I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
8
,
No
.
1
,
A
p
r
il
20
2
5
,
p
p
.
527
~
534
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
1
.
pp
527
-
5
3
4
527
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
An int
ellig
ent
intr
usio
n det
ec
tion sy
stem t
o
p
revent
U
RL
redirec
tion a
tt
a
ck
Vij
a
y
a
Sh
et
t
y
Sa
da
na
nd
,
P
a
l
a
m
a
neni
Ra
m
esh
Na
idu
,
Dileep
Reddy
B
o
lla
,
J
y
o
t
i N
ee
li,
Ra
m
y
a
P
ra
k
a
s
h
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
N
i
t
t
e
M
e
e
n
a
k
sh
i
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
7
,
2
0
2
4
R
ev
is
ed
Oct
15
,
202
4
Acc
ep
ted
Oct
30
,
2
0
2
4
In
to
d
a
y
’
s
d
ig
i
tal
a
g
e
,
t
h
e
wid
e
sp
r
e
a
d
u
se
o
f
so
c
ial
n
e
two
rk
in
g
p
latf
o
rm
s li
k
e
F
a
c
e
b
o
o
k
,
Twit
ter,
a
n
d
I
n
sta
g
ra
m
,
a
lo
n
g
si
d
e
m
e
ss
a
g
in
g
se
rv
ice
s
su
c
h
a
s
Ema
il
a
n
d
Wh
a
tsAp
p
,
h
a
s
in
c
re
a
se
d
th
e
c
o
n
v
e
n
ien
c
e
o
f
c
o
m
m
u
n
ica
ti
o
n
.
Ho
we
v
e
r,
t
h
is
a
c
c
e
ss
ib
il
it
y
h
a
s
a
lso
p
r
o
v
i
d
e
d
a
fe
rti
le
g
ro
u
n
d
fo
r
c
y
b
e
rc
rimin
a
ls
a
n
d
s
p
a
m
m
e
rs
t
o
e
x
p
l
o
it
th
e
se
p
latfo
rm
s
t
h
ro
u
g
h
URL
re
d
irec
ti
o
n
a
tt
a
c
k
s,
wh
ich
a
re
o
ft
e
n
u
se
d
to
ste
a
l
se
n
siti
v
e
u
se
r
in
f
o
rm
a
ti
o
n
.
Ex
isti
n
g
so
l
u
ti
o
n
s,
i
n
c
lu
d
in
g
m
a
c
h
in
e
lea
rn
in
g
(M
L),
d
e
e
p
lea
rn
in
g
(DL),
a
n
d
e
n
se
m
b
le
m
e
th
o
d
s
h
a
v
e
b
e
e
n
e
m
p
lo
y
e
d
to
c
o
m
b
a
t
su
c
h
th
re
a
t
s.
De
sp
it
e
th
e
ir
e
ffe
c
ti
v
e
n
e
ss
,
t
h
e
se
a
p
p
ro
a
c
h
e
s
stru
g
g
le
to
d
e
tec
t
e
m
e
rg
in
g
ty
p
e
s
o
f
a
tt
a
c
k
s
a
n
d
su
ffe
r
fro
m
li
m
it
a
ti
o
n
s
wh
e
n
d
e
a
li
n
g
wit
h
imb
a
lan
c
e
d
d
a
ta,
lea
d
in
g
to
re
d
u
c
e
d
d
e
tec
ti
o
n
p
e
rfo
rm
a
n
c
e
.
To
a
d
d
re
ss
t
h
e
se
c
h
a
ll
e
n
g
e
s,
t
h
i
s
re
se
a
rc
h
in
tro
d
u
c
e
s
a
n
imp
r
o
v
e
d
e
x
trem
e
g
ra
d
ien
t
b
o
o
sti
n
g
(IXG
B)
a
lg
o
rit
h
m
t
h
a
t
o
p
ti
m
ize
s
t
h
e
we
ig
h
t
a
d
j
u
stm
e
n
ts
i
n
th
e
m
o
d
e
l,
a
imin
g
t
o
e
n
h
a
n
c
e
th
e
d
e
tec
ti
o
n
o
f
m
a
li
c
io
u
s
URLs.
T
h
e
p
r
o
p
o
se
d
m
e
th
o
d
fo
c
u
se
s
o
n
imp
ro
v
i
n
g
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
,
e
sp
e
c
ially
fo
r
n
e
w
o
r
u
n
se
e
n
ty
p
e
s
o
f
a
tt
a
c
k
s.
Ex
p
e
rime
n
tal
re
su
lt
s
o
n
a
sta
n
d
a
rd
d
a
tas
e
t
d
e
m
o
n
stra
te
t
h
a
t
IXG
B
a
c
h
iev
e
s
su
p
e
rio
r
a
c
c
u
ra
c
y
c
o
m
p
a
re
d
to
trad
it
i
o
n
a
l
m
o
d
e
ls,
m
a
k
in
g
it
a
p
ro
m
isin
g
a
p
p
ro
a
c
h
fo
r
e
n
h
a
n
c
in
g
c
y
b
e
rse
c
u
rit
y
o
n
so
c
ial
m
e
d
ia
a
n
d
m
e
ss
a
g
in
g
p
latf
o
rm
s.
K
ey
w
o
r
d
s
:
E
n
s
em
b
le
lear
n
in
g
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
Ma
ch
in
e
lear
n
in
g
Ph
is
h
in
g
Sp
am
m
er
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
:
Vijay
a
Sh
etty
Sad
an
an
d
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Nitte
M
ee
n
ak
s
h
i I
n
s
titu
te
o
f
T
ec
h
n
o
l
o
g
y
B
en
g
alu
r
u
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail:
v
ijay
ash
etty
.
s
@
n
m
it.a
c.
in
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
ter
n
et
an
d
in
tellig
en
t
d
ev
ices
h
av
e
led
to
th
e
wid
esp
r
ea
d
u
s
e
o
f
o
n
lin
e
s
o
cial
n
etwo
r
k
s
(
OSNs
)
,
im
p
ac
tin
g
u
s
er
s
’
wo
r
k
,
s
o
cial
in
ter
ac
tio
n
s
,
a
n
d
c
o
n
ten
t
s
h
ar
in
g
.
Ho
wev
er
,
th
e
g
r
o
win
g
co
m
p
lex
ity
an
d
v
o
l
u
m
e
o
f
d
ata
with
in
OSNs
h
av
e
o
p
en
ed
n
ew
a
v
e
n
u
es
f
o
r
c
y
b
er
th
r
ea
ts
,
s
u
ch
as
UR
L
r
ed
ir
ec
tio
n
attac
k
s
,
lead
in
g
to
p
r
iv
ac
y
b
r
e
ac
h
es
an
d
f
in
an
cial
lo
s
s
es.
T
r
ad
itio
n
al
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
(
I
DS)
,
wh
ich
r
ely
o
n
p
r
e
d
ef
in
ed
s
ig
n
atu
r
es,
ar
e
in
cr
ea
s
in
g
ly
in
ef
f
e
ctiv
e
ag
ain
s
t
m
o
d
e
r
n
a
n
d
ev
o
lv
in
g
th
r
ea
ts
.
C
o
n
s
eq
u
en
tly
,
th
e
n
ee
d
f
o
r
ad
v
an
ce
d
an
o
m
aly
-
b
ased
d
etec
tio
n
s
y
s
tem
s
,
in
co
r
p
o
r
atin
g
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
m
et
h
o
d
s
[
1
]
,
[
2
]
,
is
b
ec
o
m
in
g
cr
u
c
ial.
Ho
wev
er
,
a
s
in
g
le
ML
o
r
DL
ap
p
r
o
ac
h
m
a
y
n
o
t
b
e
s
u
f
f
icien
t
to
tack
le
t
h
e
d
iv
er
s
e
n
atu
r
e
o
f
th
ese
c
y
b
er
th
r
ea
ts
th
e
r
e
v
iew
o
f
r
elev
an
t
liter
atu
r
e
as
d
is
cu
s
s
ed
b
elo
w.
Sev
er
al
r
esear
ch
er
s
h
av
e
co
n
tr
ib
u
ted
to
d
e
v
elo
p
in
g
I
DS
u
s
in
g
ML
an
d
DL
ap
p
r
o
a
ch
es
[
3
]
.
Fer
r
ag
et
a
l.
[
4
]
,
e
v
alu
ated
m
u
ltip
le
DL
m
eth
o
d
s
o
n
d
atasets
lik
e
NSL
-
KDD
an
d
C
I
C
I
D
S
2
0
1
8
.
T
h
ey
f
o
u
n
d
th
at
r
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
s
(
R
NN)
p
er
f
o
r
m
ed
b
est
in
d
etec
tin
g
s
ev
en
ty
p
es
o
f
attac
k
s
,
wh
ile
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
also
s
h
o
wed
p
r
o
m
is
e.
Kar
atas
et
a
l.
[
5
]
,
an
aly
ze
d
s
ix
ML
-
b
ased
I
DS
s
y
s
tem
s
u
s
in
g
alg
o
r
ith
m
s
s
u
ch
as k
-
n
ea
r
est n
eig
h
b
o
r
s
(
KNN)
,
r
an
d
o
m
f
o
r
e
s
t (
R
F),
d
ec
is
io
n
tr
ee
s
(
DT
)
,
an
d
Ad
aBo
o
s
t.
T
h
eir
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
5
2
7
-
5
3
4
528
an
aly
s
is
r
ev
ea
led
v
ar
y
in
g
s
u
c
ce
s
s
r
ates
f
o
r
d
if
f
er
e
n
t
m
eth
o
d
s
d
ep
en
d
in
g
o
n
th
e
ty
p
e
o
f
attac
k
.
Z
h
an
g
et
a
l.
[
6
]
,
d
ev
el
o
p
ed
a
p
lu
g
-
an
d
-
p
l
ay
p
ac
k
et
-
ca
p
tu
r
in
g
ap
p
licati
o
n
f
o
r
d
etec
tin
g
d
is
tr
ib
u
te
d
d
en
ial
o
f
s
er
v
ice
(
DDo
S)
attac
k
s
,
u
tili
zin
g
d
e
ep
n
eu
r
al
n
etwo
r
k
s
(
DNNs)
.
Oth
er
co
n
tr
ib
u
to
r
s
im
p
lem
e
n
ted
d
ee
p
lea
r
n
in
g
ap
p
r
o
ac
h
es
s
u
ch
as
C
NN
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
STM
)
f
o
r
d
etec
tin
g
cr
o
s
s
-
s
ite
s
cr
ip
tin
g
(
XSS)
an
d
SQL
in
jectio
n
attac
k
s
.
Stu
d
ies d
em
o
n
s
tr
ated
t
h
e
p
r
o
s
an
d
c
o
n
s
o
f
d
if
f
e
r
en
t m
o
d
els in
attac
k
d
etec
tio
n
.
L
is
t
o
f
u
n
r
eso
lv
e
d
p
r
o
b
lem
s
a
n
d
ar
ea
s
f
o
r
im
p
r
o
v
em
e
n
t a
r
e:
−
I
n
co
n
s
is
ten
t
p
er
f
o
r
m
a
n
ce
:
n
o
ML
/DL
alg
o
r
ith
m
h
as
co
n
s
is
ten
tly
ex
ce
lled
i
n
d
etec
tin
g
all
f
o
r
m
s
o
f
attac
k
s
ac
r
o
s
s
d
iv
er
s
e
d
atasets
.
−
I
n
cr
ea
s
in
g
tr
a
f
f
ic
co
m
p
lex
ity
:
n
etwo
r
k
tr
af
f
ic
is
in
c
r
ea
s
in
g
ly
d
iv
er
s
e
,
m
ak
in
g
it
d
if
f
icu
lt
f
o
r
ex
is
tin
g
I
DS
m
o
d
els to
k
ee
p
u
p
with
n
ew
f
o
r
m
s
o
f
attac
k
s
.
−
Nee
d
f
o
r
ad
a
p
tiv
e
m
o
d
els:
ex
is
tin
g
I
DS
s
y
s
tem
s
o
f
ten
f
ail
to
ad
ap
t
to
r
ap
id
l
y
ev
o
lv
i
n
g
th
r
ea
ts
an
d
d
y
n
am
ic
attac
k
b
eh
av
i
o
r
s
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
an
in
teg
r
ated
m
eth
o
d
th
at
co
m
b
in
es
th
e
s
tr
en
g
th
s
o
f
m
u
ltip
le
ML
an
d
DL
alg
o
r
ith
m
s
to
im
p
r
o
v
e
o
v
er
all
d
etec
tio
n
r
ate
s
.
B
y
ef
f
icien
tly
in
teg
r
atin
g
d
if
f
er
en
t
d
etec
tio
n
tech
n
iq
u
es,
th
e
ap
p
r
o
ac
h
aim
s
to
m
itig
ate
th
e
wea
k
n
ess
es
o
f
in
d
iv
id
u
al
m
o
d
els
an
d
ad
d
r
ess
th
e
g
r
o
win
g
co
m
p
lex
it
y
o
f
m
o
d
er
n
c
y
b
er
th
r
ea
ts
.
T
h
e
f
o
llo
win
g
s
ec
tio
n
s
will
d
em
o
n
s
tr
ate
h
o
w
th
is
in
teg
r
ate
d
ap
p
r
o
ac
h
was
d
ev
elo
p
ed
,
t
ested
,
an
d
v
alid
ated
ag
ain
s
t
co
n
tem
p
o
r
ar
y
d
atasets
s
u
ch
as
NSL
-
KDD
an
d
C
I
C
I
DS
2
0
1
8
.
T
h
e
r
elev
an
ce
o
f
co
m
b
in
in
g
m
u
ltip
le
d
etec
tio
n
alg
o
r
ith
m
s
will
b
e
estab
lis
h
ed
th
r
o
u
g
h
co
m
p
ar
ativ
e
an
aly
s
is
,
s
h
o
win
g
i
m
p
r
o
v
e
d
d
etec
tio
n
r
ates
o
v
er
s
in
g
le
-
m
eth
o
d
ap
p
r
o
ac
h
es
[
7
]
.
T
h
e
m
eth
o
d
o
lo
g
y
,
ex
p
er
im
e
n
tal
s
etu
p
,
a
n
d
r
esu
lts
will
h
ig
h
lig
h
t
th
e
s
ig
n
if
ican
ce
o
f
a
d
d
r
ess
in
g
cu
r
r
en
t g
ap
s
in
I
DS r
esear
ch
.
T
h
e
s
ig
n
if
ican
ce
o
f
t
h
is
r
esear
ch
is
h
ig
h
lig
h
ted
b
y
th
e
f
o
l
lo
win
g
k
ey
co
n
tr
i
b
u
tio
n
s
:
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
lev
er
a
g
es
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGB)
to
p
er
f
o
r
m
en
s
em
b
le
lear
n
i
n
g
at
th
e
f
ea
tu
r
e
lev
el,
en
h
an
cin
g
d
etec
tio
n
p
er
f
o
r
m
an
ce
.
I
t
in
co
r
p
o
r
ates
an
ef
f
ic
ien
t
f
ea
tu
r
e
o
p
tim
izati
o
n
p
r
o
ce
s
s
u
s
in
g
iter
ativ
e
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
t
o
f
in
e
-
tu
n
e
th
e
m
o
d
el.
E
x
p
e
r
im
en
ts
wer
e
co
n
d
u
cted
u
s
in
g
th
e
NSL
-
KDD
d
ataset,
wh
ich
in
clu
d
es
a
wid
e
v
ar
ie
ty
o
f
attac
k
ty
p
es,
en
s
u
r
in
g
r
o
b
u
s
t
ev
alu
atio
n
.
R
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
u
tp
e
r
f
o
r
m
s
th
e
b
aselin
e
in
ter
m
s
o
f
ac
cu
r
ac
y
,
s
p
ec
if
icity
,
a
n
d
s
en
s
itiv
ity
.
Un
lik
e
ex
is
tin
g
ap
p
r
o
ac
h
es,
th
e
p
r
o
p
o
s
ed
m
o
d
el
s
ig
n
if
ican
tly
r
ed
u
ce
s
th
e
co
m
p
u
tatio
n
al
tim
e
r
eq
u
ir
ed
f
o
r
attac
k
class
if
icatio
n
,
im
p
r
o
v
in
g
o
v
er
all
ef
f
icien
cy
.
T
h
e
f
o
r
m
at
o
f
th
e
ar
ticle
is
as
f
o
llo
ws.
Dif
f
er
en
t
I
DS
h
av
e
b
ee
n
d
escr
ib
ed
in
s
ec
tio
n
2
,
alo
n
g
with
f
ac
to
r
s
th
at
m
o
tiv
ate
th
e
s
tu
d
y
.
I
n
s
ec
tio
n
3
,
we
lay
o
u
t
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
p
e
r
atin
g
m
eth
o
d
.
T
h
e
f
o
cu
s
o
f
s
ec
tio
n
4
is
c
o
m
p
ar
i
n
g
t
h
e
r
es
u
lts
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
to
th
o
s
e
o
f
th
e
b
ase
lin
e
m
o
d
el.
T
h
e
last
s
ec
tio
n
o
f
th
e
r
esear
ch
co
n
clu
d
es with
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
T
h
is
s
ec
tio
n
s
tu
d
ies
d
if
f
er
en
t
s
tate
-
of
-
th
e
-
ar
t
tech
n
i
q
u
es
to
d
etec
t
d
iv
er
s
e
s
ec
u
r
ity
attac
k
s
in
o
n
lin
e
n
etwo
r
k
s
.
T
h
e
co
s
t
o
f
a
d
ata
b
r
ea
ch
ca
n
b
e
esti
m
ated
a
b
o
u
t
th
e
q
u
a
n
tity
o
f
af
f
ec
ted
r
ec
o
r
d
s
,
as
s
u
g
g
ested
b
y
[
8
]
.
A
ML
m
o
d
el
k
n
o
wn
as
R
F
ca
n
b
e
u
s
ed
to
esti
m
ate
h
o
w
m
a
n
y
s
u
c
h
r
ec
o
r
d
s
th
er
e
ar
e.
B
ased
o
n
o
u
r
f
in
d
in
g
s
,
we
i
n
f
er
th
at
th
e
n
u
m
b
er
o
f
af
f
ec
te
d
r
ec
o
r
d
s
h
as
a
Fré
ch
et
d
is
tr
ib
u
tio
n
,
an
d
we
u
s
e
th
is
in
f
o
r
m
atio
n
to
esti
m
ate
th
e
p
ar
am
eter
s
o
f
th
e
g
en
er
alize
d
ex
tr
em
e
v
alu
e
m
o
d
el,
w
h
ich
allo
ws
u
s
to
ca
lcu
late
th
e
v
alu
e
a
t
r
is
k
(
VaR).
T
h
e
g
r
ea
test
lo
s
s
t
h
at
m
ay
b
e
ca
u
s
ed
b
y
a
co
r
p
o
r
ate
d
ata
b
r
ea
ch
ca
n
o
n
ly
b
e
esti
m
ated
u
s
in
g
th
is
s
tu
d
y
,
m
ak
in
g
it c
r
u
cial.
Acc
o
r
d
in
g
to
[
9
]
,
d
u
e
to
th
e
h
i
g
h
d
im
en
s
io
n
ality
a
n
d
en
o
r
m
o
u
s
tails
o
f
r
is
k
p
atter
n
s
,
m
o
d
el
in
g
cy
b
er
h
az
ar
d
s
h
as
b
ee
n
a
s
ig
n
i
f
ican
t
y
et
d
if
f
icu
lt
s
u
b
ject
in
th
e
f
ield
o
f
cy
b
er
s
ec
u
r
ity
.
Pr
o
g
r
ess
in
s
tatis
tical
m
o
d
elin
g
o
f
m
u
ltiv
ar
iate
cy
b
er
r
is
k
s
h
a
s
b
ee
n
s
ty
m
ied
b
y
th
e
af
o
r
em
e
n
tio
n
ed
c
h
allen
g
es
[
10
]
.
I
n
th
is
r
esear
ch
,
au
th
o
r
s
p
r
esen
t
ed
a
n
o
v
el
ap
p
r
o
ac
h
t
o
esti
m
atin
g
th
ese
m
u
ltiv
ar
iate
cy
b
er
r
is
k
s
b
y
co
m
b
in
in
g
DL
with
ex
tr
em
e
v
alu
e
th
eo
r
y
.
T
h
e
r
ec
o
m
m
en
d
ed
m
o
d
el
ca
n
p
r
o
v
id
e
ac
cu
r
ate
p
o
in
t
p
r
e
d
ictio
n
s
an
d
s
atis
f
ac
to
r
y
h
ig
h
-
q
u
an
tile f
o
r
ec
asts
b
y
co
m
b
in
in
g
DL
a
n
d
e
x
tr
em
e
v
al
u
e
th
eo
r
y
[
11
].
N
ajaf
im
eh
r
et
a
l.
[1
2
]
s
h
o
we
d
av
ailab
ilit
y
o
f
th
e
s
er
v
ices
p
lay
s
an
im
p
o
r
tan
t
p
ar
t
in
th
e
co
m
p
u
ter
n
etwo
r
k
s
ec
u
r
ity
ag
ain
s
t
th
e
DDo
S
attac
k
s
.
Ho
wev
er
,
t
h
e
s
e
m
eth
o
d
s
b
ec
o
m
e
in
c
o
m
p
e
ten
t
to
id
e
n
tify
th
e
m
alicio
u
s
tr
af
f
ic.
T
h
is
r
esear
ch
wo
r
k
p
r
esen
ts
a
n
ew
tech
n
iq
u
e
f
o
r
m
er
g
i
n
g
b
o
th
u
n
s
u
p
e
r
v
i
s
ed
an
d
s
u
p
e
r
v
is
ed
lear
n
in
g
m
eth
o
d
s
.
I
n
itial
s
tep
s
in
clu
d
e
u
s
in
g
a
clu
s
ter
in
g
-
b
ased
tech
n
iq
u
e
to
d
if
f
e
r
en
tiate
b
etwe
en
ty
p
ical
an
d
m
alicio
u
s
tr
af
f
ic
b
y
an
aly
zin
g
a
lar
g
e
n
u
m
b
er
o
f
ch
ar
ac
ter
is
tics
d
er
iv
ed
f
r
o
m
th
e
ac
tu
al
d
at
a
f
lo
w.
Nex
t,
s
o
m
e
s
tatis
t
ical
p
ar
am
eter
s
ar
e
m
ea
s
u
r
ed
an
d
u
s
ed
f
o
r
th
e
alg
o
r
ith
m
to
class
if
y
an
d
lab
el
t
h
e
cl
u
s
ter
s
.
B
y
u
s
in
g
th
e
b
ig
d
ata
an
al
y
s
is
,
th
e
p
r
esen
t
ed
tech
n
iq
u
e
is
ev
alu
ate
d
o
n
th
e
tr
ain
in
g
d
ata
s
et
o
f
C
I
C
I
DS
2
0
1
7
a
n
d
it
is
v
er
if
ied
with
a
v
a
r
i
ety
o
f
attac
k
s
th
at
ar
e
s
u
p
p
o
r
ted
in
t
h
e
u
p
d
ated
d
ata
s
et
o
f
C
I
C
DDo
S
2
0
1
9
.
T
h
e
o
u
tco
m
e
o
f
th
is
r
esear
ch
illu
s
tr
ates
th
e
L
R
+
-
p
o
s
itiv
e
lik
elih
o
o
d
r
atio
o
f
th
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
is
an
ap
p
r
o
x
.
9
8
.
0
1
%
m
o
r
e
wh
en
co
m
p
a
r
ed
with
th
e
o
th
er
ML
alg
o
r
ith
m
s
u
s
ed
f
o
r
th
e
class
if
icatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
in
tellig
en
t in
tr
u
s
io
n
d
etec
ti
o
n
s
ystem
to
p
r
ev
en
t U
R
L red
ir
ec
tio
n
a
tta
ck
(
V
ija
ya
S
h
etty
S
a
d
a
n
a
n
d
)
529
Me
g
an
tar
a
an
d
Ah
m
a
d
[
1
3
]
u
s
e
o
f
th
e
in
ter
n
et
h
as
d
ev
elo
p
ed
v
er
y
r
ap
i
d
ly
in
r
ec
en
t
y
ea
r
s
.
Alo
n
g
with
its
b
en
ef
its
,
th
e
in
ter
n
et
h
as
m
an
y
d
is
ad
v
an
tag
es
lik
e
attac
k
s
o
n
cy
b
e
r
s
ec
u
r
ity
a
n
d
o
th
e
r
d
an
g
er
o
u
s
ac
tiv
ities
.
T
o
id
en
tify
th
e
c
y
b
er
-
att
ac
k
s
in
th
e
n
etwo
r
k
s
,
th
e
I
DS
is
em
p
lo
y
ed
,
w
h
ich
d
ete
cts
th
ese
in
co
m
in
g
cy
b
er
-
attac
k
s
[
14
]
.
T
h
e
I
DS w
ill f
u
n
ctio
n
u
s
in
g
two
m
eth
o
d
s
: a
n
o
m
aly
d
etec
tio
n
an
d
s
ig
n
at
u
r
e
d
etec
tio
n
[
1
5
]
.
I
n
th
e
I
DS
b
ased
o
n
th
e
an
o
m
aly
,
th
e
tr
ain
in
g
m
ec
h
an
is
m
o
f
th
e
d
ata
is
af
f
e
cted
b
y
th
e
q
u
ality
o
f
th
e
ML
s
y
s
tem
.
T
h
is
r
esear
ch
wo
r
k
p
r
esen
ts
a
h
y
b
r
id
ML
a
p
p
r
o
ac
h
b
y
m
er
g
in
g
th
e
m
et
h
o
d
s
o
f
s
e
lectin
g
th
e
f
ea
t
u
r
es
with
th
e
s
u
p
e
r
v
is
ed
ML
m
eth
o
d
a
n
d
r
ed
u
cin
g
th
e
in
f
o
r
m
ati
o
n
with
t
h
e
u
n
s
u
p
er
v
is
ed
ML
f
o
r
co
n
s
tr
u
ctin
g
a
s
u
itab
le
m
o
d
el.
T
h
is
s
y
s
tem
wo
r
k
s
b
y
th
e
s
elec
tio
n
o
f
i
m
p
o
r
tan
t
a
n
d
r
elate
d
f
ea
t
u
r
e
s
an
d
r
elies
o
n
th
e
d
ec
is
io
n
tr
ee
o
f
f
ea
tu
r
e
im
p
o
r
tan
ce
a
p
p
r
o
ac
h
.
T
h
e
DT
i
s
b
ased
o
n
th
e
elim
in
atio
n
o
f
f
ea
t
u
r
es
th
at
ar
e
r
ec
u
r
s
iv
e
an
d
p
er
f
o
r
m
s
th
e
d
e
tectio
n
o
f
o
u
tlier
o
r
an
o
m
aly
o
r
m
alici
o
u
s
in
f
o
r
m
atio
n
b
ase
d
o
n
th
e
L
OF
(
lo
ca
l
o
u
tlier
f
ac
to
r
)
ap
p
r
o
ac
h
.
E
x
p
er
im
en
tal
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
p
r
o
v
id
ed
m
eth
o
d
ac
h
iev
es
th
e
b
est
ac
cu
r
ac
y
(
9
9
.
8
9
%)
in
d
etec
tin
g
r
em
o
te
-
to
-
lo
ca
l
(
R
2
L
)
attac
k
s
an
d
m
ain
tain
s
h
ig
h
er
lev
els
o
f
ac
cu
r
ac
y
f
o
r
t
h
e
o
th
er
ty
p
es
o
f
ass
au
lts
wh
en
co
m
p
ar
ed
to
o
th
e
r
s
o
r
ts
o
f
r
esear
ch
ef
f
o
r
ts
in
th
e
NSL
KDD
d
ata
s
et.
Z
h
an
g
et
a
l.
[1
6
]
s
h
o
ws,
s
p
am
m
er
s
h
av
e
s
h
if
ted
th
eir
f
o
c
u
s
f
r
o
m
em
ail
to
s
o
cial
m
ed
i
a
p
latf
o
r
m
s
lik
e
T
witter
b
ec
au
s
e
o
f
th
e
lat
ter
’
s
g
r
o
win
g
im
p
o
r
ta
n
ce
in
ev
er
y
d
a
y
life
an
d
th
e
f
o
r
m
er
’
s
s
wif
t
d
ev
elo
p
m
en
t.
T
o
co
m
b
at
t
h
is
,
we
c
r
ea
te
a
n
o
v
el
s
p
a
m
d
etec
tio
n
tec
h
n
iq
u
e
ca
lled
th
e
im
p
r
o
v
ed
in
cr
e
m
en
tal
f
u
zz
y
-
k
e
r
n
el
-
r
eg
u
lar
ized
e
x
tr
em
e
lear
n
in
g
m
ac
h
in
e
(
I
2
FEL
M)
.
Sriv
astav
a
et
a
l.
[1
7
]
tak
e
th
e
f
ir
s
t step
b
y
in
s
tallin
g
a
n
e
w
ti
m
e
-
b
ased
ca
ch
e
(
T
m
C
ac
h
e)
b
etwe
en
th
e
d
atab
ase
an
d
th
e
T
witter
API
,
wh
ich
elim
in
ates
th
e
co
m
p
l
ex
ity
o
f
th
e
latter
an
d
r
ed
u
ce
s
an
aly
s
is
tim
e
b
y
8
5
.
3
6
p
er
ce
n
t.
I
t
is
d
if
f
icu
lt
to
b
u
ild
a
r
eliab
le
I
DS
in
a
co
lle
ctiv
e
-
attac
k
ca
teg
o
r
izatio
n
s
ettin
g
b
ec
au
s
e
o
f
th
e
co
m
p
lex
ity
o
f
cu
r
r
en
t a
ttack
s
,
as st
ated
in
[
18
]
.
T
o
s
u
cc
ess
f
u
lly
id
en
tify
v
a
r
io
u
s
ty
p
es o
f
at
tack
s
,
o
f
f
er
a
n
o
v
el
en
s
em
b
le
ar
ch
itectu
r
e.
W
ith
an
o
v
er
all
ac
cu
r
ac
y
o
f
9
6
.
9
7
%
an
d
a
r
ec
all
r
ate
o
f
9
7
.
4
%
.
T
h
is
m
o
tiv
ates
th
e
p
r
o
p
o
s
ed
wo
r
k
to
d
esig
n
an
ef
f
ec
tiv
e
ML
-
b
ased
f
ea
tu
r
e
e
n
s
em
b
le
m
o
d
el
to
d
etec
t
d
if
f
er
en
t
attac
k
s
[
19
].
T
h
e
ar
ch
itectu
r
e
o
f
th
e
cu
r
r
e
n
t
en
s
em
b
le
-
b
ased
I
DS sy
s
tem
is
g
iv
en
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
T
h
e
ar
ch
itectu
r
e
o
f
s
tan
d
ar
d
e
n
s
em
b
le
lear
n
in
g
m
o
d
el
f
o
r
attac
k
class
if
icatio
n
3.
P
RO
P
O
S
E
D
M
O
D
E
L
T
h
e
o
b
jectiv
e
o
f
t
h
is
wo
r
k
is
to
d
esig
n
an
in
tellig
en
t
I
DS
t
h
at
ca
n
ef
f
ec
tiv
ely
d
etec
t
d
if
f
er
en
t
UR
L
r
ed
ir
ec
tio
n
n
etwo
r
k
attac
k
s
m
o
r
e
ef
f
icien
tly
as
s
h
o
wn
in
Fig
u
r
e
2
.
I
n
m
ee
tin
g
a
n
o
v
el
en
s
em
b
le
o
f
ML
b
ased
o
n
f
ea
tu
r
e
lev
el
u
s
in
g
XGB
alg
o
r
ith
m
.
T
h
e
wo
r
k
is
f
o
cu
s
ed
in
r
ed
u
cin
g
tim
e
a
n
d
as
well
as
with
b
etter
d
etec
tio
n
ac
cu
r
ac
y
an
d
ef
f
icie
n
cy
.
M
o
r
eo
v
er
,
it
is
ch
allen
g
i
n
g
to
u
s
e
a
s
in
g
le
class
if
ier
to
ef
f
icien
tly
d
etec
t
all
k
in
d
s
o
f
attac
k
s
[
20
]
,
[
21
]
.
T
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
is
b
ased
o
n
b
u
ild
in
g
an
en
s
em
b
le
b
y
r
a
n
k
in
g
th
e
d
etec
tio
n
ab
ilit
y
o
f
d
if
f
er
en
t
b
ase
class
i
f
ier
s
to
id
en
tify
v
ar
io
u
s
ty
p
es
o
f
attac
k
s
.
T
h
e
ac
c
u
r
ac
y
o
f
a
n
alg
o
r
ith
m
is
u
s
ed
to
co
m
p
u
te
th
e
r
an
k
m
atr
ix
f
o
r
d
if
f
er
en
t a
ttack
ca
teg
o
r
ies.
Al
g
o
r
ith
m
:
a.
T
r
ain
all
th
e
class
if
ier
s
ci
in
C
o
n
ea
c
h
r
o
w
r
i
n
th
e
tr
ain
i
n
g
d
ata
T
r
.
b.
C
alcu
late
th
e
ac
cu
r
ac
y
o
f
ea
ch
class
if
ier
ci
f
o
r
ev
er
y
attac
k
c
lass
x
i.
c.
Ass
ig
n
th
e
attac
k
d
etec
tio
n
r
a
n
k
r
ij f
o
r
ea
ch
attac
k
x
i f
o
r
ea
ch
class
if
ier
cj
in
C
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
5
2
7
-
5
3
4
530
d.
Pre
d
ict
th
e
class
f
o
r
ea
ch
r
o
w
in
T
esti
n
g
s
et
T
s
f
o
r
h
ig
h
-
r
a
n
k
ed
class
if
ier
s
in
C
.
e.
T
h
e
r
esu
lts
o
f
th
e
h
i
g
h
est
-
r
a
n
k
class
if
ier
s
ar
e
co
m
p
ar
ed
f
o
r
th
e
f
in
al
r
esu
lt.
C
o
n
s
id
er
in
g
ci
as
th
e
b
est
class
if
ier
f
o
r
p
r
ed
ictin
g
th
e
att
ac
k
x
i.
T
h
e
r
esu
lt
r
ci
(
p
r
ed
ictio
n
r
esu
lt
b
y
class
if
ier
c
f
o
r
th
e
s
am
p
l
e
i)
is
co
m
p
ar
e
d
to
ch
ec
k
if
it
p
r
ed
icts
th
e
attac
k
class
x
i.
I
f
a
m
atch
is
f
o
u
n
d
,
it
is
ad
d
ed
to
th
e
r
esu
lt.
I
f
a
co
n
f
lict
is
f
o
u
n
d
o
r
n
o
m
atch
is
f
o
u
n
d
,
th
e
n
th
e
class
if
ier
’
s
r
esu
lt with
th
e
h
ig
h
er
ac
cu
r
ac
y
is
co
n
s
id
er
ed
.
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
o
f
p
r
o
p
o
s
ed
f
ea
tu
r
e
-
le
v
el
en
s
em
b
le
le
ar
n
in
g
m
o
d
el
f
o
r
attac
k
class
if
icatio
n
T
h
e
XGB
is
a
m
o
d
el
o
f
d
is
tr
ib
u
ted
g
r
a
d
ien
t
b
o
o
s
tin
g
with
s
o
m
e
ex
tr
a
f
ea
t
u
r
es
ad
d
e
d
t
o
m
ak
e
it
m
o
r
e
p
o
wer
f
u
l,
f
lex
i
b
le,
an
d
ad
ap
tiv
e.
Gr
ad
ien
t
b
o
o
s
tin
g
i
s
th
e
f
r
am
ewo
r
k
with
in
wh
ic
h
ML
co
m
p
u
tatio
n
s
a
r
e
p
er
f
o
r
m
ed
[
2
2
]
.
T
h
e
p
ar
a
llel
tr
ee
b
o
o
s
tin
g
m
eth
o
d
o
f
f
er
ed
b
y
XGB,
o
f
ten
k
n
o
wn
a
s
g
r
ad
ien
t
b
o
o
s
tin
g
d
ec
is
io
n
tr
ee
(
GB
DT
)
o
r
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
i
n
e
(
GB
M)
[
2
3
]
ar
e
u
s
ed
to
ac
h
iev
e
r
esu
lts
th
r
o
u
g
h
th
e
ac
cu
m
u
latio
n
o
f
m
an
y
tr
ee
cl
ass
if
ier
s
.
T
o
id
en
tify
p
o
te
n
tially
h
ar
m
f
u
l
UR
L
s
,
th
e
m
o
d
el
em
p
lo
y
s
a
tr
ain
in
g
d
ataset
o
f
s
ize
o
an
d
m
an
y
cla
s
s
if
ier
s
,
as sh
o
wn
in
(
1
)
.
̂
=
(
)
=
∑
ℎ
(
)
,
ℎ
∈
=
1
(
1
)
Z
j
s
tan
d
s
f
o
r
th
e
jth
d
ata
p
o
in
t
in
th
e
tr
ain
in
g
d
ataset,
K
f
o
r
th
e
s
ize
o
f
th
e
tr
ee
u
s
ed
t
o
c
ateg
o
r
ize
m
alicio
u
s
UR
L
s
in
th
e
s
o
cial
n
etwo
r
k
d
ataset,
A
j
f
o
r
th
e
class
if
icati
o
n
r
esu
lts
o
f
o
u
r
m
u
lti
-
lab
el
class
if
icatio
n
m
o
d
el
with
s
p
ec
if
ic
d
im
en
s
io
n
s
,
an
d
K
j
f
o
r
th
e
c
o
llectio
n
o
f
d
ec
is
io
n
tr
ee
s
u
s
ed
to
m
a
k
e
th
at
class
if
icatio
n
.
I
n
th
e
(
1
)
,
th
e
m
u
lti
-
lab
el
s
o
r
ti
n
g
o
r
class
if
icatio
n
m
o
d
el
co
n
clu
s
io
n
s
ar
e
d
ef
in
ed
b
y
̂
,
wh
ich
co
n
f
ir
m
s
h
o
w
a
p
r
o
b
ab
le
m
alicio
u
s
lin
k
will
b
e
ch
ar
ac
ter
ize
d
as
s
u
itab
le
to
an
ac
tu
al
clas
s
b
ased
o
n
its
lab
el.
M
d
esig
n
ates
th
e
s
ize
o
f
th
e
tr
ee
th
at
is
u
s
ed
f
o
r
th
e
class
if
icatio
n
o
f
th
e
m
alev
o
len
t
lin
k
a
n
d
m
ℎ
d
esig
n
ates
th
e
p
o
s
s
ib
ilit
y
th
at
ea
ch
m
alic
io
u
s
li
n
k
will
b
e
class
if
ied
as
r
elate
d
to
a
ce
r
tain
class
.
XG
B
is
a
class
if
icatio
n
m
o
d
el
wh
o
s
e
g
o
al
is
to
m
in
im
ize
a
lo
s
s
p
ar
am
eter
.
(
)
=
∑
(
̂
,
)
+
∑
(
ℎ
)
(
2
)
W
h
er
e,
(
ℎ
)
=
+
‖
‖
2
(
3
)
I
n
(
2
)
,
t
h
e
lo
s
s
f
u
n
ctio
n
b
et
wee
n
th
e
ac
tu
al
an
d
ca
teg
o
r
ized
o
u
tco
m
es
is
d
ef
in
e
d
b
y
th
e
f
ir
s
t
p
ar
am
eter
n
(
̂
,
)
.
T
h
e
s
ec
o
n
d
p
a
r
am
eter
β(h
l
)
d
e
n
o
tes
th
e
p
en
alizin
g
ter
m
,
wh
er
ea
s
V
r
ep
r
e
s
en
ts
th
e
s
ize
o
f
in
d
i
v
id
u
al
lea
v
es
in
a
tr
e
e,
δ
an
d
μ
d
en
o
tes
th
e
s
u
p
er
v
is
o
r
y
p
a
r
am
eter
u
s
ed
to
co
n
tr
o
l
co
m
p
u
tatio
n
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
in
tellig
en
t in
tr
u
s
io
n
d
etec
ti
o
n
s
ystem
to
p
r
ev
en
t U
R
L red
ir
ec
tio
n
a
tta
ck
(
V
ija
ya
S
h
etty
S
a
d
a
n
a
n
d
)
531
co
m
p
lex
ity
.
T
h
e
n
e
g
ativ
e
lo
g
p
r
o
b
ab
ilis
tic
lo
s
s
f
u
n
ctio
n
is
co
m
p
u
ted
u
s
in
g
th
e
f
o
llo
win
g
eq
u
atio
n
u
tili
zin
g
tr
ain
in
g
d
ata
z
with
I
D
s
p
ec
if
i
ed
b
y
n
.
(
̂
,
)
=
−
∑
(
)
l
og
̂
(
)
=
−
l
og
̂
(
)
(
4
)
I
n
(
4
)
,
th
e
a(
l
)
r
ep
r
esen
ts
th
e
j
ℎ
d
im
en
s
io
n
o
f
a.
Als
o
,
w
h
e
r
e
̂
(
n
)
r
e
p
r
esen
ts
th
e
lth
d
im
e
n
s
io
n
o
f
a
.
I
n
ad
d
itio
n
,
th
e
lo
s
s
f
u
n
ctio
n
is
o
p
tim
ized
iter
ativ
ely
to
ac
h
iev
e
a
m
in
im
al
lo
s
s
.
T
h
er
ef
o
r
e,
(
5
)
d
escr
ib
es
th
e
o
p
tim
al
lo
s
s
f
u
n
ctio
n
f
o
r
a
f
ix
ed
v
alu
e
o
f
h
.
=
∑
(
̂
(
−
1
)
+
ℎ
(
)
,
)
+
(
ℎ
)
=
1
(
5
)
T
h
e
s
u
g
g
ested
m
eth
o
d
u
s
es th
e
f
o
llo
win
g
e
q
u
atio
n
t
o
d
eter
m
in
e
h
p
s
o
t
h
at
th
e
lo
s
s
is
g
r
e
ed
ily
m
in
im
ized
.
ℎ
≅
∑
[
(
̂
(
−
1
)
+
)
+
ℎ
(
)
+
1
2
ℎ
2
(
)
]
+
(
ℎ
)
=
1
(
6
)
T
h
e
tr
ee
h
p
ca
n
b
e
f
o
u
n
d
b
y
less
en
in
g
(
6
)
,
wh
er
e
ℎ
d
ep
icts
th
e
f
ir
s
t
-
o
r
d
er
g
r
ad
ie
n
t
o
f
(
̂
(
−
1
)
+
)
an
d
d
ep
icts
th
e
s
ec
o
n
d
-
o
r
d
er
g
r
ad
ie
n
t
o
f
(
̂
(
−
1
)
+
)
.
T
h
e
m
u
ltip
le
s
ets
o
f
K
f
o
ld
s
ar
e
u
s
ed
to
co
n
s
tr
u
ct
th
e
iter
ativ
e
C
V
m
o
d
el.
I
n
s
tead
o
f
tak
in
g
a
s
in
g
le
f
o
ld
as d
ef
in
e
d
in
(
7
)
.
(
)
=
1
∑
∑
(
,
̂
−
(
)
(
,
)
)
∈
−
=
1
(
7
)
T
h
e
o
p
tim
al
v
al
u
e
f
o
r
th
e
̂
is
o
b
tain
ed
b
y
7
,
b
y
o
p
tim
izin
g
th
e
p
ar
am
eter
s
.
̂
=
a
r
g
min
∈
{
1
,
…
,
}
(
)
(
8
)
I
n
(
7
)
,
(
∙
)
d
en
o
tes
lo
s
s
f
u
n
ctio
n
,
̂
−
(
)
(
∙
)
d
en
o
tes
a
f
u
n
ctio
n
f
o
r
ass
ess
in
g
co
ef
f
icien
ts
,
an
d
d
esig
n
ates
tr
ain
in
g
d
ata
s
ize.
T
h
e
lo
s
s
f
u
n
ctio
n
is
r
e
p
r
esen
te
d
as
(
∙
)
.
T
h
e
f
u
n
ctio
n
wh
ich
is
u
s
ed
to
r
ep
r
esen
t
th
e
esti
m
atin
g
o
f
co
ef
f
icien
t
i
s
̂
−
(
)
(
∙
)
th
e
tr
ain
in
g
d
ata
s
et
is
r
ep
r
esen
ted
u
s
i
ng
‘
’
.
Usi
n
g
eq
u
at
io
n
,
th
e
f
ea
tu
r
e
lev
el
o
p
tim
izatio
n
is
d
o
n
e
to
attain
b
etter
p
er
f
o
r
m
a
n
ce
as e
x
p
er
im
en
tally
s
h
o
w
n
in
n
ex
t sectio
n
.
4.
CL
AS
SI
F
I
CAT
I
O
N
O
F
T
R
AINI
NG
DA
T
A
SE
T
T
r
ain
ea
ch
class
if
ier
,
co
m
p
u
t
e
th
e
ac
cu
r
ac
y
o
f
th
e
class
if
ier
,
an
d
d
eter
m
in
e
th
e
r
a
n
k
in
g
o
f
attac
k
d
etec
tio
n
.
T
h
e
h
ig
h
est
r
a
n
k
is
ass
ig
n
ed
to
th
e
class
if
ier
th
at
co
r
r
ec
tly
p
r
ed
icts
an
attac
k
class
.
Utilize
th
e
to
p
-
r
an
k
ed
class
if
ier
s
to
m
ak
e
p
r
ed
ictio
n
s
.
T
h
e
f
in
al
r
esu
lt
is
d
eter
m
in
ed
b
y
co
m
p
ar
in
g
t
h
e
r
esu
lts
f
r
o
m
th
e
h
ig
h
est
-
r
an
k
e
d
class
i
f
ier
s
.
Ass
u
m
in
g
ci
as
th
e
o
p
tim
al
class
i
f
ier
to
p
r
ed
ict
attac
k
class
x
i.
C
o
m
p
ar
e
th
e
r
esu
lt
class
r
ci
(
p
r
ed
ictio
n
g
e
n
er
ated
b
y
p
r
e
d
icto
r
c
,
f
o
r
in
s
tan
ce
,
i)
to
d
eter
m
in
e
if
it f
o
r
ec
asts
th
e
attac
k
class
x
i.
i.
I
f
an
a
p
p
r
o
p
r
iate
m
atch
is
d
is
c
o
v
er
ed
,
in
clu
d
e
it
in
th
e
r
esu
lt.
ii.
I
n
ca
s
e
o
f
a
co
n
tr
ad
ictio
n
o
r
wh
en
n
o
co
r
r
elatio
n
is
f
o
u
n
d
,
p
r
i
o
r
itize
th
e
class
if
icatio
n
r
esu
lt
f
r
o
m
th
e
h
ig
h
er
ac
c
u
r
ac
y
class
if
ier
.
No
tatio
n
: in
th
is
ca
s
e,
F
s
tan
d
s
f
o
r
th
e
d
ataset
’
s
s
et
o
f
f
ea
tu
r
es,
T
r
f
o
r
th
e
tr
ain
in
g
s
et,
T
s
f
o
r
th
e
test
s
et,
X
f
o
r
th
e
s
et
o
f
p
r
e
d
icted
lab
els,
an
d
C
f
o
r
th
e
class
if
ier
s
c1
th
r
o
u
g
h
ct.
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
T
h
is
s
ec
tio
n
ex
am
in
es
th
e
r
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
in
tellig
en
t
I
DS
s
y
s
tem
,
wh
ich
was
tr
ain
ed
u
s
in
g
a
n
o
v
el
f
ea
tu
r
e
en
s
em
b
le
ca
lle
d
XGB
(
FE
-
XGB).
T
h
e
r
esu
lt
is
co
m
p
ar
e
d
with
ex
is
tin
g
I
DS
tr
ain
ed
with
a
s
tan
d
ar
d
en
s
em
b
le
m
o
d
el
[
18
]
.
T
h
e
p
er
f
o
r
m
an
ce
m
etr
ics
co
n
s
id
er
ed
f
o
r
v
alid
atio
n
ar
e
a
cc
u
r
ac
y
,
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
an
d
co
m
p
u
tatio
n
o
v
er
h
ea
d
.
T
o
ass
ess
th
e
d
ep
e
n
d
ab
ilit
y
o
f
m
o
d
els,
a
lar
g
e
r
an
g
e
o
f
ass
au
lts
ar
e
in
clu
d
ed
in
th
e
NSL
-
KDD
d
ataset
[
2
4
]
,
[
2
5
]
.
5
.
1
.
Sens
it
iv
it
y
a
nd
s
pecif
icit
y
T
h
e
s
e
n
s
it
iv
it
y
is
als
o
r
e
p
r
es
en
t
e
d
as
a
t
r
u
e
p
o
s
iti
v
e
r
ate
;
th
u
s
,
t
h
e
h
i
g
h
e
r
t
h
e
v
al
u
e
b
et
te
r
t
h
e
p
e
r
f
o
r
m
a
n
c
e
a
n
d
it
is
ca
lcu
late
d
.
Fig
u
r
e
3
d
is
p
lay
s
th
e
s
en
s
iti
v
ity
r
esu
lts
.
T
h
e
s
e
n
s
iti
v
i
ty
is
also
r
ep
r
ese
n
te
d
as
a
t
r
u
e
n
e
g
at
iv
e
r
a
te;
t
h
u
s
,
t
h
e
h
ig
h
e
r
th
e
v
al
u
e
b
ett
er
t
h
e
p
e
r
f
o
r
m
an
ce
,
it
is
ca
lc
u
la
te
d
as s
h
o
wn
i
n
Fi
g
u
r
e
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
5
2
7
-
5
3
4
532
Fig
u
r
e
3
.
Sen
s
itiv
ity
p
er
f
o
r
m
a
n
ce
Fig
u
r
e
4
.
Sp
ec
if
icity
p
er
f
o
r
m
a
n
ce
5
.
2
.
Acc
ura
cy
a
nd
co
m
pu
t
a
t
io
n o
v
er
hea
d
T
h
e
ac
cu
r
ac
y
d
ef
in
es
h
o
w
e
f
f
ic
ie
n
tl
y
t
h
e
m
o
d
e
l
c
o
r
r
e
ctl
y
class
i
f
i
es
att
ac
k
s
a
n
d
n
o
r
m
a
l
wit
h
l
ess
m
is
class
if
icatio
n
;
t
h
u
s
,
t
h
e
h
i
g
h
e
r
t
h
e
v
a
lu
e
b
ette
r
t
h
e
p
e
r
f
o
r
m
a
n
ce
.
F
ig
u
r
e
5
d
is
p
la
y
s
t
h
e
r
es
u
lts
;
Fi
g
u
r
e
6
s
h
o
ws
th
e
co
m
p
u
ta
ti
o
n
o
v
er
h
e
ad
ta
k
en
f
o
r
cl
ass
i
f
y
in
g
t
h
e
U
R
L
s
.
5
.
3
.
E
f
f
iciency
a
nd
F
-
m
ea
s
ure
E
f
f
i
cie
n
c
y
d
e
f
i
n
es
h
o
w
ef
f
i
cie
n
t
t
h
e
m
o
d
e
l
is
in
c
las
s
if
y
i
n
g
atta
c
k
s
an
d
n
o
r
m
al
wit
h
l
ess
m
is
c
lass
i
f
i
ca
ti
o
n
;
t
h
u
s
,
t
h
e
h
i
g
h
e
r
t
h
e
v
al
u
e
b
e
tte
r
t
h
e
e
f
f
ic
ie
n
c
y
Fi
g
u
r
e
7
d
is
p
la
y
s
t
h
e
r
es
u
lts
.
T
h
e
F
-
m
ea
s
u
r
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
with
th
e
ex
is
tin
g
m
o
d
e
l
with
th
e
g
iv
e
n
d
ataset.
F
-
m
e
asu
r
e
p
er
f
o
r
m
an
ce
with
th
e
p
r
o
p
o
s
ed
m
o
d
el
an
d
t
h
e
ex
is
tin
g
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
8
.
5
.
4
.
Rec
a
ll
T
h
e
r
ec
all
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
d
ep
icted
in
Fig
u
r
e
9
.
T
h
e
v
alu
es
o
b
ta
in
ed
s
h
o
w
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
g
i
v
es
a
r
ec
all
o
f
0
.
7
9
an
d
th
e
e
x
is
tin
g
m
o
d
el
g
iv
es
a
r
ec
all
o
f
0
.
6
9
.
T
h
is
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
h
as a
g
o
o
d
r
ec
all
p
er
f
o
r
m
a
n
ce
as r
elate
d
to
th
e
p
r
esen
t sy
s
tem
.
Fig
u
r
e
5
.
Acc
u
r
a
c
y
p
e
r
f
o
r
m
a
n
ce
Fig
u
r
e
6
.
C
o
m
p
u
t
ati
o
n
o
v
e
r
h
e
ad
Fig
u
r
e
7
.
E
f
f
ici
en
c
y
o
f
t
h
e
p
r
o
p
o
s
e
d
m
o
d
el
Fig
u
r
e
8
.
F
-
m
ea
s
u
r
e
p
er
f
o
r
m
a
n
ce
Fig
u
r
e
9
.
R
ec
all
p
er
f
o
r
m
an
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
in
tellig
en
t in
tr
u
s
io
n
d
etec
ti
o
n
s
ystem
to
p
r
ev
en
t U
R
L red
ir
ec
tio
n
a
tta
ck
(
V
ija
ya
S
h
etty
S
a
d
a
n
a
n
d
)
533
6.
CO
NCLU
SI
O
N
T
r
ad
iti
o
n
al
D
L
m
o
d
els,
w
h
i
le
p
o
we
r
f
u
l
,
o
f
t
en
f
al
l
s
h
o
r
t
i
n
d
e
tect
in
g
n
ew
t
y
p
es
o
f
att
ac
k
s
d
u
e
t
o
th
ei
r
d
e
p
e
n
d
e
n
c
e
o
n
la
r
g
e
d
at
ase
ts
.
ML
m
o
d
els
,
o
n
t
h
e
o
t
h
e
r
h
an
d
,
a
r
e
m
o
r
e
ef
f
ec
ti
v
e
at
h
a
n
d
li
n
g
s
m
al
le
r
d
atas
ets
an
d
i
m
b
al
an
ce
d
d
at
a.
Ho
we
v
e
r
,
e
n
s
e
m
b
le
M
L
m
o
d
e
ls
,
t
h
o
u
g
h
o
f
f
e
r
i
n
g
i
m
p
r
o
v
e
d
a
c
cu
r
a
cy
,
c
o
m
e
wit
h
d
r
aw
b
a
ck
s
s
u
c
h
as
l
o
n
g
er
p
r
o
ce
s
s
i
n
g
ti
m
es
a
n
d
r
e
d
u
ce
d
p
er
f
o
r
m
a
n
c
e
w
h
e
n
e
n
c
o
u
n
te
r
i
n
g
v
a
r
i
ed
at
tac
k
ty
p
es.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
n
e
n
h
a
n
c
ed
f
e
at
u
r
e
e
n
s
e
m
b
l
e
XGB
m
o
d
e
l,
wh
ic
h
s
i
g
n
if
ica
n
t
ly
im
p
r
o
v
es
d
e
tec
ti
o
n
ac
c
u
r
a
cy
w
h
i
le
r
e
d
u
ci
n
g
c
o
m
p
u
t
ati
o
n
al
o
v
e
r
h
ea
d
.
B
y
o
p
ti
m
iz
in
g
s
e
n
s
i
ti
v
it
y
,
s
p
e
ci
f
ic
it
y
,
a
n
d
o
v
er
all
class
i
f
i
ca
t
io
n
p
e
r
f
o
r
m
an
ce
,
th
is
m
o
d
e
l
o
f
f
er
s
a
p
r
o
m
is
i
n
g
s
o
l
u
ti
o
n
to
c
u
r
r
e
n
t
lim
ita
ti
o
n
s
i
n
cy
b
e
r
s
ec
u
r
it
y
.
T
h
is
p
o
s
iti
o
n
s
t
h
e
M
L
-
b
as
e
d
ap
p
r
o
ac
h
as
a
b
et
te
r
alt
er
n
ati
v
e
f
o
r
p
r
ac
t
ic
al
d
ep
lo
y
m
e
n
t
i
n
in
t
r
u
s
i
o
n
d
e
tec
ti
o
n
s
y
s
te
m
s
.
Fu
t
u
r
e
r
ese
ar
ch
s
h
o
u
ld
f
o
c
u
s
o
n
f
u
r
t
h
e
r
v
ali
d
ati
n
g
th
e
p
r
o
p
o
s
ed
m
o
d
el
u
s
i
n
g
m
o
r
e
c
o
m
p
r
eh
en
s
iv
e
d
at
ase
ts
l
ik
e
I
SC
X
I
DS
2
0
1
2
,
C
I
C
-
I
DS
2
0
1
7
,
a
n
d
C
I
C
-
I
DS
2
0
1
8
.
Ad
d
i
ti
o
n
all
y
,
ex
p
l
o
r
i
n
g
a
d
v
a
n
c
ed
al
g
o
r
it
h
m
s
s
u
c
h
as
L
i
g
h
tGB
M
a
n
d
h
is
t
o
g
r
a
m
-
b
ase
d
g
r
ad
ie
n
t
b
o
o
s
ti
n
g
m
a
y
y
ie
ld
e
v
e
n
h
i
g
h
er
d
ete
cti
o
n
r
ates
a
n
d
r
ed
u
ce
d
late
n
cy
.
RE
F
E
R
E
NC
E
S
[
1
]
L.
Lv
,
W
.
W
a
n
g
,
Z.
Z
h
a
n
g
,
a
n
d
X
.
Li
u
,
“
A
n
o
v
e
l
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
b
a
s
e
d
o
n
a
n
o
p
t
i
ma
l
h
y
b
r
i
d
K
e
r
n
e
l
e
x
t
r
e
me
l
e
a
r
n
i
n
g
mac
h
i
n
e
,
”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
st
e
m
s
,
v
o
l
.
1
9
5
,
p
.
1
0
5
6
4
8
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
2
0
.
1
0
5
6
4
8
.
[
2
]
X
.
G
a
o
,
C
.
S
h
a
n
,
C
.
H
u
,
Z.
N
i
u
,
a
n
d
Z
.
L
i
u
,
“
A
n
a
d
a
p
t
i
v
e
e
n
sem
b
l
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
8
2
5
1
2
–
8
2
5
2
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
3
6
4
0
.
[
3
]
A
.
K
h
r
a
i
sa
t
,
I
.
G
o
n
d
a
l
,
P
.
V
a
mp
l
e
w
,
a
n
d
J.
K
a
mr
u
z
z
a
ma
n
,
“
S
u
r
v
e
y
o
f
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
ms
:
t
e
c
h
n
i
q
u
e
s,
d
a
t
a
se
t
s
a
n
d
c
h
a
l
l
e
n
g
e
s,”
C
y
b
e
rse
c
u
r
i
t
y
,
v
o
l
.
2
,
n
o
.
1
,
p
.
2
0
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
2
4
0
0
-
019
-
0
0
3
8
-
7.
[
4
]
M
.
A
.
F
e
r
r
a
g
,
L.
M
a
g
l
a
r
a
s,
S
.
M
o
s
c
h
o
y
i
a
n
n
i
s,
a
n
d
H
.
Ja
n
i
c
k
e
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
c
y
b
e
r
s
e
c
u
r
i
t
y
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
:
a
p
p
r
o
a
c
h
e
s,
d
a
t
a
se
t
s,
a
n
d
c
o
mp
a
r
a
t
i
v
e
s
t
u
d
y
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
0
,
p
.
1
0
2
4
1
9
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
s
a
.
2
0
1
9
.
1
0
2
4
1
9
.
[
5
]
G
.
K
a
r
a
t
a
s,
O
.
D
e
m
i
r
,
a
n
d
O
.
K
.
S
a
h
i
n
g
o
z
,
“
I
n
c
r
e
a
s
i
n
g
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
I
D
S
s
o
n
a
n
i
m
b
a
l
a
n
c
e
d
a
n
d
up
-
to
-
d
a
t
e
d
a
t
a
s
e
t
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
3
2
1
5
0
–
3
2
1
6
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
7
3
2
1
9
.
[
6
]
S
.
Z
h
a
n
g
,
X
.
X
i
e
,
a
n
d
Y
.
X
u
,
“
A
b
r
u
t
e
-
f
o
r
c
e
b
l
a
c
k
-
b
o
x
me
t
h
o
d
t
o
a
t
t
a
c
k
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
sy
s
t
e
m
s
i
n
c
y
b
e
r
s
e
c
u
r
i
t
y
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
2
8
2
5
0
–
1
2
8
2
6
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
8
4
3
3
.
[
7
]
R
.
A
t
e
f
i
n
i
a
a
n
d
M
.
A
h
m
a
d
i
,
“
N
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
u
si
n
g
m
u
l
t
i
-
a
r
c
h
i
t
e
c
t
u
r
a
l
m
o
d
u
l
a
r
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
T
h
e
J
o
u
rn
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
7
,
n
o
.
4
,
p
p
.
3
5
7
1
–
3
5
9
3
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
020
-
0
3
4
1
0
-
y.
[
8
]
Y
.
Z
h
o
u
,
G
.
C
h
e
n
g
,
S
.
J
i
a
n
g
,
a
n
d
M
.
D
a
i
,
“
B
u
i
l
d
i
n
g
a
n
e
f
f
i
c
i
e
n
t
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
b
a
s
e
d
o
n
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
a
n
d
e
n
s
e
mb
l
e
c
l
a
ssi
f
i
e
r
,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
rks
,
v
o
l
.
1
7
4
,
p
.
1
0
7
2
4
7
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
n
e
t
.
2
0
2
0
.
1
0
7
2
4
7
.
[
9
]
M
.
Zh
a
n
g
W
u
,
J.
L
u
o
,
X
.
F
a
n
g
,
M
.
X
u
,
a
n
d
P
.
Z
h
a
o
,
“
M
o
d
e
l
i
n
g
m
u
l
t
i
v
a
r
i
a
t
e
c
y
b
e
r
r
i
sk
s
:
d
e
e
p
l
e
a
r
n
i
n
g
d
a
t
i
n
g
e
x
t
r
e
me
v
a
l
u
e
t
h
e
o
r
y
,
”
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
S
t
a
t
i
st
i
c
s
,
v
o
l
.
5
0
,
n
o
.
3
,
p
p
.
6
1
0
–
6
3
0
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
0
2
6
6
4
7
6
3
.
2
0
2
1
.
1
9
3
6
4
6
8.
[
1
0
]
J.
S
.
K
a
m
d
e
m
a
n
d
D
.
S
e
l
a
m
b
i
,
“
C
y
b
e
r
-
r
i
s
k
f
o
r
e
c
a
st
i
n
g
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
a
n
d
g
e
n
e
r
a
l
i
z
e
d
e
x
t
r
e
me
v
a
l
u
e
d
i
s
t
r
i
b
u
t
i
o
n
s,”
H
AL O
p
e
n
S
c
i
e
n
c
e
,
2
0
2
2
.
[
1
1
]
F
.
F
e
n
g
,
X
.
Li
u
,
B
.
Y
o
n
g
,
R
.
Z
h
o
u
,
a
n
d
Q
.
Z
h
o
u
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
i
n
a
d
-
h
o
c
n
e
t
w
o
r
k
s
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
:
a
p
l
u
g
a
n
d
p
l
a
y
d
e
v
i
c
e
,
”
A
d
H
o
c
N
e
t
w
o
rks
,
v
o
l
.
8
4
,
p
p
.
8
2
–
8
9
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
h
o
c
.
2
0
1
8
.
0
9
.
0
1
4
.
[
1
2
]
M
.
N
a
j
a
f
i
me
h
r
,
S
.
Z
a
r
i
f
z
a
d
e
h
,
a
n
d
S
.
M
o
s
t
a
f
a
v
i
,
“
A
h
y
b
r
i
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
u
n
p
r
e
c
e
d
e
n
t
e
d
D
D
o
S
a
t
t
a
c
k
s,
”
T
h
e
J
o
u
r
n
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
8
,
n
o
.
6
,
p
p
.
8
1
0
6
–
8
1
3
6
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
0
2
1
-
0
4
2
5
3
-
x.
[
1
3
]
A
.
A
.
M
e
g
a
n
t
a
r
a
a
n
d
T.
A
h
ma
d
,
“
A
h
y
b
r
i
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
f
o
r
i
n
c
r
e
a
si
n
g
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
ms,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
8
,
n
o
.
1
,
p
.
1
4
2
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
1
-
0
0
5
3
1
-
w.
[
1
4
]
T.
Zh
u
k
a
b
a
y
e
v
a
,
A
.
P
e
r
v
e
z
,
Y
.
M
a
r
d
e
n
o
v
,
M
.
O
t
h
m
a
n
,
N
.
K
a
r
a
b
a
y
e
v
,
a
n
d
Z.
A
h
m
a
d
,
“
A
t
r
a
f
f
i
c
a
n
a
l
y
s
i
s a
n
d
n
o
d
e
c
a
t
e
g
o
r
i
z
a
t
i
o
n
-
a
w
a
r
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
i
n
t
e
g
r
a
t
e
d
f
r
a
me
w
o
r
k
f
o
r
c
y
b
e
r
s
e
c
u
r
i
t
y
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
o
f
W
S
N
s
i
n
sm
a
r
t
g
r
i
d
s,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
9
1
7
1
5
–
9
1
7
3
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
2
2
0
7
7
.
[
1
5
]
S
.
Ei
n
y
,
C
.
O
z
,
a
n
d
Y
.
D
.
N
a
v
a
e
i
,
“
T
h
e
a
n
o
ma
l
y
-
a
n
d
si
g
n
a
t
u
r
e
-
b
a
s
e
d
I
D
S
f
o
r
n
e
t
w
o
r
k
sec
u
r
i
t
y
u
s
i
n
g
h
y
b
r
i
d
i
n
f
e
r
e
n
c
e
s
y
st
e
ms,
”
Ma
t
h
e
m
a
t
i
c
a
l
Pr
o
b
l
e
m
s i
n
En
g
i
n
e
e
ri
n
g
,
n
o
.
1
,
p
.
6
6
3
9
7
1
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
6
6
3
9
7
1
4
.
[
1
6
]
Z.
Z
h
a
n
g
,
R
.
H
o
u
,
a
n
d
J
.
Y
a
n
g
,
“
D
e
t
e
c
t
i
o
n
o
f
so
c
i
a
l
n
e
t
w
o
r
k
s
p
a
m
b
a
se
d
o
n
i
m
p
r
o
v
e
d
e
x
t
r
e
m
e
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
1
2
0
0
3
–
1
1
2
0
1
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
2
9
4
0
.
[
1
7
]
S
.
S
r
i
v
a
s
t
a
v
a
,
S
.
A
g
r
a
h
a
r
i
,
a
n
d
A
.
K
.
S
i
n
g
h
,
“
E
a
r
l
y
s
p
a
m
d
e
t
e
c
t
i
o
n
u
si
n
g
t
i
m
e
-
b
a
se
d
c
a
c
h
e
i
n
g
r
a
p
h
d
a
t
a
b
a
se
,
”
N
e
w
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
i
n
g
,
v
o
l
.
4
1
,
n
o
.
3
,
p
p
.
6
0
7
–
6
3
4
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
3
5
4
-
023
-
0
0
2
2
3
-
4.
[
1
8
]
S
.
S
e
t
h
,
K
.
K
.
C
h
a
h
a
l
,
a
n
d
G
.
S
i
n
g
h
,
“
A
n
o
v
e
l
e
n
sem
b
l
e
f
r
a
me
w
o
r
k
f
o
r
a
n
i
n
t
e
l
l
i
g
e
n
t
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
3
8
4
5
1
–
1
3
8
4
6
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
1
6
2
1
9
.
[
1
9
]
F
.
A
r
a
u
j
o
,
G
.
A
y
o
a
d
e
,
K
.
A
l
-
N
a
a
mi
,
Y
.
G
a
o
,
K
.
W
.
H
a
m
l
e
n
,
a
n
d
L.
K
h
a
n
,
“
I
mp
r
o
v
i
n
g
i
n
t
r
u
si
o
n
d
e
t
e
c
t
o
r
s
b
y
c
r
o
o
k
-
s
o
u
r
c
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
5
t
h
An
n
u
a
l
C
o
m
p
u
t
e
r
S
e
c
u
r
i
t
y
Ap
p
l
i
c
a
t
i
o
n
s
C
o
n
f
e
r
e
n
c
e
,
D
e
c
.
2
0
1
9
,
p
p
.
2
4
5
–
2
5
6
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
5
9
7
8
9
.
3
3
5
9
8
2
2
.
[
2
0
]
K.
-
H
.
Le
,
M
.
-
H
.
N
g
u
y
e
n
,
T.
-
D
.
Tr
a
n
,
a
n
d
N
.
-
D
.
Tr
a
n
,
“
I
M
I
D
S
:
a
n
i
n
t
e
l
l
i
g
e
n
t
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
a
g
a
i
n
st
c
y
b
e
r
t
h
r
e
a
t
s
i
n
I
o
T,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
4
,
p
.
5
2
4
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
0
4
0
5
2
4
.
[
2
1
]
B
.
A
.
Ta
m
a
,
M
.
C
o
mu
z
z
i
,
a
n
d
K
.
-
H
.
R
h
e
e
,
“
TS
E
-
I
D
S
:
a
t
w
o
-
s
t
a
g
e
c
l
a
ss
i
f
i
e
r
e
n
s
e
m
b
l
e
f
o
r
i
n
t
e
l
l
i
g
e
n
t
a
n
o
m
a
l
y
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
9
4
4
9
7
–
9
4
5
0
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
8
0
4
8
.
[
2
2
]
S
.
S
.
D
h
a
l
i
w
a
l
,
A
.
-
A
.
N
a
h
i
d
,
a
n
d
R
.
A
b
b
a
s
,
“
Ef
f
e
c
t
i
v
e
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
u
si
n
g
X
G
B
o
o
st
,
”
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
7
,
p
.
1
4
9
,
J
u
n
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
i
n
f
o
9
0
7
0
1
4
9
.
[
2
3
]
A
.
E
.
O
m
o
l
a
r
a
a
n
d
M
.
A
l
a
w
i
d
a
,
“
D
a
E2
:
U
n
m
a
sk
i
n
g
ma
l
i
c
i
o
u
s
U
R
Ls
b
y
l
e
v
e
r
a
g
i
n
g
d
i
v
e
r
se
a
n
d
e
f
f
i
c
i
e
n
t
e
n
sem
b
l
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
o
n
l
i
n
e
s
e
c
u
r
i
t
y
,
”
C
o
m
p
u
t
e
rs &
S
e
c
u
ri
t
y
,
v
o
l
.
1
4
8
,
p
.
1
0
4
1
7
0
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
s
e
.
2
0
2
4
.
1
0
4
1
7
0
.
[
2
4
]
“
C
S
E
-
C
I
C
-
I
D
S
2
0
1
8
o
n
A
W
S
,
”
C
a
n
a
d
i
a
n
I
n
s
t
i
t
u
t
e
f
o
r
C
y
b
e
rs
e
c
u
ri
t
y
,
U
N
B
,
2
0
1
8
.
h
t
t
p
s:
/
/
w
w
w
.
u
n
b
.
c
a
/
c
i
c
/
d
a
t
a
se
t
s/
i
d
s
-
2
0
1
8
.
h
t
ml
.
[
2
5
]
M
.
T
a
v
a
l
l
a
e
e
,
E
.
B
a
g
h
e
r
i
,
W
.
L
u
,
a
n
d
A
.
A
.
G
h
o
r
b
a
n
i
,
“
A
d
e
t
a
i
l
e
d
a
n
a
l
y
s
i
s
o
f
t
h
e
K
D
D
C
U
P
9
9
d
a
t
a
s
e
t
,
”
i
n
2
0
0
9
I
EEE
S
y
m
p
o
s
i
u
m
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
S
e
c
u
r
i
t
y
a
n
d
D
e
f
e
n
se
A
p
p
l
i
c
a
t
i
o
n
s
(
C
I
S
D
A)
,
Ju
l
.
2
0
0
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
S
D
A
.
2
0
0
9
.
5
3
5
6
5
2
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
5
2
7
-
5
3
4
534
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Vija
y
a
S
h
e
tt
y
S
a
d
a
n
a
n
d
is
a
p
r
o
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
a
t
NM
IT,
Be
n
g
a
lu
ru
.
S
h
e
is
c
u
rre
n
tl
y
e
x
e
c
u
ti
n
g
a
p
ro
jec
t
in
th
e
d
o
m
a
in
o
f
d
e
e
p
lea
rn
i
n
g
f
u
n
d
e
d
b
y
t
h
e
Visio
n
G
ro
u
p
o
n
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
(VG
S
T).
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
m
in
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
d
istri
b
u
ted
c
o
m
p
u
ti
n
g
.
S
h
e
is
a
Li
fe
m
e
m
b
e
r
o
f
t
h
e
In
d
ian
S
o
c
iety
f
o
r
T
e
c
h
n
ica
l
Ed
u
c
a
ti
o
n
(I
S
TE
),
a
m
e
m
b
e
r
o
f
IE
EE
a
n
d
th
e
C
o
m
p
u
ter
S
o
c
iety
o
f
I
n
d
ia
(CS
I).
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
ij
a
y
a
sh
e
tt
y
.
s@
n
m
it
.
a
c
.
i
n
.
Dr
.
Pa
la
m
a
n
e
n
i
Ra
m
e
sh
Na
id
u
is
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
a
a
ss
o
c
iate
p
ro
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
Nitt
e
M
e
e
n
a
k
sh
i
In
st
it
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Be
n
g
a
l
u
ru
.
He
h
a
s
to
tal
1
7
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
a
n
d
1
y
e
a
r
I
n
d
u
stry
e
x
p
e
rien
c
e
.
His
re
se
a
rc
h
a
re
a
is
c
lo
u
d
c
o
m
p
u
ti
n
g
,
we
b
tec
h
n
o
l
o
g
ies
a
n
d
b
lo
c
k
c
h
a
in
tec
h
n
o
l
o
g
i
e
s.
He
h
a
s
p
u
b
li
sh
e
d
t
o
tal
3
4
in
tern
a
ti
o
n
a
l,
n
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
1
1
p
a
ten
ts.
He
is
a
li
fe
m
e
m
b
e
r
o
f
th
e
I
n
d
ian
S
o
c
iety
f
o
r
Tec
h
n
ica
l
Ed
u
c
a
ti
o
n
(IS
TE
)
a
n
d
li
fe
o
f
In
sti
tu
te
o
f
En
g
i
n
e
e
r
’
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
i
l:
ra
m
e
sh
.
n
a
id
u
@n
m
it
.
a
c
.
in
.
Dr
.
Dilee
p
Re
d
d
y
Bo
ll
a
h
a
s
1
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
i
n
tea
c
h
in
g
a
n
d
0
9
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
re
se
a
rc
h
.
He
is
wo
rk
in
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
CS
E,
Nitt
e
M
e
e
n
a
k
sh
i
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
lo
re
,
Ka
r
n
a
tak
a
,
In
d
ia.
He
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
o
n
th
e
in
si
g
h
ts
o
f
5
G
m
o
b
il
e
c
o
m
m
u
n
ica
ti
o
n
;
i
n
tern
e
t
o
f
t
h
i
n
g
s
(I
o
T
),
M
L,
a
d
v
a
n
c
e
d
e
m
b
e
d
d
e
d
sy
ste
m
s
a
n
d
Io
T
.
He
is
e
x
c
e
ll
e
n
t
t
ime
b
o
u
n
d
e
d
,
e
n
t
h
u
sia
stic
se
lf
-
m
o
ti
v
a
ted
,
re
sp
o
n
si
b
le p
e
rso
n
.
He
is
a
m
a
tu
re
tea
m
wo
rk
e
r
a
n
d
a
d
o
p
ta
b
le
to
c
h
a
ll
e
n
g
i
n
g
si
tu
a
ti
o
n
s.
He
h
a
d
4
4
+
re
se
a
rc
h
a
rti
c
le
in
d
e
x
e
d
i
n
S
c
o
p
u
s,
Wo
S
,
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
to
th
e
c
r
e
d
it
.
He
is
a
n
a
c
ti
v
e
m
e
m
b
e
r
in
IS
TE
,
IEI
,
a
n
d
I
EE
E.
He
is
a
n
in
n
o
v
a
ti
o
n
a
m
b
a
ss
a
d
o
r
fo
r
I
n
stit
u
ti
o
n
’
s
In
n
o
v
a
ti
o
n
Co
u
n
c
il
-
An
In
it
iativ
e
o
f
M
i
n
istry
o
f
Ed
u
c
a
ti
o
n
,
In
d
ia.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
il
e
e
p
.
b
o
ll
a
@g
m
a
il
.
c
o
m
.
Dr
.
J
y
o
ti
Ne
e
li
is
p
ro
fe
ss
o
r
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
De
p
a
rtme
n
t
a
t
Nitt
e
M
e
e
e
n
a
k
sh
i
In
stit
u
te
o
f
tec
h
n
o
lo
g
y
,
Ye
lah
a
n
k
a
,
Ba
n
g
a
lo
re
.
S
h
e
h
a
s
tea
c
h
in
g
e
x
p
e
rien
c
e
o
f
2
3
y
e
a
rs
i
n
a
c
a
d
e
m
ics
.
S
h
e
c
o
m
p
lete
d
h
e
r
P
h
.
D
.
u
n
d
e
r
t
h
e
g
u
id
a
n
c
e
o
f
Dr.
N
K
Ca
u
v
e
ry
P
ro
fe
ss
o
r,
R
V
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
i
n
VTU
u
n
i
v
e
rsity
.
S
h
e
h
a
s
m
a
n
y
p
u
b
l
ica
ti
o
n
s
i
n
re
p
u
ted
j
o
u
r
n
a
ls
with
in
d
e
x
i
n
g
i
n
Wo
S
,
S
CI
,
S
c
o
p
u
s,
S
p
rin
g
e
r,
Tay
lo
r
a
n
d
F
ra
n
c
is
a
n
d
S
c
ien
c
e
d
irec
t.
He
r
p
a
ten
ts
a
re
g
ra
n
te
d
i
n
Au
stra
li
a
n
p
a
ten
t
a
n
d
so
m
e
a
r
e
p
u
b
li
sh
e
d
i
n
In
d
ian
p
a
te
n
t.
S
h
e
is
a
re
v
iew
e
r
to
S
CI
i
n
d
e
x
e
d
jo
u
r
n
a
l
a
n
d
to
m
a
n
y
o
th
e
r
c
o
n
fe
r
e
n
c
e
s.
S
h
e
h
a
s
c
o
u
rse
ra
a
n
d
Np
tel
c
e
rti
fica
ti
o
n
i
n
Io
T
a
n
d
c
y
b
e
rse
c
u
rit
y
,
o
r
g
a
n
ize
d
a
n
d
a
tt
e
n
d
e
d
F
DP
a
n
d
w
o
rk
s
h
o
p
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
j
y
o
th
i
.
n
e
e
li
@n
m
it
.
a
c
.
i
n
.
Ra
m
y
a
Pra
k
a
sh
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
h
e
r
M
.
Tec
h
in
C
o
m
p
u
ter
S
c
ien
c
e
a
t
Nitt
e
M
e
e
n
a
k
sh
i
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Be
n
g
a
l
u
ru
.
S
h
e
h
a
s
1
7
+
y
e
a
r
s
o
f
i
n
d
u
stry
e
x
p
e
rien
c
e
with
a
p
ro
v
e
n
trac
k
re
c
o
rd
o
f
su
c
c
e
ss
fu
ll
y
lea
d
in
g
m
u
lt
i
p
le
tea
m
s
in
d
e
v
e
lo
p
i
n
g
h
i
g
h
-
q
u
a
l
it
y
s
o
ftwa
re
so
lu
ti
o
n
s
f
o
r
t
h
e
h
e
a
lt
h
c
a
re
d
o
m
a
in
,
a
s
a
so
ftwa
re
q
u
a
li
ty
a
n
a
ly
st
a
n
d
d
e
v
e
l
o
p
e
r.
He
r
c
u
rre
n
t
in
tere
sts
a
re
DL,
M
L
a
n
d
th
e
Io
T
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
m
y
a
.
p
rk
sh
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.