
t
b
ot
n
e
t
s
i
n
I
o
T
s
c
e
n
a
r
i
o
s
.
T
h
e
da
t
a
s
e
t
o
f
f
e
r
s
a
t
h
o
r
o
ugh
de
pi
c
t
i
o
n
o
f
n
e
t
wor
k
t
r
a
f
f
i
c
s
c
e
n
a
r
i
o
s
a
n
d
c
o
n
s
i
s
t
s
o
f
49
v
a
r
i
a
bl
e
s
d
i
vi
de
d
i
n
t
o
ni
ne
c
l
a
s
s
e
s
.
T
o
i
m
pr
o
v
e
m
o
de
l
a
pp
li
c
a
bil
i
t
y
,
da
t
a
p
r
e
pr
o
c
e
s
s
i
ng
t
e
c
h
ni
que
s
i
n
c
l
ud
e
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
,
c
l
a
m
p
i
ng
e
x
t
r
e
m
e
v
a
l
u
e
s
,
l
o
g
tr
a
n
s
f
o
r
m
a
t
i
o
n
,
a
n
d
l
o
we
r
i
n
g
c
a
r
d
i
n
a
li
t
y
i
n
c
a
t
e
go
r
i
c
a
l
f
e
a
t
ur
e
s
.
T
hi
s
r
e
s
e
a
r
c
h
e
mp
l
o
y
s
t
h
e
S
e
l
e
c
t
KB
e
s
t
m
e
t
h
o
d
wi
t
h
C
hi
-
S
qua
r
e
s
c
o
r
i
n
g
to
i
d
e
n
t
i
f
y
c
r
i
t
i
c
a
l
f
e
a
t
ur
e
s
,
o
p
t
i
mi
z
i
ng
t
h
e
GR
U
m
o
de
l
’
s
a
bi
li
t
y
to
de
t
e
c
t
b
ot
n
e
t
s
e
f
f
e
c
t
i
v
e
ly
.
T
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
m
a
c
hi
ne
l
e
a
r
ni
n
g
a
l
go
r
i
t
hm
s
li
ke
GR
U,
L
S
T
M
,
a
n
d
R
F
in
r
e
a
l
-
t
i
m
e
i
n
t
r
us
i
o
n
de
t
e
c
t
i
o
n
i
s
a
s
s
e
s
s
e
d.
T
h
e
a
ppr
o
a
c
h
s
e
e
ks
t
o
m
i
t
i
ga
t
e
t
h
e
gr
o
wi
n
g
t
h
r
e
a
t
o
f
b
o
t
n
e
t
a
s
s
a
u
l
t
s
i
n
I
o
T
c
o
n
t
e
x
t
s
a
n
d
e
nh
a
n
c
e
t
h
e
e
f
f
i
c
a
c
y
o
f
c
ur
r
e
n
t
I
DS
by
c
o
m
bi
n
i
ng
c
utt
i
n
g
-
e
dge
m
o
de
l
s
a
n
d
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
a
ppr
o
a
c
h
e
s
.
R
e
s
e
a
r
c
h
e
r
s
h
a
v
e
b
e
e
n
l
o
o
ki
n
g
i
n
t
o
s
e
v
e
r
a
l
t
e
c
hniques
to
i
m
pr
o
vi
n
g
I
DSs
.
A
c
c
o
r
di
n
g
to
t
h
e
s
t
udy
,
i
t
wa
s
d
i
s
c
o
ve
r
e
d
t
h
a
t
a
ppl
yi
ng
XG
B
oo
s
t
f
o
r
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
i
m
pr
o
v
e
d
I
DS
pe
r
f
o
r
m
a
n
c
e
o
n
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t,
r
e
s
u
l
t
i
n
g
i
n
hi
g
h
e
r
a
c
c
ur
a
c
y
a
n
d
l
o
we
r
c
o
m
p
l
e
xi
t
y
,
pa
r
t
i
c
u
l
a
r
ly
f
o
r
bi
na
r
y
c
l
a
s
s
if
i
c
a
t
i
o
n
tas
ks
[
8]
.
An
i
n
t
e
gr
a
t
e
d
r
ul
e
-
ba
s
e
d
I
DS
de
m
o
n
s
t
r
a
t
e
d
g
oo
d
a
c
c
ur
a
c
y
a
n
d
l
o
we
r
f
a
l
s
e
a
l
a
r
m
r
a
t
e
s
o
n
b
o
t
h
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
a
n
d
a
r
e
a
l
-
t
i
m
e
da
t
a
s
e
t
f
r
o
m
NI
T
P
a
t
n
a
,
b
ut
i
t
wa
s
l
im
i
t
e
d
i
n
i
t
s
c
a
pa
c
i
t
y
t
o
de
t
e
c
t
z
e
r
o
-
da
y
a
t
t
a
c
ks
due
to
i
t
s
r
e
l
i
a
n
c
e
o
n
pr
e
de
t
e
r
m
i
ne
d
s
i
g
n
a
t
ur
e
s
[
9]
.
F
ur
t
h
e
r
m
o
r
e
,
a
t
w
o
-
s
t
a
ge
a
n
o
m
a
ly
-
b
a
s
e
d
s
tr
a
t
e
g
y
e
m
p
l
o
yi
ng
r
e
c
ur
s
i
v
e
f
e
a
t
ur
e
r
e
m
o
va
l
a
n
d
RF
s
h
a
d
pr
o
m
i
s
e
,
b
ut
i
t
di
d
n
ot
s
i
g
nif
i
c
a
n
t
l
y
i
nc
r
e
a
s
e
de
t
e
c
t
i
o
n
,
pa
r
t
i
c
u
l
a
r
l
y
w
i
t
h
de
c
i
s
i
o
n
t
r
e
e
s
(
DT
)
a
n
d
Na
i
ve
B
a
y
e
s
(
NB
)
c
l
a
s
s
if
i
e
r
s
[
10]
.
M
o
hy
-
E
dd
i
n
e
e
t
al.
[
11]
c
r
e
a
t
e
d
a
n
e
t
wo
r
k
i
n
t
r
us
i
o
n
de
t
e
c
t
i
o
n
s
y
s
t
e
m
(
NI
DS)
f
o
r
I
o
T
c
o
n
t
e
x
t
s
u
t
i
l
i
z
i
ng
a
K
NN
c
l
a
s
s
i
f
i
e
r
a
l
o
n
g
w
i
t
h
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
a
ppr
o
a
c
h
e
s
s
uc
h
a
s
P
C
A
,
u
ni
va
r
i
a
t
e
s
t
a
t
i
s
t
i
c
a
l
t
e
s
t
s
,
a
n
d
t
h
e
Ge
n
e
t
i
c
Al
go
r
i
t
hm
.
T
hi
s
m
o
de
l
a
c
hi
e
ve
d
99.
99%
a
c
c
ur
a
c
y
a
n
d
l
o
we
r
e
d
f
o
r
e
c
a
s
t
t
i
m
e
f
r
o
m
o
v
e
r
51,
000
s
e
c
o
n
ds
to
l
e
s
s
t
h
a
n
o
n
e
m
i
nut
e
,
a
l
t
h
o
u
gh
i
t
h
a
d
li
mi
t
a
t
i
o
ns
i
n
bi
na
r
y
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
da
t
a
s
e
t
c
o
v
e
r
a
ge
,
a
n
d
s
e
n
s
i
t
i
v
i
t
y
t
o
n
o
i
s
y
da
t
a
.
Ve
n
ka
t
a
c
h
a
l
a
m
a
n
d
J
a
c
o
b
[
12]
us
e
d
r
e
c
ur
s
i
ve
f
e
a
t
ur
e
e
l
im
i
na
t
i
o
n
(
R
F
E
)
wi
t
h
RF
o
n
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
,
l
o
we
r
i
n
g
f
e
a
t
ur
e
s
f
r
o
m
45
to
4
whi
l
e
a
t
t
a
i
ni
ng
98.
3%
a
c
c
ur
a
c
y
.
Ho
we
v
e
r
,
b
e
c
a
us
e
o
f
t
h
e
n
a
r
r
o
w
f
e
a
t
ur
e
s
e
t,
o
u
r
t
e
c
h
ni
que
m
a
y
h
a
v
e
mi
s
s
e
d
c
o
m
p
li
c
a
t
e
d
pa
tt
e
r
n
s
.
A
n
o
t
h
e
r
a
ppr
o
a
c
h
[
13]
,
e
x
p
l
o
r
e
s
m
e
t
h
o
ds
f
o
r
de
t
e
c
t
i
n
g
b
o
t
n
e
t
s
,
f
o
c
us
i
n
g
o
n
b
e
h
a
vi
o
r
-
b
a
s
e
d
a
n
a
ly
s
i
s
a
n
d
f
l
o
w
-
b
a
s
e
d
f
e
a
t
ur
e
s
.
T
h
e
s
ugge
s
t
e
d
m
u
l
t
il
a
y
e
r
f
r
a
m
e
wo
r
k,
whi
c
h
us
e
s
a
v
a
r
i
e
t
y
o
f
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
e
t
h
o
ds
,
e
xhi
b
i
t
s
go
o
d
a
c
c
ur
a
c
y
r
a
t
e
s
.
On
e
m
o
r
e
a
ppr
o
a
c
h
[
14]
,
t
a
c
k
l
e
s
t
h
e
s
c
a
n
t
kno
wl
e
dge
o
f
t
h
e
b
e
h
a
vi
o
r
o
f
h
a
r
m
f
u
l
b
o
t
n
e
t
s
,
e
x
po
s
i
n
g
t
h
e
i
r
s
ub
s
t
a
n
t
i
a
l
c
o
n
t
r
i
b
ut
i
o
n
to
un
de
s
i
r
e
d
i
n
t
e
r
n
e
t
t
r
a
f
f
i
c
a
n
d
a
v
a
r
i
e
t
y
o
f
vi
c
t
i
m
do
m
a
i
ns
.
Our
s
t
udy
de
m
o
ns
t
r
a
t
e
s
t
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
a
GR
U
-
b
a
s
e
d
de
e
p
l
e
a
r
ni
ng
m
o
de
l
f
o
r
b
ot
n
e
t
de
t
e
c
t
i
o
n
,
e
nh
a
nc
e
d
by
S
e
l
e
c
t
K
B
e
s
t
wi
t
h
t
h
e
C
hi
-
s
qua
r
e
t
e
s
t.
GR
Us
o
u
t
pe
r
f
o
r
m
t
r
a
di
t
i
o
n
a
l
m
a
c
hi
ne
l
e
a
r
ni
ng
m
o
de
l
s
in
bi
na
r
y
c
l
a
s
s
i
f
i
c
a
t
i
o
n
by
r
e
c
o
gni
z
i
ng
l
o
n
g
-
t
e
r
m
de
p
e
n
de
nc
i
e
s
i
n
s
e
que
n
t
i
a
l
da
t
a
.
T
hi
s
r
e
s
e
a
r
c
h
a
im
s
t
o
de
v
e
l
o
p
a
s
c
a
l
a
bl
e
a
n
d
e
f
f
i
c
i
e
n
t
b
o
t
n
e
t
de
t
e
c
t
i
o
n
s
y
s
t
e
m
t
ha
t
i
m
pr
o
v
e
s
a
c
c
ur
a
c
y
,
r
e
duc
e
s
f
a
l
s
e
po
s
i
t
i
v
e
s
,
a
n
d
e
n
s
ur
e
s
a
pp
l
i
c
a
bil
i
t
y
i
n
r
e
s
o
ur
c
e
-
c
o
n
s
t
r
a
i
n
e
d
I
o
T
e
n
vi
r
o
nmen
t
s
.
B
y
a
ddr
e
s
s
i
ng
c
o
m
put
a
t
i
o
n
a
l
e
f
f
i
c
i
e
nc
y
a
n
d
r
e
a
l
-
t
i
m
e
de
t
e
c
t
i
o
n
,
t
hi
s
s
t
ud
y
s
t
r
e
n
gt
h
e
ns
c
y
b
e
r
s
e
c
ur
i
t
y
a
ga
i
ns
t
e
v
o
l
vi
ng
b
o
t
n
e
t
t
h
r
e
a
t
s
.
T
h
e
pa
pe
r
i
s
o
r
g
a
ni
z
e
d
a
s
f
o
l
l
o
ws
:
s
e
c
t
i
o
n
2
c
o
v
e
r
s
t
h
e
m
e
t
h
o
do
l
o
g
y
,
s
e
c
t
i
o
n
3
di
s
c
u
s
s
e
s
r
e
s
u
l
t
s
a
n
d
c
o
n
c
l
u
s
i
o
ns
,
a
n
d
s
e
c
t
i
o
n
4
pr
e
s
e
n
t
s
t
h
e
f
i
na
l
c
o
n
c
l
us
i
o
n
.
2.
M
E
T
HO
D
T
o
e
n
h
a
n
c
e
t
h
e
de
t
e
c
t
i
o
n
o
f
b
ot
n
e
t
s
i
n
I
oT
e
n
vi
r
o
nm
e
n
t
s
,
we
h
a
v
e
de
v
e
l
o
pe
d
a
n
o
v
e
l
c
y
be
r
s
e
c
ur
i
t
y
s
y
s
t
e
m
us
i
ng
a
GR
U
-
S
e
l
e
c
t
KB
e
s
t
de
e
p
l
e
a
r
ni
ng
m
o
de
l
.
T
hi
s
s
e
c
t
i
o
n
de
s
c
r
i
be
s
t
h
e
s
y
s
t
e
m
a
t
i
c
s
t
e
ps
i
nv
o
l
v
e
d
in
de
t
e
c
t
i
n
g
b
o
t
n
e
t
s
us
i
n
g
a
GR
U
-
b
a
s
e
d
a
ppr
o
a
c
h
.
T
h
e
t
e
c
hni
que
s
i
nc
l
ude
da
t
a
c
o
l
l
e
c
t
i
o
n
a
n
d
pr
e
pr
o
c
e
s
s
i
n
g,
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
,
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
de
s
i
g
n
,
t
r
a
i
nin
g,
a
n
d
e
va
l
u
a
t
i
o
n
.
F
i
gur
e
1
de
p
i
c
t
s
t
h
e
s
ugge
s
t
e
d
de
s
i
g
n
,
e
ns
ur
i
n
g
a
t
h
o
r
o
ugh
un
de
r
s
t
a
n
d
i
ng
o
f
t
h
e
un
de
r
lyi
n
g
pr
o
c
e
s
s
e
s
.
2.
1.
Dat
as
e
t
T
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
wa
s
c
h
o
s
e
n
f
o
r
t
h
i
s
s
tud
y
due
to
i
t
s
de
t
a
i
l
e
d
r
e
pr
e
s
e
n
t
a
t
i
o
n
o
f
m
o
de
r
n
n
e
t
wo
r
k
v
u
l
n
e
r
a
bi
li
t
i
e
s
,
whi
c
h
i
s
c
r
uc
i
a
l
f
o
r
e
v
a
l
u
a
t
i
n
g
I
DSs
i
n
I
o
T
e
n
vi
r
o
nm
e
n
t
s
.
T
hi
s
da
t
a
s
e
t
i
n
c
ludes
49
f
e
a
t
ur
e
s
c
a
t
e
g
o
r
i
z
e
d
i
n
t
o
9
gr
o
ups
,
o
f
f
e
r
i
n
g
a
b
a
l
a
n
c
e
d
c
o
m
p
l
e
xi
t
y
t
h
a
t
i
s
b
o
t
h
r
e
l
e
v
a
n
t
a
n
d
c
h
a
ll
e
ng
i
n
g
f
o
r
t
e
s
t
i
n
g
a
d
v
a
n
c
e
d
m
a
c
hi
ne
l
e
a
r
ni
ng
a
n
d
de
e
p
l
e
a
r
nin
g
m
o
de
l
s
.
Unl
i
ke
o
l
de
r
da
t
a
s
e
t
s
l
i
ke
K
DD
C
UP99
[
15]
a
n
d
NSL
K
DD
[
16]
,
whi
c
h
a
r
e
c
o
n
s
t
r
a
i
n
e
d
by
o
ut
da
t
e
d
a
tt
a
c
k
s
c
e
n
a
r
i
o
s
,
UN
S
W
-
NB
15
c
a
pt
ur
e
s
a
b
r
o
a
de
r
r
a
n
ge
o
f
n
e
t
wo
r
k
b
e
ha
vi
o
r
s
,
m
a
k
i
ng
i
t
m
o
r
e
a
ppl
i
c
a
bl
e
to
c
ur
r
e
n
t
I
o
T
s
e
c
ur
i
t
y
c
h
a
ll
e
n
ge
s
[
17]
.
A
dd
i
t
i
o
n
a
ll
y
,
c
o
m
pa
r
e
d
to
n
e
we
r
da
t
a
s
e
t
s
s
uc
h
a
s
B
o
t
-
I
oT
,
UN
S
W
-
NB
15
pr
o
vi
de
s
a
m
o
r
e
c
o
m
pr
e
h
e
ns
i
ve
e
nvi
r
o
nm
e
n
t
f
o
r
e
v
a
l
ua
t
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
:
1
098
-
1
105
1100
m
o
de
l
pe
r
f
o
r
m
a
n
c
e
,
b
a
l
a
n
c
i
ng
c
o
m
p
l
e
xi
t
y
a
n
d
r
e
a
l
-
wo
r
l
d
a
pp
li
c
a
bi
li
t
y
[
18]
,
[
19]
.
T
hi
s
c
h
o
i
c
e
i
n
f
o
r
m
e
d
t
h
e
pr
e
pr
o
c
e
s
s
i
ng
s
t
e
ps
,
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
ds
,
a
n
d
e
v
a
l
ua
t
i
o
n
pr
o
c
e
s
s
e
s
,
e
n
s
ur
i
ng
t
h
e
r
o
b
us
t
n
e
s
s
a
n
d
r
e
l
e
v
a
nc
e
o
f
o
ur
f
i
nd
i
ngs
[
20]
,
[
21
]
.
2.
2.
Dat
a
p
r
e
p
r
o
c
e
s
s
in
g
T
o
p
r
e
pa
r
e
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
f
o
r
e
f
f
e
c
t
i
v
e
m
o
de
li
ng
a
n
d
a
n
a
ly
s
i
s
,
s
e
v
e
r
a
l
pr
e
pr
o
c
e
s
s
i
ng
s
t
e
ps
we
r
e
un
de
r
t
a
ke
n
:
F
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
a
n
d
dr
o
ppi
n
g:
i
r
r
e
l
e
v
a
n
t
o
r
hi
g
hly
c
o
r
r
e
l
a
t
e
d
f
e
a
t
ur
e
s
we
r
e
r
e
m
o
v
e
d
to
pr
e
v
e
n
t
o
v
e
r
-
f
i
t
t
i
n
g
a
n
d
s
t
r
e
a
m
l
i
ne
t
h
e
da
t
a
s
e
t
,
e
n
h
a
n
c
i
ng
t
h
e
m
o
de
l
’
s
a
bil
i
t
y
t
o
ge
n
e
r
a
l
i
z
e
to
n
e
w
da
t
a
.
C
l
a
m
p
i
ng
e
x
t
r
e
m
e
v
a
l
ue
s
:
m
i
t
i
ga
t
e
d
s
ke
wne
s
s
by
c
l
a
m
p
i
ng
n
u
m
e
r
i
c
f
e
a
t
ur
e
s
,
b
a
l
a
nc
i
n
g
da
t
a
di
s
t
r
i
b
ut
i
o
n
a
n
d
r
e
duc
i
ng
o
u
t
l
i
e
r
i
nf
l
ue
n
c
e
.
A
pp
lyi
ng
l
o
g
tr
a
n
s
f
o
r
m
a
t
i
o
n
:
n
o
r
m
a
li
z
e
d
hi
g
h
c
a
r
d
i
n
a
li
t
y
a
n
d
s
k
e
we
d
f
e
a
t
ur
e
s
t
h
r
o
ugh
l
o
ga
r
i
t
hmi
c
t
r
a
n
s
f
o
r
m
a
t
i
o
n
t
o
e
n
ha
n
c
e
m
o
de
l
s
u
i
t
a
bil
i
t
y
.
R
e
duc
i
ng
c
a
r
d
i
n
a
li
t
y
i
n
c
a
t
e
go
r
i
c
a
l
f
e
a
t
ur
e
s
:
r
e
duc
e
d
hi
g
h
c
a
r
d
i
na
li
t
y
i
n
c
a
t
e
go
r
i
c
a
l
f
e
a
t
ur
e
s
by
gr
o
upi
ng
l
e
s
s
f
r
e
que
n
t
l
a
b
e
l
s
,
s
i
m
p
li
f
yi
ng
t
h
e
da
t
a
s
e
t
wi
t
h
o
ut
l
o
s
i
ng
e
s
s
e
n
t
i
a
l
i
nf
o
r
m
a
t
i
o
n
.
Va
l
i
da
t
i
o
n
a
n
d
vi
s
u
a
l
i
z
a
t
i
o
n
:
v
a
li
da
t
e
d
pr
e
pr
o
c
e
s
s
i
n
g
by
vi
s
ua
ll
y
i
ns
pe
c
t
i
n
g
f
e
a
t
ur
e
r
e
pr
e
s
e
n
t
a
t
i
o
n
s
b
e
f
o
r
e
a
n
d
a
f
t
e
r
tr
a
n
s
f
o
r
m
a
t
i
o
n
,
e
ns
ur
i
n
g
r
e
a
d
i
ne
s
s
f
o
r
m
o
de
l
t
r
a
i
ni
ng.
F
i
gur
e
1.
P
r
o
p
o
s
e
d
a
r
c
hi
t
e
c
t
ur
e
di
a
gr
a
m
2.
3.
F
e
at
u
r
e
s
e
l
e
c
t
ion
S
e
l
e
c
t
KB
e
s
t
[
22]
wi
t
h
C
hi
-
S
qua
r
e
s
c
o
r
i
n
g
wa
s
c
ho
s
e
n
a
s
t
h
e
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
d
b
e
c
a
us
e
o
f
i
t
s
e
f
f
e
c
t
i
v
e
n
e
s
s
i
n
m
a
n
a
g
i
ng
hi
g
h
-
d
i
m
e
ns
i
o
n
a
l
da
t
a
,
e
s
pe
c
i
a
ll
y
i
n
I
o
T
s
i
t
ua
t
i
o
ns
w
h
e
r
e
f
e
a
t
ur
e
r
e
l
e
va
n
c
e
v
a
r
i
e
s
s
i
g
nif
i
c
a
n
t
l
y
.
T
hi
s
m
e
t
h
o
d
wa
s
s
e
l
e
c
t
e
d
o
v
e
r
ot
h
e
r
s
b
e
c
a
u
s
e
t
h
e
C
hi
-
S
qua
r
e
t
e
s
t
i
s
pa
r
t
i
c
u
l
a
r
ly
w
e
l
l
-
s
u
i
t
e
d
f
o
r
c
a
t
e
g
o
r
i
c
a
l
d
a
t
a
,
whi
c
h
i
s
pr
e
v
a
l
e
n
t
i
n
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
.
B
y
e
v
a
l
ua
t
i
n
g
e
a
c
h
f
e
a
t
ur
e
’
s
r
e
l
e
v
a
nc
e
to
t
h
e
t
a
r
ge
t
v
a
r
i
a
bl
e
,
t
hi
s
m
e
t
h
o
d
e
ns
ur
e
s
t
h
a
t
o
nl
y
t
h
e
m
o
s
t
i
nf
o
r
m
a
t
i
v
e
f
e
a
t
ur
e
s
a
r
e
r
e
t
a
i
n
e
d,
r
e
duc
i
n
g
d
i
m
e
n
s
i
o
na
l
i
t
y
w
hil
e
pr
e
s
e
r
vi
ng
t
h
e
da
t
a
s
e
t
’
s
i
n
t
e
gr
i
t
y
f
o
r
m
o
de
l
tr
a
i
ni
n
g.
T
h
e
C
hi
-
S
qua
r
e
s
t
a
t
i
s
t
i
c
,
whi
c
h
c
o
m
pa
r
e
s
o
b
s
e
r
v
e
d
a
n
d
e
x
p
e
c
t
e
d
f
r
e
que
nc
i
e
s
,
wa
s
us
e
d
t
o
r
a
n
k
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
b
a
s
e
d
o
n
t
h
e
i
r
pr
e
d
i
c
t
i
ve
a
bil
i
t
y
.
S
e
l
e
c
t
KB
e
s
t
i
m
pr
o
v
e
s
m
o
de
l
a
c
c
ur
a
c
y
a
n
d
l
o
we
r
s
t
h
e
c
h
a
n
c
e
o
f
o
v
e
r
f
i
t
t
i
n
g
by
d
i
m
e
ns
i
o
n
a
li
t
y
r
e
duc
i
n
g
t
he
da
t
a
s
e
t
whi
l
e
m
a
i
n
t
a
i
n
i
ng
i
m
po
r
t
a
n
t
f
e
a
t
ur
e
s
.
T
h
e
c
hi
-
s
qua
r
e
s
t
a
t
i
s
t
i
c
us
e
d
i
n
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
h
a
s
t
h
e
(
1)
.
2
=
∑
(
−
)
2
(
1)
W
e
r
e
,
O
m
r
e
pr
e
s
e
n
t
s
t
h
e
o
b
s
e
r
v
e
d
f
r
e
que
n
c
y
,
a
n
d
E
m
t
h
e
e
x
p
e
c
t
e
d
f
r
e
que
nc
y
u
n
d
e
r
i
n
de
pe
n
d
e
n
c
e
.
Gi
ve
n
t
h
e
h
hi
g
h
d
i
m
e
ns
i
o
n
a
li
t
y
o
f
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
,
e
f
f
e
c
t
i
v
e
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
i
s
c
r
uc
i
a
l
f
o
r
i
de
n
t
i
f
yi
ng
r
e
l
e
v
a
n
t
a
tt
r
i
b
ut
e
s
,
s
uc
h
a
s
n
e
t
wo
r
k
tr
a
f
f
i
c
,
pa
c
ke
t
pa
y
l
o
a
d
s
,
a
n
d
pr
o
to
c
o
l
h
e
a
de
r
s
[
22]
.
S
e
l
e
c
t
KB
e
s
t
w
i
t
h
C
hi
-
S
qua
r
e
s
c
o
r
i
n
g
a
l
l
o
w
s
a
n
a
l
y
s
t
s
to
a
s
s
e
s
s
t
h
e
c
o
r
r
e
l
a
t
i
o
n
b
e
t
we
e
n
v
a
r
i
a
bl
e
s
a
n
d
n
e
t
wo
r
k
i
n
t
r
us
i
o
n
s
,
h
e
l
p
i
ng
to
i
de
n
t
i
f
y
f
e
a
t
ur
e
s
t
h
a
t
s
tr
o
n
g
l
y
c
o
r
r
e
l
a
t
e
w
i
t
h
i
n
t
r
us
i
o
n
i
ns
t
a
n
c
e
s
f
o
r
m
o
de
l
t
r
a
i
ni
ng
a
n
d
e
v
a
l
ua
t
i
o
n
[
23]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
A
G
R
U
-
bas
e
d
appr
oac
h
f
or
botnet
de
tec
ti
on
us
ing
de
e
p
lear
ning
tec
hnique
(
Suc
he
tha
G.
)
1101
2.
4.
GRU
ar
c
h
it
e
c
t
u
r
e
T
h
e
GR
U,
a
t
y
pe
o
f
r
e
c
ur
r
e
n
t
n
e
ur
a
l
n
e
t
wo
r
k
(
R
NN
)
,
wa
s
c
h
o
s
e
n
f
o
r
i
t
s
e
f
f
i
c
i
e
n
c
y
i
n
pr
o
c
e
s
s
i
ng
s
e
que
n
t
i
a
l
da
t
a
,
e
s
s
e
n
t
i
a
l
f
o
r
de
t
e
c
t
i
n
g
b
o
t
n
e
t
a
c
t
i
vi
t
i
e
s
.
T
hi
s
m
o
de
l
,
im
p
l
e
m
e
n
t
e
d
wi
t
h
t
h
e
Ke
r
a
s
S
e
que
n
t
i
a
l
A
P
I
,
us
e
s
GR
U
to
c
a
pt
u
r
e
l
o
n
g
-
t
e
r
m
de
pe
n
de
n
c
i
e
s
t
h
r
o
ugh
i
t
s
m
e
m
o
r
y
uni
t
s
a
n
d
m
o
r
e
e
f
f
i
c
i
e
n
t
a
r
c
hi
t
e
c
t
ur
e
t
h
a
n
L
S
T
M
,
whi
l
e
s
t
i
l
l
m
a
i
n
t
a
i
ni
ng
r
o
b
us
t
pe
r
f
o
r
m
a
n
c
e
.
T
hi
s
a
r
c
hi
t
e
c
t
ur
e
,
c
o
m
bi
ne
d
w
i
t
h
dr
o
p
o
u
t
t
e
c
hni
que
s
to
pr
e
v
e
n
t
o
v
e
r
f
i
t
t
i
n
g,
e
n
s
ur
e
s
t
h
e
m
o
de
l
’
s
s
u
i
t
a
bil
i
t
y
f
o
r
r
e
a
l
-
t
i
m
e
a
pp
li
c
a
t
i
o
n
s
i
n
r
e
s
o
ur
c
e
-
c
o
n
s
t
r
a
i
n
e
d
I
oT
e
nvi
r
o
nm
e
n
t
s
.
A
dd
i
t
i
o
n
a
ll
y
,
GR
U
’
s
ga
t
i
n
g
m
e
c
h
a
ni
s
m
a
ll
o
ws
i
t
to
c
a
p
t
ur
e
l
o
n
g
-
t
e
r
m
de
pe
n
de
n
c
i
e
s
i
n
da
t
a
e
f
f
e
c
t
i
v
e
ly
,
pr
o
vi
d
i
ng
a
goo
d
b
a
l
a
n
c
e
b
e
t
we
e
n
m
o
de
l
c
o
m
p
l
e
xi
t
y
a
n
d
pe
r
f
o
r
m
a
n
c
e
.
A
GR
U
u
ni
t
’
s
pr
i
n
c
i
pa
l
pa
r
t
s
a
r
e
a
s
(
2)
-
(
5)
.
=
(
∙
∙
∙
[
ℎ
−
1
,
]
+
)
(
2)
=
(
∙
[
ℎ
−
1
,
]
+
)
(
3)
ℎ
′
=
ℎ
(
∙
[
⊙
ℎ
−
1
,
]
+
ℎ
)
(
4)
ℎ
=
(
1
−
)
⊙
ℎ
−
1
+
⊙
ℎ
′
(
5)
I
n
o
r
de
r
to
i
m
pr
o
v
e
da
t
a
qua
l
i
t
y
f
o
r
m
o
de
l
t
r
a
i
ni
n
g,
A
l
go
r
i
t
hm
1
de
s
c
r
i
be
s
a
s
y
s
t
e
m
a
t
i
c
m
e
t
h
o
d
to
b
o
t
n
e
t
d
e
te
c
t
i
o
n
t
h
a
t
f
o
c
us
s
e
s
pr
e
p
r
oc
e
s
s
i
n
g
,
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
u
s
i
n
g
S
e
l
e
c
t
K
B
e
s
t,
a
n
d
l
a
b
e
l
e
n
c
odi
n
g
.
S
tan
da
r
d
-
S
c
a
l
e
r
p
os
t
da
ta
s
pl
i
tt
i
n
g
i
s
us
e
d
f
or
f
e
a
t
u
r
e
s
c
a
l
i
ng
i
n
or
de
r
to
s
pe
e
d
u
p
m
ode
l
c
o
n
v
e
r
ge
n
c
e
.
On
e
H
o
tE
n
c
od
e
r
c
o
n
v
e
r
ts
c
a
te
g
or
i
c
a
l
l
a
b
e
l
s
i
n
to
n
um
e
r
i
c
a
l
f
or
m
a
t.
T
h
e
12
8
-
uni
t
GR
U
l
a
y
e
r
o
f
t
h
e
GR
U
m
o
d
e
l
,
whi
c
h
w
a
s
c
o
n
s
tr
u
c
ted
us
i
n
g
K
e
r
a
s
’
s
S
e
q
ue
n
t
i
a
l
A
P
I
,
i
s
us
e
d
f
or
s
e
q
ue
n
t
i
a
l
da
ta
pr
oc
e
s
s
i
n
g.
A
dr
op
ou
t
l
a
y
e
r
wi
t
h
a
r
a
te
o
f
0
.
5
r
a
n
d
o
m
l
y
e
l
i
mi
n
a
t
e
s
i
n
pu
t
u
n
i
t
s
d
u
r
i
n
g
tr
a
i
ni
n
g
to
a
v
o
i
d
o
v
e
r
f
i
tt
i
n
g.
A
de
n
s
e
l
y
c
o
n
n
e
c
t
e
d
l
a
y
e
r
wi
t
h
6
4
uni
t
s
a
n
d
a
r
e
c
t
i
f
i
e
d
l
i
n
e
a
r
uni
t
(
R
e
L
U)
a
c
t
i
v
a
t
i
o
n
f
un
c
t
i
o
n
a
r
e
u
s
e
d
to
i
n
t
r
o
duc
e
n
o
n
-
l
i
ne
a
r
i
t
y
[
24]
,
[
25
]
.
Al
go
r
i
t
hm
1
.
F
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
,
da
t
a
s
p
l
i
t
t
i
n
g,
f
e
a
t
ur
e
s
c
a
l
i
ng,
a
n
d
l
a
b
e
l
e
n
c
odi
n
g
Require:
Feature
matrix
(
X
),
Label
vector
(
y
),
Number
of
features
to
select
(
k
),
Num
ber
of
c
la
ss
es
Ensure:
T
r
an
sf
or
me
d
f
ea
tu
re
s
X
se
le
ct
ed
,
E
nc
ode
d
l
ab
el
s
y
en
co
de
d
,
Sp
li
t
d
at
as
et
s
(
X
t
rai
n
,
X
va
l
,
X
te
st
,
y
tra
in
,
y
v
al
,
y
test
)
1:
Perform
Feature
S
e
le
ct
io
n:
2:
Use
SelectKBest
with
chi
-
squared
scoring
to
select
the
top
k
f
e
at
ur
es
.
3:
Fit
SelectKBest
on
the
features
(
X
)
and
la
bels
(
y
).
4:
Transform
the
features
(
X
)
to
obtain
the
s
elected
features
(
X
s
el
ec
te
d
).
5:
Split
the
Data:
6:
Split
the
dataset
into
training,
validatio
n,
and
testing
s
et
s.
7:
Scale
the
F
ea
tu
re
s:
8:
Scale
the
features
using
St
an
da
rd
Sc
al
er
.
9:
Fit
the
scaler
on
the
training
set
and
tran
sform
all
sets
of
f
e
at
ur
es
.
10:
Encode
the
La
be
ls
:
11:
Perform
one
-
hot
encoding
on
the
labels
usin
g
On
eH
ot
En
co
de
r.
12:
Fit
the
encoder
on
the
training
labels
and
transform
all
sets
of
l
a
be
ls
.
T
h
e
A
l
go
r
i
t
hm
2
de
s
c
r
i
be
s
h
o
w
t
h
e
GR
U
-
b
a
s
e
d
m
o
de
l
i
s
b
u
il
t
,
t
r
a
i
n
e
d,
e
v
a
l
ua
t
e
d,
a
n
d
s
a
v
e
d,
a
s
s
ur
i
ng
m
a
xim
u
m
pe
r
f
o
r
m
a
n
c
e
f
o
r
b
ot
n
e
t
de
t
e
c
t
i
o
n
t
h
r
o
u
gh
o
r
ga
ni
s
e
d
c
o
m
p
i
l
a
t
i
o
n
a
n
d
v
a
li
da
t
i
o
n
.
T
r
a
i
ni
n
g
o
c
c
ur
s
o
v
e
r
200
e
po
c
h
s
w
i
t
h
a
b
a
t
c
h
s
i
z
e
o
f
32,
ut
i
li
z
i
n
g
v
a
li
da
t
i
o
n
da
t
a
to
pr
e
v
e
n
t
o
v
e
r
f
i
t
t
i
n
g.
E
v
a
l
ua
t
i
o
n
o
n
t
h
e
t
e
s
t
i
n
g
da
t
a
s
e
t
pr
o
vi
d
e
s
m
e
t
r
i
c
s
li
ke
t
e
s
t
l
o
s
s
a
n
d
a
c
c
ur
a
c
y
,
a
s
s
e
s
s
i
ng
t
h
e
m
o
de
l
’
s
a
bi
li
t
y
t
o
c
l
a
s
s
i
f
y
u
n
k
n
o
wn
da
t
a
.
I
n
n
e
ur
a
l
n
e
t
wo
r
ks
,
R
e
L
U
f
u
n
c
t
i
o
n
h
=
m
a
x
(
0
,
a
)
i
s
pr
e
f
e
r
r
e
d
f
o
r
c
l
a
s
s
if
i
c
a
t
i
o
n
due
to
i
t
s
c
o
n
s
t
a
n
t
gr
a
d
i
e
n
t
f
o
r
po
s
i
t
i
v
e
i
nput
s
,
m
i
t
i
g
a
t
i
n
g
t
h
e
va
ni
s
hi
ng
gr
a
d
i
e
n
t
i
s
s
ue
o
f
s
i
g
m
o
i
d
f
u
nc
t
i
o
ns
a
n
d
e
n
a
bli
ng
f
a
s
t
e
r
l
e
a
r
ni
ng.
T
o
e
nh
a
n
c
e
t
h
e
m
o
de
l
’
s
pe
r
f
o
r
m
a
n
c
e
,
s
e
v
e
r
a
l
f
e
a
t
ur
e
e
n
g
i
ne
e
r
i
ng
t
e
c
hni
que
s
w
e
r
e
e
m
p
l
o
y
e
d.
T
his
i
nc
l
ude
d
n
o
r
m
a
l
i
z
a
t
i
o
n
to
s
c
a
l
e
t
h
e
da
t
a
,
o
n
e
-
h
ot
e
n
c
o
d
i
n
g
f
o
r
c
a
t
e
g
o
r
i
c
a
l
v
a
r
i
a
bl
e
s
,
a
n
d
t
h
e
a
pp
l
i
c
a
t
i
o
n
o
f
S
e
l
e
c
t
KB
e
s
t
f
o
r
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
us
i
ng
t
h
e
c
hi
-
s
qua
r
e
d
t
e
s
t
.
T
h
e
s
e
t
e
c
h
ni
qu
e
s
we
r
e
e
s
s
e
n
t
i
a
l
i
n
r
e
duc
i
n
g
d
i
m
e
n
s
i
o
na
l
i
t
y
,
i
m
pr
o
vi
ng
m
o
de
l
a
c
c
ur
a
c
y
,
a
n
d
r
e
duc
i
n
g
o
v
e
r
f
i
t
t
i
n
g
by
s
e
l
e
c
t
i
n
g
t
h
e
m
o
s
t
r
e
l
e
v
a
n
t
f
e
a
t
ur
e
s
.
Al
go
r
i
t
hm
2
.
M
o
de
l
b
u
il
d
i
ng,
c
o
m
p
i
l
a
t
i
o
n
,
t
r
a
i
ni
n
g,
e
v
a
l
ua
t
i
o
n
,
a
n
d
m
o
de
l
s
a
vi
ng
Require:
Transformed features Xselected, Encoded labels yencoded, Number of classes
Ensure:
Trained GRU model, Test loss, Test accuracy
1: Build the Model:
2:
Build a Sequential model using Keras.
3:
Add a GRU layer with 128 units and the input shape based on the
selected features.
4:
Add a Dropout layer with a dropout rate of 0.5.
5:
Add a Dense layer with 64 units and ReLU activation function.
6:
Add
a
Dense
output
layer
with
units
equ
al
to
the
number
of
classes
and
softmax
activation.
7: Compile the Model:
8:
Co
mpile with Adam (learning rate 0.001) and categorical cross
-
entropy loss.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
:
1
098
-
1
105
1102
9: Train the Model:
10:
Reshape
the
data
for
the
GRU
input
and
tr
ain
for
200
epochs
(batch
size
32)
using
validation data.
11: Evaluate the Model:
12:
Evaluate
the
trained
model
on
t
he
testing
data
to
obtain
the
test
loss
and
accuracy
and save the model
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
h
e
e
x
pe
r
im
e
n
t
s
i
n
t
hi
s
s
t
udy
we
r
e
c
o
n
duc
t
e
d
us
i
n
g
P
y
t
h
o
n
3.
12.
0
i
n
J
up
y
t
e
r
Not
e
b
oo
k
7
.
0.
6
o
n
a
W
i
ndo
ws
10
×
64
m
a
c
hi
ne
w
i
t
h
a
n
I
n
t
e
l
C
o
r
e
i
5
pr
o
c
e
s
s
o
r
a
n
d
16
GB
o
f
R
AM
.
T
h
e
m
a
c
hi
ne
l
e
a
r
ni
n
g
m
o
de
l
s
we
r
e
de
v
e
l
o
pe
d
a
n
d
e
v
a
l
ua
t
e
d
us
i
n
g
t
h
e
S
c
i
k
i
t
-
L
e
a
r
n
l
i
br
a
r
y
.
Our
pr
o
p
o
s
e
d
GR
U
-
b
a
s
e
d
de
e
p
l
e
a
r
ni
n
g
m
o
de
l
f
o
r
b
ot
n
e
t
de
t
e
c
t
i
o
n
wa
s
t
e
s
t
e
d
o
n
t
h
e
UN
S
W
-
NB
1
5
da
t
a
s
e
t
a
n
d
c
o
m
pa
r
e
d
w
i
t
h
s
e
v
e
r
a
l
m
o
de
l
s
,
i
n
c
l
u
d
i
n
g
R
F
,
DT
,
K
NN
,
a
n
d
L
S
T
M
.
T
h
e
GR
U
m
o
de
l
,
c
om
b
i
ne
d
w
i
t
h
t
h
e
S
e
l
e
c
t
K
B
e
s
t
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
d,
o
u
t
pe
r
f
o
r
m
e
d
t
h
e
s
e
m
o
de
l
s
i
n
ke
y
m
e
t
r
i
c
s
s
uc
h
a
s
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
-
s
c
o
r
e
.
A
c
r
uc
i
a
l
s
t
e
p
i
n
o
ur
a
ppr
o
a
c
h
wa
s
t
h
e
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
pr
o
c
e
s
s
,
wh
e
r
e
t
h
e
S
e
l
e
c
t
K
B
e
s
t
m
e
t
h
o
d
wa
s
e
m
p
l
o
y
e
d
t
o
i
de
n
t
i
f
y
t
h
e
m
o
s
t
r
e
l
e
va
n
t
f
e
a
t
ur
e
s
f
r
o
m
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
.
F
i
gur
e
2
i
ll
us
t
r
a
t
e
s
t
h
e
to
p
20
f
e
a
t
ur
e
s
s
e
l
e
c
t
e
d
b
a
s
e
d
o
n
t
h
e
c
hi
-
s
qu
a
r
e
s
c
o
r
e
s
,
whi
c
h
we
r
e
c
r
uc
i
a
l
i
n
o
pt
i
mi
z
i
ng
t
h
e
pe
r
f
o
r
m
a
nc
e
o
f
t
h
e
GR
U
m
o
de
l
.
T
h
e
s
e
f
e
a
t
ur
e
s
s
i
g
nif
i
c
a
n
t
l
y
c
o
n
t
r
i
b
ut
e
d
to
r
e
duc
i
n
g
t
h
e
m
o
de
l
’
s
c
o
m
p
l
e
xi
t
y
w
hil
e
m
a
i
n
t
a
i
n
i
ng
hi
g
h
a
c
c
ur
a
c
y
,
a
s
t
h
e
y
r
e
pr
e
s
e
n
t
e
d
t
h
e
m
o
s
t
i
nf
o
r
m
a
t
i
v
e
a
tt
r
i
b
ut
e
s
f
o
r
b
ot
n
e
t
de
t
e
c
t
i
o
n
.
T
h
e
a
bi
li
t
y
to
e
f
f
e
c
t
i
ve
ly
f
il
t
e
r
o
u
t
l
e
s
s
r
e
l
e
v
a
n
t
f
e
a
t
ur
e
s
n
ot
o
nl
y
im
pr
o
v
e
d
t
h
e
m
o
de
l
’
s
a
c
c
ur
a
c
y
but
a
l
s
o
pl
a
y
e
d
a
r
o
l
e
i
n
r
e
duc
i
n
g
o
v
e
r
f
i
t
t
i
n
g,
whi
c
h
i
s
o
f
t
e
n
a
c
h
a
ll
e
n
ge
i
n
m
a
c
hi
ne
l
e
a
r
ni
ng
m
o
de
l
s
de
a
l
i
ng
w
it
h
hi
g
h
-
d
im
e
n
s
i
o
n
a
l
da
t
a
.
F
i
gur
e
2.
T
o
p
20
f
e
a
t
ur
e
s
f
r
o
m
S
e
l
e
c
t
KB
e
s
t
Our
f
i
nd
i
ngs
a
l
i
g
n
w
i
t
h
e
a
r
l
i
e
r
r
e
s
e
a
r
c
h
t
h
a
t
hi
g
hli
g
h
t
s
t
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
de
e
p
l
e
a
r
ni
ng
m
o
de
l
s
i
n
I
DSs
.
F
or
i
n
s
t
a
nc
e
,
Yua
n
e
t
al.
[
4
]
e
m
p
l
o
y
e
d
C
NN
s
a
n
d
L
S
T
M
m
o
de
l
s
f
o
r
de
t
e
c
t
i
n
g
DD
o
S
a
tt
a
c
ks
,
a
c
hi
e
vi
ng
hi
g
h
a
c
c
ur
a
c
y
.
Ho
we
v
e
r
,
o
ur
GR
U
-
b
a
s
e
d
m
o
de
l
,
e
n
h
a
nc
e
d
by
t
h
e
S
e
l
e
c
t
K
B
e
s
t
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
,
s
ur
pa
s
s
e
s
t
h
e
s
e
r
e
s
u
l
t
s
,
pa
r
t
i
c
u
l
a
r
ly
i
n
t
h
e
c
o
n
t
e
x
t
o
f
h
a
n
d
li
n
g
t
h
e
c
o
m
p
l
e
xi
t
i
e
s
o
f
I
oT
n
e
t
w
o
r
k
t
r
a
f
f
i
c
.
T
hi
s
s
ug
ge
s
t
s
t
h
a
t
GR
U
n
e
t
wo
r
ks
a
r
e
pa
r
t
i
c
u
l
a
r
ly
w
e
l
l
-
s
u
i
t
e
d
f
o
r
pr
oc
e
s
s
i
ng
s
e
que
n
t
i
a
l
d
a
t
a
wi
t
h
hi
g
h
-
d
i
m
e
n
s
i
o
n
a
l
f
e
a
t
ur
e
s
,
a
s
f
o
u
n
d
i
n
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
.
W
h
e
n
c
o
m
pa
r
i
n
g
o
ur
r
e
s
u
l
t
s
wi
t
h
Ka
s
o
n
go
a
n
d
S
un
[
8]
,
wh
o
us
e
d
XG
B
o
o
s
t
f
o
r
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
n
t
h
e
U
NSW
-
NB
15
da
t
a
s
e
t
,
o
ur
GR
U
m
o
de
l
d
e
m
o
n
s
t
r
a
ted
hi
g
h
e
r
a
c
c
ur
a
c
y
a
n
d
l
o
we
r
e
r
r
o
r
r
a
t
e
s
.
T
hi
s
pe
r
f
o
r
m
a
n
c
e
d
i
f
f
e
r
e
n
c
e
l
i
ke
ly
a
r
i
s
e
s
f
r
o
m
t
h
e
GR
U’
s
a
bil
i
t
y
t
o
m
a
i
n
t
a
in
i
n
f
o
r
m
a
t
i
o
n
o
v
e
r
l
o
n
ge
r
s
e
que
n
c
e
s
,
c
r
uc
i
a
l
f
o
r
a
c
c
ur
a
t
e
l
y
i
d
e
n
t
i
f
yi
ng
s
o
phi
s
t
i
c
a
t
e
d
b
ot
n
e
t
b
e
h
a
vi
o
r
s
i
n
t
h
e
da
t
a
s
e
t.
M
o
r
e
o
v
e
r
,
o
ur
m
o
de
l
s
h
o
we
d
r
o
b
us
t
n
e
s
s
,
l
i
k
e
ly
due
to
t
h
e
e
f
f
e
c
t
i
v
e
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
pr
oc
e
s
s
a
n
d
dr
o
p
o
u
t
r
e
gul
a
r
i
z
a
t
i
o
n
a
pp
li
e
d
dur
i
n
g
t
r
a
i
ni
n
g,
u
nli
ke
s
o
m
e
ot
h
e
r
s
t
udi
e
s
t
h
a
t
s
tr
uggl
e
d
w
i
t
h
o
v
e
r
f
i
t
t
i
ng
i
s
s
ue
s
.
T
h
e
pr
o
p
o
s
e
d
GR
U
m
o
de
l
a
c
hi
e
v
e
d
a
n
a
c
c
ur
a
c
y
o
f
97.
39%
,
s
i
g
nif
i
c
a
n
t
l
y
s
ur
pa
s
s
i
ng
t
h
e
RF
m
o
de
l
’
s
a
c
c
ur
a
c
y
o
f
96.
538%
a
n
d
t
h
e
L
S
T
M
m
o
de
l
’
s
a
c
c
ur
a
c
y
o
f
96.
94%
.
T
h
e
GR
U
m
o
de
l
’
s
pr
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
w
e
r
e
a
l
s
o
hi
g
h
e
r
,
wi
t
h
pr
e
c
i
s
i
o
n
a
t
98.
10
%
a
n
d
r
e
c
a
l
l
a
t
97.
12%
,
i
n
d
i
c
a
t
i
n
g
t
h
e
m
o
de
l
’
s
e
f
f
e
c
t
i
ve
-
n
e
s
s
i
n
c
o
r
r
e
c
t
ly
i
de
n
t
i
f
y
i
ng
b
o
t
n
e
t
-
r
e
l
a
t
e
d
a
c
t
i
vi
t
i
e
s
.
T
h
e
c
o
nf
us
io
n
m
a
t
r
i
c
e
s
s
h
o
wn
o
n
F
i
gur
e
3
r
e
pr
e
s
e
n
t
s
t
h
e
da
t
a
o
f
d
i
f
f
e
r
e
n
t
M
L
m
o
de
l
s
a
n
d
DL
m
o
de
l
s
.
F
i
gur
e
s
3(
a
)
to
3(
d)
r
e
p
r
e
s
e
n
t
s
t
h
e
pr
e
di
c
t
e
d
v
a
l
ue
s
o
f
L
R
,
KN
N,
DT
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
A
G
R
U
-
bas
e
d
appr
oac
h
f
or
botnet
de
tec
ti
on
us
ing
de
e
p
lear
ning
tec
hnique
(
Suc
he
tha
G.
)
1103
a
n
d
R
F
w
i
t
h
t
h
e
i
m
pr
o
v
e
m
e
n
t
o
f
a
c
c
ur
a
c
y
,
wh
e
r
e
a
s
F
i
gur
e
s
3(
e
)
a
n
d
3(
f
)
r
e
pr
e
s
e
n
t
s
c
o
nf
u
s
i
o
n
m
a
t
r
i
x
o
f
t
h
e
L
S
T
M
a
n
d
t
h
e
pr
o
po
s
e
d
m
o
de
l
GR
U
h
a
vi
ng
t
h
e
hi
g
h
e
s
t
a
c
c
ur
a
c
y
s
h
o
w
i
n
g
s
upe
r
i
o
r
pe
r
f
o
r
m
a
n
c
e
b
y
mi
n
im
i
z
i
ng
b
o
t
h
f
a
l
s
e
po
s
i
t
i
v
e
s
a
n
d
f
a
l
s
e
n
e
ga
t
i
v
e
s
,
l
e
a
d
i
ng
t
o
t
h
e
hi
g
h
e
s
t
F
1
-
s
c
o
r
e
o
f
97.
61%
.
T
h
e
r
e
c
e
i
v
e
r
o
pe
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
(
R
OC
)
c
ur
v
e
a
n
d
l
o
s
s
gr
a
ph
a
n
a
ly
s
i
s
wa
s
c
o
n
duc
t
e
d
to
a
s
s
e
s
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
a
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
a
n
d
a
l
s
o
to
pr
o
vi
de
c
o
m
pr
e
he
ns
i
ve
i
n
s
i
g
h
t
s
i
n
t
o
t
h
e
m
o
de
l
’
s
pe
r
f
o
r
m
a
nc
e
,
a
s
s
h
o
w
n
i
n
F
i
gur
e
4.
T
h
e
R
OC
c
ur
v
e
f
o
r
t
h
e
GR
U
m
o
de
l
i
n
F
i
gur
e
4
(
a
)
h
a
d
t
h
e
hi
g
he
s
t
a
r
e
a
un
de
r
t
h
e
c
ur
ve
(
A
UC
)
,
f
ur
t
h
e
r
r
e
i
nf
o
r
c
i
ng
i
t
s
s
upe
r
i
o
r
pe
r
f
o
r
m
a
n
c
e
.
T
o
pr
o
vi
de
a
c
o
m
pr
e
h
e
n
s
i
ve
c
o
m
pa
r
i
s
o
n
,
T
a
bl
e
1
s
u
m
m
a
-
r
i
z
e
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s
o
f
d
i
f
f
e
r
e
n
t
m
o
de
l
s
,
i
n
c
l
ud
i
ng
L
R
,
K
NN
,
DT
,
R
F
,
L
S
T
M
,
a
n
d
GR
U.
T
h
e
GR
U
m
o
de
l
o
ut
pe
r
f
o
r
m
e
d
a
l
l
o
t
h
e
r
m
o
de
l
s
a
c
r
o
s
s
ke
y
m
e
t
r
i
c
s
,
i
nc
l
ud
i
n
g
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F1
-
s
c
o
r
e
,
un
de
r
s
c
o
r
i
n
g
i
t
s
r
o
b
us
t
n
e
s
s
a
n
d
e
f
f
e
c
t
i
v
e
n
e
s
s
i
n
b
o
t
n
e
t
de
t
e
c
t
i
o
n
.
(
a
)
(
b
)
(
c
)
(
d)
(
e
)
(
f
)
F
i
gur
e
3.
C
o
nf
u
s
i
o
n
m
a
t
r
i
x
o
f
;
(
a
)
l
o
g
i
s
t
i
c
r
e
gr
e
s
s
io
n
(
L
R
)
,
(
b
)
K
NN
,
(
c
)
D
T
,
(
d)
R
F
,
(
e
)
L
S
T
M
,
a
n
d
(
f
)
GR
U
A
ke
y
s
t
r
e
n
gt
h
o
f
o
u
r
a
ppr
o
a
c
h
i
s
t
h
e
i
n
t
e
gr
a
t
i
o
n
o
f
t
h
e
GR
U
m
o
de
l
w
i
t
h
t
h
e
S
e
l
e
c
t
KB
e
s
t
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
d,
whi
c
h
r
e
duc
e
s
d
im
e
n
s
i
o
n
a
li
t
y
w
hil
e
m
a
i
n
t
a
i
n
i
ng
hi
g
h
pe
r
f
o
r
m
a
n
c
e
.
T
h
e
c
hi
-
s
qu
a
r
e
s
t
a
t
i
s
t
i
c
i
n
S
e
l
e
c
t
KB
e
s
t
e
n
s
ur
e
s
t
h
a
t
o
nl
y
r
e
l
e
va
n
t
f
e
a
t
ur
e
s
a
r
e
r
e
t
a
i
n
e
d,
e
nh
a
nc
i
n
g
a
c
c
ur
a
c
y
a
n
d
m
i
n
im
i
z
i
ng
o
v
e
r
f
i
t
t
i
n
g.
Ho
we
v
e
r
,
t
h
e
dr
o
p
o
u
t
l
a
y
e
r
w
i
t
h
a
r
a
t
e
o
f
0.
5
h
e
l
ps
pr
e
v
e
n
t
o
v
e
r
f
i
t
t
i
n
g
dur
i
n
g
t
r
a
i
ni
ng,
a
s
i
n
d
i
c
a
t
e
d
by
t
h
e
s
t
e
a
d
y
de
c
l
i
ne
i
n
v
a
li
da
t
i
o
n
l
o
s
s
o
v
e
r
t
h
e
e
po
c
h
s
a
s
s
h
o
w
n
i
n
F
i
gur
e
4
(
b
)
.
GR
U
o
u
t
pe
r
f
o
r
m
e
d
L
S
T
M
,
de
s
p
i
t
e
L
S
T
M
’
s
s
t
r
e
n
gt
h
i
n
m
a
n
a
g
i
ng
l
o
n
g
-
t
e
r
m
de
p
e
n
de
nc
i
e
s
,
due
to
GR
U’
s
s
im
p
l
e
r
a
r
c
hi
t
e
c
t
ur
e
a
n
d
c
o
m
p
ut
a
t
i
o
n
a
l
e
f
f
i
c
i
e
nc
y
,
w
hi
c
h
a
ll
o
we
d
i
t
to
ge
n
e
r
a
l
i
z
e
b
e
t
t
e
r
to
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t
.
F
ut
u
r
e
r
e
s
e
a
r
c
h
s
h
o
u
l
d
e
x
p
l
o
r
e
o
p
t
i
mi
z
a
t
i
o
n
s
t
h
a
t
m
a
ke
t
h
e
m
o
de
l
m
o
r
e
s
u
i
t
a
bl
e
f
o
r
s
uc
h
e
nvi
r
o
nm
e
n
t
s
.
(
a
)
(
b
)
F
i
gur
e
4.
P
e
r
f
o
r
m
a
n
c
e
gr
a
p
h
s
o
f
t
h
e
GR
U
m
o
de
l
o
n
t
h
e
UN
S
W
-
NB
15
d
a
t
a
s
e
t
,
(
a
)
R
OC
pl
o
t
a
n
d
(
b
)
l
o
s
s
gr
a
ph
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
:
1
098
-
1
105
1104
T
a
bl
e
1.
C
o
m
pa
r
i
s
o
n
o
f
pr
o
p
o
s
e
d
m
o
de
l
’
s
pe
r
f
o
r
m
a
n
c
e
w
i
t
h
ot
h
e
r
de
e
p
l
e
a
r
ni
n
g
m
o
de
l
s
i
nve
s
t
i
ga
t
e
d
i
n
s
t
ud
y
ML
m
o
de
ls
A
c
c
u
r
a
c
y
(
%
)
R
e
c
a
l
l
P
r
e
c
i
s
io
n
F1
-
s
c
o
r
e
(
%
)
E
r
r
o
r
-
r
a
te
LR
9
2
.6
5
0
.
92
08
0
.
94
44
9
3
.2
48
4
0
.
07
34
K
N
N
9
6
.2
16
7
0
.
96
11
0
.
96
97
9
6
.5
43
3
0
.
03
78
DT
9
6
.5
38
5
0
.
96
93
0
.
96
76
9
6
.8
54
3
0
.
03
46
RF
9
6
.8
90
8
0
.
96
91
0
.
97
41
9
7
.1
64
7
0
.
03
11
L
S
T
M
9
6
.9
45
4
0
.
97
73
0
.
96
74
9
7
.2
35
8
0
.
03
05
G
R
U
9
7
.3
88
7
0
.
97
12
0
.
98
10
9
7
.6
12
0
.
02
61
4.
CONC
L
USI
ON
Our
w
o
r
k
s
h
o
ws
t
h
a
t
a
GR
U
-
b
a
s
e
d
de
e
p
l
e
a
r
ni
n
g
m
o
de
l
wa
s
us
e
d
t
o
de
t
e
c
t
b
ot
n
e
t
s
o
n
t
h
e
UN
S
W
-
NB
15
da
t
a
s
e
t.
T
h
e
m
o
de
l
’
s
pe
r
f
o
r
m
a
nc
e
wa
s
e
v
a
luat
e
d
a
ga
i
n
s
t
v
a
r
i
o
us
m
a
c
hi
ne
l
e
a
r
ni
ng
a
n
d
de
e
p
l
e
a
r
ni
ng
m
o
de
l
s
,
i
nc
l
ud
i
ng
R
F
,
LR
,
K
NN
,
DT
,
a
n
d
L
S
T
M
.
F
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
wa
s
pe
r
f
o
r
m
e
d
u
s
i
ng
S
e
l
e
c
t
K
B
e
s
t
wi
t
h
t
h
e
c
hi
-
s
qua
r
e
d
s
t
a
t
i
s
t
i
c
a
l
t
e
s
t
.
T
h
e
GR
U
m
o
de
l
,
c
om
b
i
ne
d
w
i
t
h
S
e
l
e
c
t
K
B
e
s
t
,
o
u
t
pe
r
f
o
r
m
e
d
a
l
l
ot
h
e
r
m
o
de
l
s
,
a
c
hi
e
vi
ng
a
n
a
c
c
ur
a
c
y
o
f
97.
38%
,
a
r
e
c
a
l
l
o
f
97.
12%
,
a
n
d
a
p
r
e
c
i
s
i
o
n
o
f
98.
10%
.
T
hi
s
s
ur
p
a
s
s
e
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
L
S
T
M
m
o
de
l
,
whi
c
h
h
a
d
t
h
e
hi
gh
e
s
t
r
e
c
a
l
l
a
n
d
pr
e
c
i
s
i
o
n
a
m
o
n
g
t
h
e
ot
h
e
r
m
o
de
l
s
,
a
n
d
t
h
e
RF
m
o
de
l
,
w
hi
c
h
a
l
s
o
s
h
o
we
d
s
tr
o
n
g
r
e
s
u
l
t
s
.
T
h
e
r
e
s
u
l
t
s
s
ugge
s
t
t
h
a
t
t
h
e
GR
U
-
b
a
s
e
d
m
o
de
l
i
s
hi
g
hly
e
f
f
e
c
t
i
v
e
f
o
r
r
e
a
l
-
t
i
m
e
i
n
t
r
us
i
o
n
de
t
e
c
t
i
o
n
i
n
I
o
T
e
nvi
r
o
nm
e
n
t
s
,
w
i
t
h
t
h
e
pot
e
n
t
i
a
l
t
o
e
nh
a
n
c
e
c
y
be
r
s
e
c
ur
i
t
y
f
r
a
m
e
wo
r
ks
by
im
pr
o
vi
n
g
de
t
e
c
t
i
o
n
r
a
t
e
s
a
n
d
r
e
duc
i
ng
f
a
l
s
e
po
s
i
t
i
v
e
s
.
F
ut
ur
e
wor
k
wi
ll
f
o
c
us
o
n
a
pp
lyi
ng
t
hi
s
a
p
pr
o
a
c
h
to
ot
h
e
r
b
ot
n
e
t
-
r
e
l
a
t
e
d
da
t
a
s
e
t
s
to
f
ur
t
h
e
r
v
a
l
i
da
t
e
i
t
s
r
o
b
us
t
n
e
s
s
a
n
d
i
n
t
e
gr
a
t
i
n
g
i
t
i
n
t
o
r
e
a
l
-
t
i
m
e
n
e
t
wo
r
k
s
e
c
ur
i
t
y
s
y
s
t
e
m
s
t
o
e
n
ha
n
c
e
pr
ot
e
c
t
i
o
n
a
ga
i
ns
t
e
v
o
l
vi
ng
c
yb
e
r
t
h
r
e
a
t
s
.
RE
F
E
R
E
NC
E
S
[
1]
N
. H
o
qu
e
, D
. K
.
B
ha
tt
a
c
ha
r
yy
a
, a
nd J
. K
. K
a
li
ta
, “
B
o
tn
e
t
in
D
D
o
S
a
tt
a
c
ks
:
t
r
e
nds
a
nd c
ha
ll
e
ng
e
s
,”
I
E
E
E
C
om
m
uni
c
at
io
ns
Sur
v
e
y
s
&
T
ut
or
ia
ls
,
vo
l.
17, n
o
. 4, pp. 2242
–
2270, 2015, d
o
i:
10.1109/
C
O
M
S
T
.2015.2457491.
[
2]
I
r
f
a
n,
I
.
M
.
W
il
da
ni
,
a
nd
I
.
N
.
Y
ul
it
a
,
“
C
la
s
s
if
y
in
g
b
o
tn
e
t
a
tt
a
c
k
o
n
in
te
r
ne
t
of
th
in
gs
de
vi
c
e
us
in
g
r
a
ndo
m
f
or
e
s
t,
”
I
O
P
C
onf
e
r
e
n
c
e
Se
r
ie
s
:
E
ar
th
and E
nv
ir
onm
e
nt
al
Sc
ie
n
c
e
, v
o
l.
248, Apr
. 2019, do
i:
10.1088
/1
755
-
1315/248/
1/
012002.
[
3]
D
.
T
r
a
n,
H
.
M
a
c
,
V
.
T
o
ng,
H
.
A
.
T
r
a
n,
a
nd
L
.
G
.
N
gu
y
e
n,
“
A
L
S
T
M
ba
s
e
d
f
r
a
m
e
w
o
r
k
f
o
r
ha
ndl
in
g
mul
ti
c
la
s
s
im
ba
la
nc
e
in
D
G
A
bo
tn
e
t
d
e
t
e
c
t
i
o
n
,”
N
e
ur
oc
om
put
in
g
, v
o
l.
275, pp. 2401
–
2413, J
a
n. 2018, do
i:
10.1016/j
.n
e
u
c
o
m.2017.11.018.
[
4]
X
. Y
ua
n, C
.
L
i,
a
nd X
.
L
i,
“
D
e
e
pD
e
f
e
ns
e
:
i
d
e
nt
i
f
y
in
g
D
D
o
S
a
t
ta
c
k
v
ia
d
e
e
p
le
a
r
ni
ng,”
i
n
2017
I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
Sm
ar
t
C
om
put
in
g (
SM
A
R
T
C
O
M
P
)
, M
a
y
201
7, pp. 1
–
8. d
o
i:
10.
1109/S
M
A
R
T
C
O
M
P
.2017.7946998.
[
5]
M
.
F
e
il
y
,
A
.
S
ha
hr
e
s
ta
ni
,
a
nd
S
.
R
a
ma
d
a
s
s
,
“
A
s
ur
v
e
y
of
b
o
tn
e
t
a
nd
bo
tn
e
t
d
e
t
e
c
t
i
o
n,”
in
2009
T
hi
r
d
I
nt
e
r
nat
io
nal
C
on
f
e
r
e
nc
e
on
E
m
e
r
gi
ng
Se
c
ur
it
y
I
nf
or
m
at
io
n,
Sy
s
te
m
s
and
T
e
c
hnol
ogi
e
s
,
2009,
pp.
268
–
273
.
do
i:
10.1109/
S
E
C
U
R
W
A
R
E
.2009.48.
[
6]
R
.
D
o
s
hi
,
N
.
A
pt
h
or
pe
,
a
nd
N
.
F
e
a
ms
te
r
,
“
M
a
c
hi
n
e
l
e
a
r
ni
ng
D
D
o
S
de
t
e
c
ti
o
n
f
o
r
c
o
ns
um
e
r
in
te
r
ne
t
of
th
in
gs
d
e
v
ic
e
s
,”
in
2018
I
E
E
E
Se
c
ur
it
y
and P
r
iv
ac
y
W
or
k
s
hops
(
SP
W
)
, M
a
y
2018, pp. 29
–
35.
do
i:
10.1109/
S
P
W
.2018.00013.
[
7]
N
.
M
o
us
ta
f
a
a
nd
J
.
S
la
y
,
“
U
N
S
W
-
N
B
15:
A
c
o
mp
r
e
h
e
ns
i
ve
da
ta
s
e
t
f
o
r
n
e
tw
o
r
k
in
tr
us
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
ms
(
U
N
S
W
-
N
B
15
n
e
tw
o
r
k
da
ta
s
e
t)
,”
in
2015
M
il
i
ta
r
y
C
om
m
uni
c
at
io
ns
and
I
nf
o
r
m
at
io
n
Sy
s
te
m
s
C
on
f
e
r
e
nc
e
(
M
il
C
I
S)
,
N
ov
.
2015,
pp.
1
–
6.
do
i:
10.1109/M
il
C
I
S
.20
15.7348942.
[
8]
S
.
M
.
K
a
s
o
ng
o
a
nd
Y
.
S
un,
“
P
e
r
f
o
r
ma
n
c
e
a
na
l
y
s
is
of
in
tr
us
i
o
n
de
t
e
c
t
i
o
n
s
y
s
te
ms
us
in
g
a
f
e
a
tu
r
e
s
e
l
e
c
ti
o
n
me
th
o
d
o
n
th
e
U
N
S
W
-
N
B
15 da
ta
s
e
t,
”
J
our
nal
of
B
ig
D
at
a
, v
ol
. 7, n
o
. 1, p. 105, De
c
.
2020, do
i:
10.1186/s
40537
-
020
-
00379
-
6.
[
9]
V
.
K
uma
r
,
D
.
S
in
ha
,
A
.
K
.
D
a
s
,
S
.
C
.
P
a
nde
y
,
a
nd
R
.
T
.
G
o
s
w
a
mi
,
“
A
n
in
te
gr
a
t
e
d
r
ul
e
ba
s
e
d
in
t
r
us
io
n
d
e
t
e
c
ti
o
n
s
y
s
t
e
m:
a
na
l
y
s
is
o
n
U
N
S
W
-
N
B
15
da
ta
s
e
t
a
nd
th
e
r
e
a
l
ti
m
e
o
nl
in
e
da
ta
s
e
t,
”
C
lu
s
te
r
C
om
put
in
g
,
v
o
l.
23,
n
o
.
2,
pp.
1397
–
1418,
J
un.
2020,
do
i:
10.1007/s
10586
-
019
-
03008
-
x.
[
10]
S
.
M
e
f
ta
h,
T
.
R
a
c
hi
di
,
a
nd
N
.
A
s
s
e
m,
“
N
e
tw
o
r
k
ba
s
e
d
in
tr
us
i
on
de
t
e
c
ti
o
n
us
in
g
th
e
U
N
S
W
-
N
B
15
d
a
ta
s
e
t,
”
I
nt
e
r
nat
io
nal
J
ou
r
nal
of
C
om
put
in
g and Digit
al
Sy
s
t
e
m
s
, v
o
l.
8, n
o
. 5, pp. 477
–
487, J
a
n. 2019, do
i:
10.12785/i
j
c
ds
/0
80505.
[
11]
M
.
M
o
h
y
-
e
ddi
n
e
,
A
. G
u
e
z
z
a
z
,
S
. B
e
nki
r
a
ne
,
a
nd
M
.
A
z
r
o
ur
,
“
A
n
e
f
f
ic
i
e
nt
n
e
tw
o
r
k
in
tr
us
i
o
n
de
t
e
c
ti
o
n
m
o
d
e
l
f
or
I
oT
s
e
c
ur
it
y
us
in
g
K
-
N
N
c
la
s
s
if
i
e
r
a
nd
f
e
a
tu
r
e
s
e
l
e
c
ti
o
n,”
M
ul
ti
m
e
di
a
T
ool
s
and
A
ppl
ic
at
io
ns
,
vo
l.
82,
no
.
15,
pp.
23615
–
23633,
J
un.
2
023,
do
i:
10.1007/s
11042
-
023
-
14795
-
2.
[
12]
K
.
V
e
nka
ta
c
ha
la
m
a
nd
P
.
J
a
c
o
b,
“
U
N
S
W
-
N
B
15
da
ta
s
e
t
f
e
a
tu
r
e
s
e
l
e
c
t
i
o
n
a
nd
ne
twor
k
in
tr
us
i
o
n
de
t
e
c
ti
o
n
us
in
g
de
e
p
l
e
a
r
ni
n
g,”
I
nt
e
r
nat
io
nal
J
our
nal
of
R
e
c
e
nt
T
e
c
hnol
ogy
and E
ngi
ne
e
r
in
g (
I
J
R
T
E
)
,
vo
l.
7, n
o
. 5
S
2, pp. 443
–
446, 2019.
[
13]
W
.
N
.
H
.
I
b
r
a
hi
m
e
t
al
.
,
“
M
ul
ti
la
y
e
r
f
r
a
m
e
w
o
r
k
f
or
b
o
tn
e
t
d
e
te
c
ti
o
n
us
in
g
ma
c
h
in
e
le
a
r
ni
ng
a
lg
or
it
hms
,”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
9,
pp. 48753
–
48768, 2021, do
i:
10.1109/AC
C
E
S
S
.2021.3060778.
[
14]
M
.
A
bu
R
a
ja
b,
J
.
Z
a
r
f
o
s
s
,
F
.
M
o
nr
o
s
e
,
a
nd
A
.
T
e
r
z
is
,
“
A
mu
lt
i
f
a
c
e
t
e
d
a
ppr
o
a
c
h
t
o
und
e
r
s
ta
ndi
ng
th
e
b
ot
ne
t
ph
e
n
o
m
e
n
o
n,”
in
P
r
oc
e
e
di
ngs
of
th
e
6t
h
A
C
M
SI
G
C
O
M
M
c
on
f
e
r
e
n
c
e
on
I
nt
e
r
n
e
t
m
e
as
u
r
e
m
e
nt
,
O
c
t.
2006,
pp.
41
–
52.
do
i:
10.1145/1177080.1
177086.
[
15]
M
.
T
a
v
a
ll
a
e
e
,
E
.
B
a
ghe
r
i,
W
.
L
u,
a
nd
A
.
A
.
G
ho
r
ba
ni
,
“
A
de
ta
il
e
d
a
na
l
y
s
is
of
th
e
K
D
D
C
U
P
99
da
ta
s
e
t,
”
in
2009
I
E
E
E
Sy
m
pos
iu
m
on
C
om
put
at
io
nal
I
nt
e
ll
ig
e
nc
e
fo
r
Se
c
u
r
it
y
and
D
e
f
e
n
s
e
A
ppl
ic
at
io
ns
,
J
ul
.
2009,
pp.
1
–
6.
do
i:
10.1109/C
I
S
D
A
.2009.5356528.
[
16]
S
.
R
e
v
a
th
i
a
nd
A
.
M
a
la
th
i,
“
A
de
ta
il
e
d
a
na
l
y
s
is
o
n
N
S
L
-
K
D
D
da
ta
s
e
t
us
in
g
v
a
r
i
o
us
ma
c
hi
n
e
l
e
a
r
ni
ng
t
e
c
hni
qu
e
s
f
or
in
t
r
u
s
io
n
de
t
e
c
t
i
o
n,”
I
nt
e
r
nat
io
nal
J
our
nal
of
E
ngi
ne
e
r
in
g R
e
s
e
ar
c
h &
T
e
c
hnol
ogy
(
I
J
E
R
T
,
vo
l.
2, n
o
. 12, pp. 1848
–
1853, 2013.
[
17]
Y
.
Y
in
e
t
al
.
,
“
I
G
RF
-
R
F
E
:
A
h
y
br
id
f
e
a
tu
r
e
s
e
l
e
c
ti
o
n
m
e
th
o
d
f
or
M
L
P
-
ba
s
e
d
n
e
tw
o
r
k
in
tr
us
i
o
n
d
e
te
c
ti
o
n
o
n
U
N
S
W
-
N
B
15
da
ta
s
e
t,
”
J
our
nal
of
B
ig
D
at
a
, v
o
l.
10, n
o
. 1, F
e
b. 2023, d
o
i:
10.1186
/s
40537
-
023
-
00694
-
8.
[
18]
J
.
M
.
P
e
t
e
r
s
o
n,
J
.
L
.
L
e
e
vy
,
a
nd
T
.
M
.
K
h
o
s
hg
of
ta
a
r
,
“
A
r
e
v
i
e
w
a
nd
a
na
l
y
s
is
of
th
e
b
ot
-
I
oT
da
ta
s
e
t,
”
in
2021
I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
Se
r
v
ic
e
-
O
r
ie
n
te
d
Sy
s
te
m
E
ngi
ne
e
r
in
g
(
SO
SE
)
,
A
ug.
2021,
pp.
20
–
27.
do
i:
10.1109/
S
O
S
E
52839.2021.00007.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
A
G
R
U
-
bas
e
d
appr
oac
h
f
or
botnet
de
tec
ti
on
us
ing
de
e
p
lear
ning
tec
hnique
(
Suc
he
tha
G.
)
1105
[
19]
A
. Ö
z
gür
a
nd H
. E
r
d
e
m, “
A
r
e
v
i
e
w
of
K
D
D
99 da
ta
s
e
t
us
a
ge
i
n i
nt
r
us
io
n
d
e
t
e
c
ti
o
n a
nd ma
c
hi
n
e
l
e
a
r
ni
ng be
tw
e
e
n 2010 a
nd 2015
,
”
A
pr
. 14, 2016. do
i:
10.7287
/p
e
e
r
j.
p
r
e
pr
in
ts
.1954
v
1.
[
20]
N
.
M
o
us
ta
f
a
a
nd
J
.
S
la
y
,
“
T
h
e
s
ig
ni
f
i
c
a
nt
f
e
a
tu
r
e
s
of
th
e
U
N
S
W
-
N
B
15
a
nd
th
e
K
D
D
99
da
ta
s
e
ts
f
o
r
n
e
tw
o
r
k
in
t
r
us
io
n
d
e
t
e
c
ti
o
n
s
y
s
te
ms
,”
in
2015
4
th
I
nt
e
r
nat
io
nal
W
or
k
s
hop
on
B
ui
ld
in
g
A
nal
y
s
is
D
at
as
e
ts
and
G
at
he
r
in
g
E
x
pe
r
ie
nc
e
R
e
tu
r
n
s
f
or
Se
c
u
r
it
y
(
B
A
D
G
E
R
S)
, N
ov
. 2015, pp. 25
–
31. d
o
i:
10.1109/
B
A
D
G
E
R
S
.2
015.014.
[
21]
M
. Z
e
e
s
ha
n
e
t
al
.
, “
P
r
o
to
c
o
l
-
ba
s
e
d de
e
p i
nt
r
us
io
n d
e
t
e
c
t
i
o
n f
or
D
o
S
a
nd D
D
o
S
a
tt
a
c
ks
us
in
g U
N
S
W
-
N
B
15 a
nd bo
t
-
I
oT
da
ta
-
s
e
ts
,”
I
E
E
E
A
c
c
e
s
s
, v
ol
. 10, pp. 2269
–
2283, 2022, d
o
i:
10.1109/AC
C
E
S
S
.2021.3137201.
[
22]
N
.
R
.
A
bi
d
-
A
lt
ha
qa
f
i
a
nd
H
.
A
.
A
ls
a
la
ma
h,
“
T
he
e
f
f
e
c
t
of
f
e
a
tu
r
e
s
e
le
c
ti
o
n
o
n
th
e
a
c
c
ur
a
c
y
of
X
-
p
la
t
f
o
r
m
us
e
r
c
r
e
di
bi
li
t
y
d
e
t
e
c
ti
o
n
w
it
h
s
upe
r
v
is
e
d
ma
c
hi
ne
le
a
r
ni
ng,”
E
le
c
tr
oni
c
s
,
vo
l.
13,
n
o
.
1,
J
a
n.
2024,
do
i:
10.3390/
e
l
e
c
tr
o
ni
c
s
13010205.
[
23]
N
.
C
ha
v
a
n,
M
.
K
ukr
e
ja
,
G
.
J
a
gw
a
ni
,
N
.
N
is
ha
d,
a
nd
N
.
D
e
b,
“
D
D
o
S
a
tt
a
c
k
de
t
e
c
ti
o
n
a
nd
b
o
tn
e
t
pr
e
ve
nt
i
o
n
us
in
g
ma
c
hi
ne
l
e
a
r
ni
ng,”
in
2022
8t
h
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
A
dv
anc
e
d
C
om
put
in
g
and
C
om
m
uni
c
at
io
n
Sy
s
te
m
s
(
I
C
A
C
C
S)
,
M
a
r
.
2022,
pp.
1159
–
1
163.
do
i:
10.1109/
I
C
A
C
C
S
54159.2022.9785247.
[
24]
E
.
B
ig
la
r
B
e
ig
i,
H
.
H
a
di
a
n
J
a
z
i,
N
.
S
ta
kha
nov
a
,
a
nd
A
.
A
.
G
ho
r
ba
ni
,
“
T
ow
a
r
ds
e
f
f
e
c
t
i
v
e
f
e
a
tu
r
e
s
e
l
e
c
ti
o
n
in
ma
c
hi
n
e
le
a
r
n
in
g
-
ba
s
e
d bo
tn
e
t
d
e
te
c
ti
o
n a
ppr
o
a
c
h
e
s
,”
i
n
2014 I
E
E
E
C
onf
e
r
e
nc
e
on C
om
m
uni
c
at
io
ns
and
N
e
tw
or
k
Se
c
u
r
it
y
, O
c
t.
2014, pp. 247
–
255.
do
i:
10.1109/C
N
S
.2014.6997492.
[
25]
G
.
K
oc
h
e
r
a
nd
G
.
K
uma
r
,
“
A
na
l
y
s
is
of
ma
c
h
in
e
l
e
a
r
ni
ng
a
lg
or
it
hms
w
it
h
f
e
a
tu
r
e
s
e
l
e
c
t
i
o
n
f
or
in
tr
us
i
o
n
d
e
t
e
c
ti
o
n
us
in
g
U
N
S
W
-
N
B
15
da
ta
s
e
t,
”
I
nt
e
r
nat
io
nal
J
our
nal
o
f
N
e
tw
or
k
Se
c
u
r
it
y
&
I
ts
A
ppl
ic
at
io
ns
,
vo
l.
13,
no
.
1,
pp.
21
–
31,
J
a
n.
20
21,
do
i:
10.5121/i
jn
s
a
.2021.1
3102.
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
Su
c
h
et
h
a
G
.
r
ece
i
v
e
d
t
h
e
B
.
E
.
an
d
M.
T
ec
h
.
d
eg
r
ee
i
n
CSE
fro
m
V
i
s
v
e
s
v
ara
y
a
T
e
ch
n
o
l
o
g
i
c
al
U
n
i
v
e
rs
i
t
y
,
I
n
d
i
a.
Cu
rr
en
t
l
y
,
s
h
e
i
s
w
o
rk
i
n
g
as
an
as
s
i
s
t
an
t
p
ro
fe
s
s
o
r
i
n
t
h
e
D
e
p
art
men
t
o
f
In
fo
r
m
at
i
o
n
S
c
i
en
ce
a
n
d
E
n
g
i
n
ee
r
i
n
g
at
S
ah
y
ad
r
i
Co
l
l
eg
e
o
f
E
n
g
i
n
ee
ri
n
g
an
d
Man
ag
eme
n
t
,
In
d
i
a.
H
e
r
ar
e
a
o
f
i
n
t
e
r
e
s
t
s
i
n
cl
u
d
e
s
cy
b
e
rs
ecu
ri
t
y
,
AI
,
ML
,
an
d
I
o
T
.
Sh
e
h
as
p
u
b
l
i
s
h
ed
r
e
s
e
ar
ch
p
ap
e
rs
i
n
v
ar
i
o
u
s
re
p
u
t
e
d
j
o
u
rn
al
s
a
n
d
co
n
f
e
r
en
ce
s
.
Sh
e
i
s
a
l
i
f
e
mem
b
e
r
o
f
t
h
e
CS
I
an
d
D
at
a
S
c
i
en
ce
A
s
s
o
ci
at
i
o
n
.
S
h
e
c
a
n
b
e
c
o
n
t
ac
t
ed
at
em
ai
l
:
s
u
c
h
e
t
h
a
g
8
7
@
g
m
ai
l
.
co
m
.
D
r.
P
u
s
h
pa
l
a
th
a
K
.
i
s
w
o
r
k
i
n
g
as
Pro
f
e
s
s
o
r
i
n
t
h
e
D
e
p
art
men
t
o
f
A
rt
i
f
i
ci
a
l
I
n
t
e
l
l
i
g
e
n
ce
an
d
Ma
ch
i
n
e
L
e
arn
i
n
g
,
Sah
y
a
d
ri
Co
l
l
eg
e
o
f
E
n
g
i
n
ee
ri
n
g
an
d
Ma
n
ag
emen
t
,
I
n
d
i
a
.
Sh
e
h
as
co
m
p
l
e
t
ed
h
e
r
P
h
.
D
.
i
n
i
m
ag
e
p
ro
ce
s
s
i
n
g
fro
m
N
I
T
K
,
S
u
rat
h
k
a
l
.
S
h
e
h
as
1
5
y
e
ars
o
f
t
e
a
c
h
i
n
g
e
x
p
e
ri
en
ce
.
S
h
e
h
as
p
u
b
l
i
s
h
ed
r
e
s
e
ar
c
h
p
ap
e
rs
i
n
SC
I
i
n
d
e
x
e
d
j
o
u
rn
a
l
s
an
d
c
o
n
f
e
r
e
n
ce
s
.
H
e
r
ar
e
as
o
f
i
n
t
e
r
e
s
t
are
b
i
o
med
i
c
a
l
s
i
g
n
al
p
ro
ce
s
s
i
n
g
a
n
d
b
rai
n
i
m
ag
i
n
g
.
Sh
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
ai
l
:
p
u
s
h
p
ak
@
g
m
a
i
l
.
co
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.