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
7
,
No
.
3
,
Ma
r
ch
20
2
5
,
p
p
.
1
7
2
6
~
1
733
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
1
7
2
6
-
1
7
3
3
1726
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Ev
o
lv
ing
s
trategies
in
a
nti
-
phish
in
g
:
a
n in
-
d
epth
ana
ly
sis
of
detec
tion te
chniq
ues a
nd f
u
ture
re
sea
rch direc
tions
P
re
et
i,
P
rit
i Sha
rm
a
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
A
p
p
l
i
c
a
t
i
o
n
s
,
M
a
h
a
r
s
h
i
D
a
y
a
n
a
n
d
U
n
i
v
e
r
s
i
t
y
,
R
o
h
t
a
k
,
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
5
,
2
0
2
4
R
ev
is
ed
Sep
19
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
P
h
ish
i
n
g
a
tt
a
c
k
s
a
re
a
m
a
jo
r
d
ig
it
a
l
th
re
a
t,
imp
a
c
ti
n
g
i
n
d
i
v
i
d
u
a
ls
a
n
d
o
rg
a
n
iza
ti
o
n
s
g
lo
b
a
ll
y
.
Th
is
re
v
i
e
w
p
a
p
e
r
e
x
a
m
in
e
s
e
v
o
lv
in
g
a
n
t
i
-
p
h
is
h
in
g
stra
teg
ies
b
y
a
n
a
ly
z
in
g
fiv
e
k
e
y
t
e
c
h
n
iq
u
e
s:
URL
b
lac
k
li
sts,
v
is
u
a
l
sim
il
a
rit
y
d
e
tec
ti
o
n
,
h
e
u
r
isti
c
m
e
th
o
d
s,
m
a
c
h
in
e
lea
rn
i
n
g
m
o
d
e
ls,
a
n
d
d
e
e
p
lea
rn
i
n
g
tec
h
n
iq
u
e
s
.
Eac
h
tec
h
n
i
q
u
e
is
e
v
a
lu
a
ted
fo
r
it
s
m
e
c
h
a
n
ism
s,
u
n
iq
u
e
fe
a
tu
re
s,
a
n
d
c
h
a
ll
e
n
g
e
s.
A
sy
ste
m
a
ti
c
li
tera
tu
re
su
r
v
e
y
(
S
LR)
is
c
o
n
d
u
c
ted
to
c
o
m
p
a
re
th
e
se
m
e
th
o
d
s;
e
ffe
c
ti
v
e
n
e
ss
.
Th
e
p
a
p
e
r
h
i
g
h
li
g
h
ts
s
ig
n
ifi
c
a
n
t
re
se
a
rc
h
c
h
a
ll
e
n
g
e
s
a
n
d
su
g
g
e
sts
fu
tu
re
d
irec
ti
o
n
s,
e
m
p
h
a
siz
in
g
th
e
in
teg
ra
ti
o
n
o
f
a
rti
ficia
l
in
tell
ig
e
n
c
e
a
n
d
b
e
h
a
v
i
o
ra
l
a
n
a
l
y
ti
c
s
t
o
c
o
m
b
a
t
e
v
o
lv
in
g
p
h
is
h
in
g
tac
ti
c
s,
t
h
is
s
tu
d
y
a
ims
to
a
d
v
a
n
c
e
u
n
d
e
rsta
n
d
in
g
a
n
d
in
sp
ire m
o
re
e
ffe
c
ti
v
e
a
n
ti
-
p
h
ish
i
n
g
s
o
l
u
t
io
n
s.
K
ey
w
o
r
d
s
:
An
ti
-
p
h
is
h
in
g
tech
n
iq
u
es
C
y
b
er
s
ec
u
r
ity
Dee
p
lear
n
in
g
Ma
ch
in
e
lear
n
in
g
Ph
is
h
in
g
attac
k
s
U
R
L
b
lack
lis
ts
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
:
Pre
eti
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
Ap
p
licatio
n
s
,
Ma
h
ar
s
h
i D
ay
an
an
d
Un
iv
er
s
ity
R
o
h
tak
,
I
n
d
ia
E
m
ail:
m
is
k
h
o
k
h
ar
1
2
1
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Ph
is
h
in
g
is
a
p
r
ev
alen
t
c
y
b
er
c
r
im
e
wh
er
e
attac
k
er
s
u
s
e
ca
lls
,
em
ails
,
an
d
tex
ts
to
s
teal
p
er
s
o
n
al
an
d
f
in
an
cial
in
f
o
r
m
atio
n
th
r
o
u
g
h
d
ec
ep
tiv
e
m
e
an
s
.
E
m
p
l
o
y
in
g
s
o
cial
en
g
in
ee
r
in
g
tactics,
p
h
is
h
er
s
m
asq
u
er
ad
e
as
leg
itima
te
en
titi
es
to
co
m
m
it
o
n
l
in
e
id
e
n
tity
th
ef
t
[
1
]
,
[
2
]
.
Key
s
tu
d
ies
in
th
is
ar
ea
e
x
p
lo
r
e
v
ar
io
u
s
a
n
ti
-
p
h
is
h
in
g
tech
n
iq
u
es.
UR
L
b
l
ac
k
lis
ts
ar
e
cr
u
cial
f
o
r
b
lo
ck
i
n
g
k
n
o
wn
p
h
is
h
in
g
s
ites
,
p
r
e
v
en
tin
g
u
s
er
s
f
r
o
m
ac
ce
s
s
in
g
h
ar
m
f
u
l
UR
L
s
[
3
]
.
Vis
u
al
s
im
ilar
ity
d
etec
tio
n
f
o
c
u
s
es
o
n
a
n
aly
zin
g
web
s
ite
d
esig
n
s
to
id
en
tify
an
d
f
lag
s
ites
th
at
clo
s
ely
r
esem
b
le
leg
itima
te
o
n
es
[
4
]
.
Heu
r
is
tic
m
eth
o
d
s
u
s
e
p
r
ed
ef
in
e
d
r
u
le
s
to
d
etec
t
u
n
u
s
u
al
b
eh
av
io
r
s
an
d
p
atter
n
s
in
d
icativ
e
o
f
p
h
is
h
in
g
attem
p
ts
[
5
]
.
M
ac
h
in
e
lear
n
in
g
m
o
d
els ap
p
ly
s
o
p
h
is
ticated
d
ata
-
d
r
i
v
en
alg
o
r
ith
m
s
to
i
d
en
tify
an
d
p
r
e
d
ict
p
h
is
h
in
g
attem
p
ts
b
y
lear
n
in
g
f
r
o
m
e
x
is
tin
g
p
a
tter
n
s
an
d
f
ea
tu
r
es
[
6
]
.
Dee
p
l
ea
r
n
in
g
a
d
v
an
ce
s
p
h
is
h
in
g
UR
L
d
etec
tio
n
b
y
u
s
in
g
n
eu
r
al
n
etwo
r
k
s
to
an
aly
ze
an
d
lear
n
f
r
o
m
co
m
p
lex
p
atter
n
s
in
d
ata.
T
h
e
s
e
tech
n
iq
u
es
tr
ain
o
n
lar
g
e
d
atasets
to
id
en
tify
s
u
b
tle
f
ea
tu
r
es
an
d
an
o
m
alies
ass
o
ciate
d
with
p
h
is
h
in
g
attem
p
ts
,
en
ab
lin
g
e
f
f
ec
tiv
e
a
n
d
a
d
ap
tiv
e
d
etec
tio
n
o
f
n
ew
an
d
e
v
o
lv
in
g
th
r
ea
ts
[
7
]
.
T
h
ese
tech
n
iq
u
es
c
o
llectiv
ely
ad
v
a
n
ce
th
e
ab
ilit
y
to
d
et
ec
t
p
h
is
h
in
g
UR
L
attac
k
s
a
n
d
en
h
an
ce
o
v
er
all
cy
b
e
r
s
ec
u
r
ity
.
T
h
e
k
ey
f
o
cu
s
in
g
o
n
th
ese
an
ti
-
p
h
is
h
in
g
tech
n
iq
u
es a
r
e
o
u
tlin
e
d
as f
o
llo
ws:
-
B
lack
lis
t
s
b
ased
:
t
h
ese
tech
n
i
q
u
es
d
etec
t
p
h
is
h
in
g
b
y
c
o
m
p
ar
in
g
UR
L
s
ag
ain
s
t
k
n
o
wn
lis
ts
o
f
m
alicio
u
s
s
ites
.
T
h
ese
lis
ts
ar
e
co
m
p
iled
f
r
o
m
h
is
to
r
ical
d
ata
a
n
d
r
ep
o
r
ted
p
h
is
h
in
g
in
ci
d
en
ts
.
W
h
en
a
UR
L
m
atch
es
a
b
lack
lis
t
en
tr
y
,
it
is
f
lag
g
ed
as
p
o
ten
tially
h
ar
m
f
u
l,
h
elp
in
g
p
r
ev
en
t
p
h
is
h
in
g
attac
k
s
b
y
b
lo
ck
in
g
ac
ce
s
s
to
id
en
tifie
d
f
r
au
d
u
len
t
s
ites
.
T
ab
le1
p
r
o
v
id
es
an
aly
s
is
o
f
s
tu
d
ies
o
n
UR
L
b
lack
lis
t
tech
n
iq
u
es
f
o
r
p
h
is
h
in
g
d
etec
tio
n
,
in
clu
d
in
g
v
ar
io
u
s
m
eth
o
d
o
lo
g
ies f
o
r
m
ai
n
tain
in
g
an
d
u
p
d
atin
g
t
h
ese
lis
ts
.
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
E
vo
lvin
g
s
tr
a
teg
ies in
a
n
ti
-
p
h
is
h
in
g
:
a
n
in
-
d
e
p
th
a
n
a
lysi
s
o
f d
etec
tio
n
tech
n
iq
u
es
…
(
P
r
ee
ti
)
1727
T
ab
le
1
.
Key
s
tu
d
y
b
ase
o
n
U
R
L
b
lack
lis
ts
tech
n
iq
u
es
R
e
f
e
r
e
n
c
e
n
u
m
b
e
r
D
a
t
a
s
o
u
r
c
e
s
D
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
Li
mi
t
a
t
i
o
n
F
u
t
u
r
e
i
mp
r
o
v
e
me
n
t
s
[
8
]
2
0
0
l
e
g
i
t
i
m
a
t
e
(
1
0
t
o
p
l
o
g
i
n
p
a
g
e
s,
5
0
A
l
e
x
a
s
i
t
e
s,
1
4
0
y
a
h
o
o
)
,
2
0
0
p
h
i
s
h
i
n
g
p
a
g
e
s
(
P
h
i
s
h
Ta
n
k
)
.
Ev
a
l
u
a
t
e
s
t
h
e
a
c
c
u
r
a
c
y
o
f
i
d
e
n
t
i
f
y
i
n
g
p
h
i
sh
i
n
g
v
s.
l
e
g
i
t
i
m
a
t
e
p
a
g
e
s
u
si
n
g
w
h
i
t
e
l
i
st
a
n
d
S
V
M
c
l
a
ssi
f
i
e
r
.
Th
e
a
p
p
r
o
a
c
h
a
c
h
i
e
v
e
s
9
8
.
4
%
Tr
u
e
p
o
si
t
i
v
e
r
a
t
e
,
9
7
.
2
%
P
r
e
c
i
s
i
o
n
,
a
n
d
9
7
.
7
%
F
1
-
s
c
o
r
e
.
C
a
n
n
o
t
d
e
t
e
c
t
D
N
S
sp
o
o
f
i
n
g
,
r
e
l
i
a
n
c
e
o
n
se
a
r
c
h
e
n
g
i
n
e
may
a
f
f
e
c
t
p
e
r
f
o
r
m
a
n
c
e
.
I
n
c
o
r
p
o
r
a
t
e
I
P
a
d
d
r
e
sse
s,
r
e
f
i
n
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
e
a
t
u
r
e
s,
a
n
d
i
mp
r
o
v
e
s
e
a
r
c
h
e
n
g
i
n
e
i
n
t
e
g
r
a
t
i
o
n
.
[
9
]
P
h
i
s
h
Ta
n
k
,
S
p
a
mS
c
a
t
t
e
r
,
D
M
O
Z,
a
n
d
Y
a
h
o
o
R
a
n
d
o
m U
R
L
G
e
n
e
r
a
t
o
r
u
se
d
f
o
r
p
h
i
s
h
i
n
g
a
n
d
b
e
n
i
g
n
U
R
L
a
n
a
l
y
si
s
.
Ef
f
e
c
t
i
v
e
h
e
u
r
i
s
t
i
c
s a
n
d
f
a
s
t
a
p
p
r
o
x
i
m
a
t
e
m
a
t
c
h
i
n
g
s
h
o
w
l
o
w
f
a
l
se
p
o
s
i
t
i
v
e
s/
n
e
g
a
t
i
v
e
s,
o
u
t
p
e
r
f
o
r
m
i
n
g
G
o
o
g
l
e
’
s Saf
e
B
r
o
w
si
n
g
A
P
I
i
n
s
p
e
e
d
.
Th
e
h
i
g
h
e
st
a
c
c
u
r
a
c
y
f
a
c
t
o
r
i
s
“
H
i
g
h
S
i
mi
l
a
r
i
t
y
(
9
0
-
1
0
0
%)
:
1
0
,
6
0
6
U
R
Ls
f
r
o
m
H
e
u
r
i
st
i
c
H3
-
D
i
r
e
c
t
o
r
y
.
Tr
a
d
e
-
o
f
f
b
e
t
w
e
e
n
f
a
l
se
p
o
si
t
i
v
e
s
/
n
e
g
a
t
i
v
e
s
;
h
e
u
r
i
s
t
i
c
s
n
o
t
e
x
h
a
u
st
i
v
e
;
D
N
S
/
c
o
n
t
e
n
t
mat
c
h
i
n
g
d
e
p
e
n
d
e
n
c
y
;
l
e
ss
e
f
f
e
c
t
i
v
e
o
n
v
e
r
y
sh
o
r
t
-
l
i
v
e
d
d
o
ma
i
n
s.
Ex
p
a
n
d
h
e
u
r
i
st
i
c
s,
e
n
h
a
n
c
e
U
R
L
g
e
n
e
r
a
t
i
o
n
,
r
e
f
i
n
e
mat
c
h
i
n
g
a
c
c
u
r
a
c
y
,
i
n
t
e
g
r
a
t
e
m
o
r
e
d
a
t
a
so
u
r
c
e
s,
a
n
d
i
mp
l
e
m
e
n
t
a
d
a
p
t
i
v
e
l
e
a
r
n
i
n
g
.
[
1
0
]
U
t
i
l
i
z
e
s UR
L
-
b
a
se
d
d
e
t
e
c
t
i
o
n
,
v
i
su
a
l
U
R
L
e
x
t
r
a
c
t
i
o
n
,
a
n
d
v
i
s
u
a
l
si
mi
l
a
r
i
t
y
c
o
m
p
a
r
i
so
n
s
b
e
t
w
e
e
n
s
u
s
p
i
c
i
o
u
s
a
n
d
l
e
g
i
t
i
m
a
t
e
p
a
g
e
s
.
Th
e
a
p
p
r
o
a
c
h
i
s
e
x
p
e
c
t
e
d
t
o
a
c
h
i
e
v
e
i
m
p
r
o
v
e
d
d
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
c
o
mp
a
r
e
d
t
o
e
x
i
s
t
i
n
g
met
h
o
d
s,
w
i
t
h
f
e
w
e
r
f
a
l
se
p
o
s
i
t
i
v
e
s
a
n
d
b
e
t
t
e
r
c
o
v
e
r
a
g
e
.
M
a
y
n
o
t
d
e
t
e
c
t
a
l
l
so
p
h
i
st
i
c
a
t
e
d
p
h
i
s
h
i
n
g
a
t
t
e
mp
t
s;
v
i
s
u
a
l
s
i
mi
l
a
r
i
t
y
mi
g
h
t
b
e
l
e
ss
e
f
f
e
c
t
i
v
e
a
g
a
i
n
st
h
i
g
h
l
y
a
d
v
a
n
c
e
d
p
h
i
s
h
i
n
g
t
e
c
h
n
i
q
u
e
s.
En
h
a
n
c
e
a
c
c
u
r
a
c
y
b
y
r
e
f
i
n
i
n
g
U
R
L
-
b
a
s
e
d
a
n
d
v
i
su
a
l
si
mi
l
a
r
i
t
y
t
e
c
h
n
i
q
u
e
s,
i
n
c
o
r
p
o
r
a
t
e
a
d
d
i
t
i
o
n
a
l
d
e
t
e
c
t
i
o
n
met
h
o
d
s,
a
n
d
r
e
d
u
c
e
f
a
l
se
p
o
si
t
i
v
e
f
u
r
t
h
e
r
.
[
1
1
]
Le
g
i
t
i
ma
t
e
so
u
r
c
e
s
i
n
c
l
u
d
e
A
l
e
x
a
,
D
M
O
Z;
p
h
i
s
h
i
n
g
so
u
r
c
e
s
i
n
c
l
u
d
e
P
h
i
s
h
T
a
n
k
,
O
p
e
n
P
h
i
sh
.
C
u
r
r
e
n
t
me
t
h
o
d
s
o
f
t
e
n
s
u
f
f
e
r
f
r
o
m i
m
b
a
l
a
n
c
e
d
d
a
t
a
,
l
e
a
d
i
n
g
t
o
h
i
g
h
f
a
l
se
p
o
s
i
t
i
v
e
s.
I
mb
a
l
a
n
c
e
d
d
a
t
a
s
e
t
s
c
a
u
se
b
i
a
s,
a
n
d
U
R
L
f
e
a
t
u
r
e
s
c
a
n
b
e
man
i
p
u
l
a
t
e
d
,
a
f
f
e
c
t
i
n
g
d
e
t
e
c
t
i
o
n
r
e
l
i
a
b
i
l
i
t
y
.
F
o
c
u
s
o
n
d
o
m
a
i
n
n
a
m
e
-
b
a
se
d
f
e
a
t
u
r
e
s
a
n
d
b
a
l
a
n
c
e
d
d
a
t
a
s
e
t
s
t
o
e
n
h
a
n
c
e
d
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
a
n
d
r
e
l
i
a
b
i
l
i
t
y
.
[
1
2
]
Tw
o
d
a
t
a
s
e
t
s fr
o
m
t
h
e
U
C
I
r
e
p
o
si
t
o
r
y
:
P
h
i
s
h
i
n
g
D
a
t
a
s
e
t
1
w
i
t
h
1
3
5
3
U
R
Ls(
5
4
8
l
e
g
i
t
i
m
a
t
e
,
7
0
2
p
h
i
s
h
i
n
g
,
1
0
3
su
sp
i
c
i
o
u
s)
a
n
d
p
h
i
s
h
i
n
g
D
a
t
a
se
t
2
w
i
t
h
4
8
9
8
p
h
i
sh
i
n
g
U
R
Ls
a
n
d
6
1
5
7
l
e
g
i
t
i
m
a
t
e
U
R
Ls
.
Th
e
h
y
b
r
i
d
a
l
g
o
r
i
t
h
m a
c
h
i
e
v
e
d
a
c
c
u
r
a
c
i
e
s
o
f
0
.
9
4
5
3
a
n
d
0
.
9
9
0
8
,
s
u
r
p
a
ssi
n
g
J
R
i
p
a
n
d
P
A
R
T.
Th
e
st
u
d
y
p
r
i
mari
l
y
e
v
a
l
u
a
t
e
s
p
e
r
f
o
r
m
a
n
c
e
o
n
sp
e
c
i
f
i
c
d
a
t
a
se
t
s;
g
e
n
e
r
a
l
i
z
a
b
i
l
i
t
y
t
o
o
t
h
e
r
p
h
i
s
h
i
n
g
sce
n
a
r
i
o
s
a
n
d
d
a
t
a
se
t
v
a
r
i
a
t
i
o
n
s
may
b
e
l
i
m
i
t
e
d
.
R
e
se
a
r
c
h
w
i
l
l
f
o
c
u
s
o
n
a
d
a
p
t
i
v
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
t
o
e
n
h
a
n
c
e
d
e
t
e
c
t
i
o
n
o
f
Ze
r
o
-
d
a
y
p
h
i
s
h
i
n
g
t
h
r
e
a
t
s.
[
1
3
]
P
h
i
s
h
Ta
n
k
.
Th
e
p
r
o
p
o
s
e
d
r
u
l
e
-
b
a
se
d
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
a
c
h
i
e
v
e
d
c
o
m
p
e
t
i
t
i
v
e
a
c
c
u
r
a
c
y
w
i
t
h
C
4
.
5
a
n
d
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
,
y
i
e
l
d
i
n
g
a
n
a
c
c
u
r
a
c
y
o
f
9
9
%
,
w
i
t
h
a
f
a
l
s
e
p
o
s
i
t
i
v
e
r
a
t
e
o
f
0
.
5
%
a
n
d
a
f
a
l
se
n
e
g
a
t
i
v
e
r
a
t
e
o
f
2
.
5
%.
Th
e
r
u
l
e
s
e
t
u
s
e
d
i
n
t
h
i
s a
p
p
r
o
a
c
h
i
s
p
r
e
ma
t
u
r
e
a
n
d
n
e
e
d
s
e
x
p
a
n
si
o
n
.
I
t
ma
y
mi
ss
p
h
i
s
h
i
n
g
w
e
b
p
a
g
e
s
d
e
si
g
n
e
d
t
o
mi
n
i
m
i
z
e
r
u
l
e
mat
c
h
e
s
o
r
t
h
o
se
h
o
s
t
e
d
o
n
h
a
c
k
e
d
l
e
g
i
t
i
m
a
t
e
p
a
g
e
s.
F
u
t
u
r
e
w
o
r
k
w
i
l
l
f
o
c
u
s
o
n
r
e
f
i
n
i
n
g
t
h
e
r
u
l
e
se
t
t
o
r
e
d
u
c
e
f
a
l
se
p
o
si
t
i
v
e
s
a
n
d
n
e
g
a
t
i
v
e
s
,
d
e
v
e
l
o
p
i
n
g
a
l
i
g
h
t
w
e
i
g
h
t
,
r
e
a
l
-
t
i
m
e
p
h
i
sh
i
n
g
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
a
n
d
e
x
p
l
o
r
i
n
g
o
p
t
i
m
a
l
i
n
t
e
r
v
a
l
s f
o
r
r
e
t
r
a
i
n
i
n
g
t
h
e
s
y
st
e
m
w
i
t
h
n
e
w
d
a
t
a
.
[
3
]
U
R
Ls
e
x
t
r
a
c
t
e
d
f
r
o
m sp
a
m f
i
l
t
e
r
s,
u
ser re
p
o
r
t
s,
a
n
d
p
h
i
s
h
i
n
g
w
e
b
si
t
e
s
i
d
e
n
t
i
f
i
e
d
b
y
h
e
u
r
i
s
t
i
c
s
.
H
i
g
h
a
c
c
u
r
a
c
y
,
w
i
t
h
h
e
u
r
i
st
i
c
s
d
e
t
e
c
t
i
n
g
m
o
r
e
p
h
i
s
h
i
n
g
a
t
t
e
m
p
t
s
i
n
i
t
i
a
l
l
y
;
b
l
a
c
k
l
i
s
t
s
u
p
d
a
t
e
sl
o
w
e
r
.
D
a
t
a
so
u
r
c
e
d
f
r
o
m
a
si
n
g
l
e
a
n
t
i
-
s
p
a
m
v
e
n
d
o
r
;
o
n
l
y
e
ma
i
l
U
R
Ls
c
o
n
si
d
e
r
e
d
;
n
o
o
t
h
e
r
v
e
c
t
o
r
s.
S
p
e
e
d
u
p
b
l
a
c
k
l
i
st
u
p
d
a
t
e
s
,
e
n
h
a
n
c
e
h
e
u
r
i
s
t
i
c
me
t
h
o
d
s,
a
n
d
i
mp
r
o
v
e
u
ser
p
h
i
s
h
i
n
g
a
w
a
r
e
n
e
ss.
T
ab
le
1
h
ig
h
lig
h
ts
v
ar
io
u
s
s
tu
d
ies
o
n
UR
L
b
lack
lis
t
tech
n
iq
u
es.
On
e
s
tu
d
y
ac
h
iev
ed
a
9
8
.
4
%
tr
u
e
p
o
s
itiv
e
r
ate
an
d
9
7
.
7
%
F1
-
s
co
r
e
u
s
in
g
w
h
itelis
t
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
c
lass
if
ier
s
,
th
o
u
g
h
it
co
u
ld
n
’
t
d
etec
t
DNS
s
p
o
o
f
in
g
an
d
was
af
f
ec
ted
b
y
s
ea
r
c
h
en
g
in
e
r
elian
ce
.
An
o
t
h
er
u
tili
ze
d
h
eu
r
is
tics
an
d
f
ast
m
atch
in
g
,
o
u
tp
er
f
o
r
m
in
g
Go
o
g
le’
s
Saf
e
B
r
o
wsi
n
g
API
b
u
t stru
g
g
led
with
v
er
y
s
h
o
r
t
-
liv
ed
d
o
m
ain
s
.
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
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
726
-
1
7
3
3
1728
A
h
y
b
r
id
alg
o
r
ith
m
s
h
o
wed
9
4
.
5
3
%
an
d
9
9
.
0
8
%
ac
cu
r
ac
y
b
u
t
n
ee
d
ed
r
ef
in
e
m
en
t
to
h
an
d
l
e
s
o
p
h
is
ticated
p
h
is
h
in
g
.
Fu
tu
r
e
im
p
r
o
v
em
e
n
ts
ac
r
o
s
s
s
tu
d
ies
in
clu
d
ed
in
co
r
p
o
r
atin
g
I
P
ad
d
r
ess
es,
r
ef
in
in
g
f
ea
tu
r
es,
an
d
e
n
h
an
ci
n
g
h
e
u
r
is
tic
m
eth
o
d
s
.
-
Heu
r
is
tic
b
ased
tech
n
iq
u
es:
t
h
is
ap
p
r
o
ac
h
i
d
en
tifie
s
p
h
is
h
in
g
attem
p
ts
b
y
a
n
aly
zin
g
U
R
L
s
an
d
web
co
n
ten
t
f
o
r
s
u
s
p
icio
u
s
p
atter
n
s
an
d
ch
a
r
ac
ter
is
tics
.
T
h
ese
m
eth
o
d
s
u
s
e
p
r
ed
ef
in
e
d
r
u
les
a
n
d
alg
o
r
ith
m
s
to
d
etec
t
an
o
m
alies
th
at
m
i
g
h
t
i
n
d
icate
p
h
is
h
in
g
,
s
u
c
h
as
u
n
u
s
u
al
UR
L
s
tr
u
ctu
r
es
o
r
c
o
n
ten
t
i
n
co
n
s
is
ten
cies.
B
y
ass
es
s
in
g
v
ar
io
u
s
h
e
u
r
is
tics
,
th
ese
tech
n
iq
u
es
aim
t
o
p
o
t
p
h
is
h
in
g
s
ites
th
at
m
ig
h
t
ev
ad
e
s
im
p
ler
d
etec
tio
n
m
eth
o
d
s
.
T
h
e
d
etai
led
an
aly
s
is
o
f
s
tu
d
ies
o
n
h
e
u
r
is
tic
b
ased
tech
n
iq
u
es,
as
o
u
tlin
ed
b
elo
w,
ex
p
lo
r
es th
eir
e
f
f
ec
tiv
en
ess
in
d
et
ec
tin
g
p
h
is
h
in
g
attac
k
s
[1
4
]
.
I
n
th
is
r
esear
ch
,
Ph
is
h
Sh
ield
was
d
ev
elo
p
ed
to
d
etec
t
p
h
is
h
in
g
web
s
ites
with
9
6
.
5
7
%
ac
cu
r
ac
y
b
y
an
aly
zin
g
UR
L
an
d
co
n
te
n
t
th
r
o
u
g
h
h
eu
r
is
tics
s
u
ch
as
f
o
o
ter
lin
k
s
an
d
co
p
y
r
ig
h
t
in
f
o
r
m
atio
n
.
I
t
o
u
tp
er
f
o
r
m
e
d
tr
ad
itio
n
al
m
eth
o
d
s
an
d
b
lac
k
lis
ts
,
p
ar
ticu
lar
ly
f
o
r
ze
r
o
-
h
o
u
r
attac
k
s
.
Ho
wev
er
,
its
r
elian
ce
o
n
h
e
u
r
is
tics
d
id
n
o
t
co
v
er
all
s
o
p
h
is
ticated
p
h
is
h
in
g
t
ec
h
n
iq
u
es
an
d
f
ac
e
d
ch
allen
g
es
with
ev
o
lv
in
g
th
r
ea
ts
[1
5
]
.
T
h
is
r
esear
ch
p
r
o
p
o
s
ed
a
n
o
v
el
p
h
is
h
in
g
d
etec
tio
n
a
p
p
r
o
ac
h
u
s
in
g
UR
L
f
ea
tu
r
es
a
n
d
m
etr
ics,
co
m
b
in
ed
with
p
ag
e
r
an
k
in
g
.
E
v
alu
ated
o
n
a
d
ataset
o
f
9
,
6
6
1
p
h
is
h
in
g
an
d
1
,
0
0
0
leg
iti
m
ate
web
s
ites
,
th
e
tech
n
iq
u
e
ac
h
iev
ed
o
v
e
r
9
7
%
d
etec
tio
n
ac
cu
r
ac
y
.
Ho
wev
er
,
d
esp
ite
its
ef
f
ec
tiv
en
ess
,
th
e
ap
p
r
o
ac
h
m
a
y
f
ac
e
lim
itatio
n
s
in
h
an
d
l
in
g
s
o
p
h
is
ticated
p
h
is
h
in
g
m
eth
o
d
s
th
at
m
im
ic
leg
itima
te
UR
L
s
clo
s
el
y
an
d
m
ay
n
o
t
f
u
lly
ad
d
r
ess
ev
o
lv
in
g
p
h
is
h
in
g
ta
ctics
[1
6
]
.
A
m
eth
o
d
f
o
r
d
e
tectin
g
p
h
is
h
in
g
an
d
m
alwa
r
e
was
in
tr
o
d
u
ce
d
,
an
aly
zin
g
s
p
ec
if
ic
s
tr
in
g
s
in
UR
L
s
an
d
em
ails
m
e
s
s
ag
es,
u
s
ed
with
p
r
o
x
ies
an
d
an
ti
-
s
p
a
m
f
ilter
s
.
I
t
ac
h
iev
ed
d
etec
tio
n
ac
cu
r
ac
y
b
etwe
en
7
3
.
3
% a
n
d
9
7
.
6
6
% with
an
av
e
r
ag
e
m
o
r
e
s
o
p
h
is
ticated
p
h
is
h
i
n
g
tech
n
i
q
u
es
[1
7
]
.
T
h
e
p
r
o
p
o
s
ed
h
e
u
r
is
tic
-
b
ased
p
h
is
h
in
g
d
etec
tio
n
tec
h
n
iq
u
e,
wh
ich
u
s
ed
UR
L
-
b
ased
f
e
atu
r
es
an
d
m
ac
h
in
e
lear
n
i
n
g
class
if
ier
s
,
ac
h
iev
ed
9
6
%
ac
cu
r
ac
y
with
a
lo
w
f
alse
-
p
o
s
itiv
e
r
ate,
e
f
f
e
ctiv
ely
id
en
tify
in
g
n
ew
an
d
tem
p
o
r
ar
y
p
h
is
h
in
g
s
ites
.
Ho
wev
er
,
th
e
ap
p
r
o
ac
h
f
ac
ed
ch
allen
g
es
with
em
er
g
i
n
g
p
h
is
h
in
g
tactics
d
u
e
to
its
r
elian
ce
o
n
s
p
ec
if
ic
UR
L
f
ea
tu
r
es.
Fu
tu
r
e
wo
r
k
aim
ed
to
ex
p
lo
r
e
n
ew
f
ea
tu
r
es,
en
h
an
ce
ac
cu
r
ac
y
,
an
d
d
e
v
elo
p
a
b
r
o
wser
p
l
u
g
in
f
o
r
r
ea
l
-
tim
e
p
h
is
h
in
g
ale
r
ts
[1
8
]
.
-
Vis
u
al
s
im
i
lar
ity
b
ased
tech
n
iq
u
es
:
t
h
is
s
ec
tio
n
ex
am
in
es th
e
an
aly
s
is
o
f
p
h
is
h
in
g
attac
k
d
etec
tio
n
th
r
o
u
g
h
v
is
ib
ilit
y
-
b
ased
tech
n
iq
u
es.
T
h
e
s
tu
d
y
f
o
cu
s
ed
o
n
ev
alu
atin
g
v
is
u
al
f
ea
tu
r
es
o
f
we
b
p
a
g
es,
s
u
ch
as
d
esig
n
elem
en
ts
an
d
lay
o
u
t,
to
id
en
tify
p
h
is
h
in
g
th
r
ea
ts
.
B
y
lev
er
ag
in
g
th
ese
v
is
u
al
cu
es,
t
h
e
ap
p
r
o
ac
h
aim
ed
t
o
d
is
tin
g
u
is
h
b
etwe
en
leg
itima
te
an
d
p
h
is
h
in
g
s
ites
.
Deta
ils
o
f
th
e
s
tu
d
y
ar
e
d
escr
ib
e
d
b
el
o
w,
h
ig
h
lig
h
tin
g
k
ey
f
in
d
in
g
s
an
d
lim
itatio
n
s
o
f
p
r
ev
io
u
s
wo
r
k
u
s
in
g
v
is
u
al
s
im
ilar
ity
tech
n
iq
u
es
I
n
th
is
p
ap
er
,
th
e
r
esear
c
h
e
s
in
tr
o
d
u
ce
d
a
n
o
v
el
p
h
is
h
i
n
g
d
etec
tio
n
m
eth
o
d
co
m
p
a
r
in
g
v
is
u
al
s
im
ilar
ity
b
etwe
en
s
u
s
p
icio
u
s
an
d
leg
itima
te
p
ag
e
s
,
in
s
p
ir
e
d
b
y
ex
is
tin
g
a
n
ti
-
p
h
is
h
in
g
t
o
o
ls
.
T
h
ey
an
aly
ze
d
tex
t,
im
ag
es
an
d
o
v
er
all
v
is
u
al
ap
p
ea
r
an
ce
.
R
esu
lts
with
4
1
p
h
is
h
in
g
p
a
g
es
s
h
o
wed
n
o
f
alse
p
o
s
itiv
es
an
d
o
n
ly
two
m
is
s
ed
d
etec
tio
n
s
.
Key
f
in
d
in
g
s
in
clu
d
e
d
h
ig
h
ac
cu
r
ac
y
an
d
ef
f
ec
tiv
en
es
s
,
wh
ile
lim
itatio
n
s
in
v
o
lv
ed
o
cc
asio
n
al
f
ailu
r
e
t
o
d
etec
t
h
ig
h
l
y
d
is
s
im
ilar
p
h
is
h
in
g
attem
p
ts
.
Fu
tu
r
e
w
o
r
k
s
h
o
u
ld
e
n
h
an
ce
d
etec
tio
n
ca
s
es
[
4
]
.
T
h
e
s
tu
d
y
ev
alu
ated
v
is
u
al
s
im
ilar
ity
-
b
ased
p
h
is
h
in
g
d
etec
t
in
g
m
o
d
els
u
s
in
g
a
d
ataset
o
f
4
5
0
k
r
ea
l
-
wo
r
ld
p
h
is
h
in
g
web
s
ites
,
r
ev
e
alin
g
p
er
f
o
r
m
a
n
ce
g
a
p
s
b
etwe
en
r
ea
l
-
wo
r
ld
an
d
c
o
n
tr
o
lled
en
v
ir
o
n
m
en
ts
.
Key
lim
itatio
n
s
in
clu
d
ed
a
lack
o
f
u
s
er
s
tu
d
ies,
f
o
c
u
s
w
o
r
k
s
h
o
u
ld
en
h
an
ce
r
o
b
u
s
tn
ess
b
y
in
teg
r
atin
g
tex
t
r
ec
o
g
n
itio
n
,
ad
v
e
r
s
ar
ial
d
ata
a
u
g
m
en
tatio
n
,
an
d
m
u
lti
-
cu
e
e
n
s
em
b
le
ap
p
r
o
ac
h
es
[
19
]
.
Vis
u
alPh
is
h
Net,
a
r
o
b
u
s
t
p
h
is
h
in
g
d
etec
tio
n
f
r
am
ewo
r
k
,
s
ig
n
if
ican
tly
o
u
tp
er
f
o
r
m
e
d
p
r
io
r
v
is
u
al
s
im
ilar
ity
ap
p
r
o
ac
h
es,
ac
h
i
ev
i
n
g
a
5
6
%
im
p
r
o
v
em
e
n
t
in
m
atch
in
g
ac
cu
r
ac
y
a
n
d
a
3
0
%
i
n
cr
ea
s
e
in
r
ec
eiv
e
r
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
(
R
OC
)
ar
ea
u
n
d
e
r
th
e
cu
r
v
e
(
AUC)
.
Ho
wev
er
,
th
e
f
o
c
u
s
o
n
v
is
u
al
s
im
ilar
ity
an
d
th
e
lim
ited
ev
alu
atio
n
s
co
p
e
wer
e
k
ey
lim
itatio
n
s
.
Fu
tu
r
e
wo
r
k
was
r
ec
o
m
m
en
d
ed
to
e
x
p
lo
r
e
ad
d
itio
n
al
attac
k
v
ec
to
r
s
,
co
n
d
u
ct
u
s
er
s
tu
d
ies,
an
d
s
tr
en
g
th
e
n
d
ef
e
n
s
e
ag
ain
s
t e
v
o
lv
in
g
ev
asio
n
tactics
[2
0
]
.
T
h
e
r
esear
ch
p
r
o
p
o
s
ed
a
v
is
u
al
s
im
ilar
ity
-
b
ased
p
h
is
h
in
g
d
etec
tio
n
m
eth
o
d
u
s
in
g
b
o
th
lo
ca
l
an
d
g
lo
b
al
web
p
ag
e
f
ea
tu
r
es.
I
t
a
ch
iev
ed
o
v
er
9
0
%
tr
u
e
p
o
s
itiv
e
an
d
9
7
%
tr
u
e
n
eg
ativ
e
r
ates
o
n
a
lar
g
e
d
ataset.
Ho
wev
er
,
its
r
elian
ce
o
n
im
a
g
e
-
lev
el
an
aly
s
is
lim
its
its
ab
ili
t
y
to
d
etec
t
ad
v
an
ce
d
p
h
is
h
in
g
tech
n
iq
u
es.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
en
h
a
n
cin
g
d
etec
tio
n
ca
p
a
b
ilit
ies
an
d
ex
p
an
d
in
g
its
ap
p
licatio
n
t
o
d
iv
er
s
e
p
h
is
h
in
g
s
ce
n
ar
io
s
[2
1
]
.
B
aitAlar
m
,
an
an
ti
-
p
h
is
h
in
g
ap
p
r
o
ac
h
th
at
u
tili
ze
d
C
SS
an
d
v
is
u
al
f
ea
tu
r
es
f
o
r
s
im
ilar
ity
co
m
p
ar
is
o
n
s
b
etwe
en
s
u
s
p
ici
o
u
s
an
d
tar
g
et
p
a
g
es,
d
em
o
n
s
tr
ated
ef
f
ec
tiv
e
n
ess
th
r
o
u
g
h
ev
alu
atio
n
s
with
n
u
m
er
o
u
s
p
h
is
h
in
g
p
ag
es.
De
s
p
ite
its
s
u
cc
es
s
,
it
f
ac
ed
lim
itatio
n
s
d
u
e
to
v
u
ln
er
ab
ilit
y
to
ev
asio
n
attac
k
s
.
Fu
tu
r
e
wo
r
k
s
aim
ed
to
en
h
an
c
e
its
r
esil
ien
ce
ag
ain
s
t su
ch
attac
k
s
[2
2
]
.
-
Ma
ch
in
e
lear
n
in
g
b
ased
tech
n
iq
u
es
:
i
n
th
is
s
ec
tio
n
,
we
d
escr
ib
e
a
s
tu
d
y
b
ased
o
n
m
a
ch
in
e
lear
n
in
g
tech
n
iq
u
es.
T
h
e
s
tu
d
y
ex
p
lo
r
ed
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
to
im
p
r
o
v
es
p
h
is
h
in
g
d
etec
tio
n
.
I
t
f
o
cu
s
ed
o
n
lev
er
a
g
in
g
ad
v
an
c
ed
alg
o
r
ith
m
s
to
an
aly
ze
p
atter
n
s
an
d
an
o
m
alies
in
d
ata
to
id
en
tify
p
h
is
h
in
g
attem
p
ts
m
o
r
e
ac
cu
r
ately
.
Deta
i
ls
o
f
th
e
tech
n
iq
u
es,
m
o
d
els
u
s
ed
,
an
d
r
esu
lts
ar
e
p
r
o
v
id
ed
b
elo
w.
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
E
vo
lvin
g
s
tr
a
teg
ies in
a
n
ti
-
p
h
is
h
in
g
:
a
n
in
-
d
e
p
th
a
n
a
lysi
s
o
f d
etec
tio
n
tech
n
iq
u
es
…
(
P
r
ee
ti
)
1729
T
h
e
s
tu
d
y
ev
al
u
ated
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
p
h
is
h
in
g
UR
L
d
etec
tio
n
,
I
n
clu
d
in
g
d
ec
is
io
n
tr
ee
,
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
,
r
a
n
d
o
m
f
o
r
est
,
XGBo
o
s
t,
Au
to
en
co
d
e
r
n
eu
r
al
n
etwo
r
k
,
an
d
SVM
.
Usi
n
g
a
d
ataset
f
r
o
m
Ph
is
h
tan
k
a
n
d
th
e
Un
iv
er
s
ity
o
f
New
B
r
u
n
s
wick
,
it
f
o
u
n
d
R
an
d
o
m
Fo
r
s
t
an
d
XGBo
o
s
t
o
u
tp
er
f
o
r
m
ed
o
th
er
s
,
ac
h
iev
in
g
an
o
v
er
all
ac
cu
r
ac
y
o
f
9
8
%
in
p
h
is
h
in
g
d
etec
tio
n
[2
3
]
.
A
g
en
etic
alg
o
r
ith
m
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
im
p
r
o
v
ed
UR
L
p
h
is
h
in
g
d
etec
tio
n
,
with
r
an
d
o
m
f
o
r
est
ac
h
iev
in
g
9
9
.
9
3
%
ac
cu
r
ac
y
.
L
im
itatio
n
s
in
cl
u
d
e
d
s
p
ec
if
ic
f
ea
tu
r
e
r
elian
ce
an
d
s
ca
lab
ilit
y
is
s
u
es.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
o
p
tim
ize
f
o
r
d
iv
er
s
e
d
atasets
an
d
s
ce
n
ar
io
s
[2
4
]
.
A
m
ac
h
in
e
lear
n
in
g
-
b
ased
s
y
s
t
em
,
PHI
SH
-
SAFE,
was
d
ev
elo
p
ed
to
d
etec
t
p
h
is
h
in
g
web
s
ites
u
s
in
g
1
4
UR
L
f
ea
tu
r
es.
T
r
ain
ed
o
n
a
d
ataset
o
f
o
v
er
3
3
,
0
0
0
U
R
L
s
,
th
e
s
y
s
tem
u
ti
lized
SV
M
an
d
Naïv
e
B
ay
es
class
if
ier
s
.
T
h
e
SVM
c
lass
if
ier
d
em
o
n
s
tr
ated
o
v
er
9
0
% a
cc
u
r
ac
y
in
id
en
tify
i
n
g
p
h
is
h
in
g
s
ites
,
s
h
o
wca
s
in
g
th
e
m
eth
o
d
’
s
ef
f
ec
tiv
en
ess
in
cy
b
er
s
ec
u
r
ity
[2
5
]
.
T
h
e
r
esear
ch
d
e
v
elo
p
e
d
a
h
y
b
r
id
en
s
em
b
le
f
ea
tu
r
e
s
elec
tio
n
(
HE
FS
)
m
eth
o
d
u
s
in
g
UR
L
f
ea
tu
r
es
f
o
r
p
h
is
h
in
g
d
etec
tio
n
,
ac
h
iev
in
g
9
7
.
9
%
ac
c
u
r
ac
y
with
a
n
o
v
el
C
DF
-
g
alg
o
r
ith
m
.
Ho
we
v
er
,
th
e
s
tu
d
y
f
ac
e
d
ch
allen
g
es
in
class
if
ier
co
m
p
l
ex
ity
an
d
d
ata
p
ar
titi
o
n
i
n
g
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
r
e
f
in
in
g
th
ese
is
s
u
es
to
en
h
an
ce
s
tab
ilit
y
an
d
p
er
f
o
r
m
an
ce
f
u
r
t
h
er
.
T
h
e
h
ig
h
est ac
cu
r
ac
y
was o
b
tain
ed
b
y
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
[2
6
]
.
T
h
e
s
tu
d
y
u
tili
ze
d
m
ac
h
in
e
lear
n
in
g
a
lg
o
r
ith
m
s
,
s
p
ec
if
i
ca
lly
SVM,
to
d
etec
t
p
h
is
h
i
n
g
UR
L
s
,
ac
h
iev
in
g
im
p
r
o
v
ed
ac
cu
r
ac
y
b
y
lev
er
ag
i
n
g
UR
L
f
ea
tu
r
es
f
r
o
m
a
Kag
g
le
d
ataset.
Ho
we
v
er
,
th
e
s
tu
d
y
was
lim
ited
b
y
its
r
elian
ce
o
n
a
s
p
ec
if
ic
d
ataset
an
d
th
e
p
o
te
n
tial
n
ee
d
f
o
r
m
o
r
e
co
m
p
r
e
h
en
s
iv
e
f
ea
tu
r
e
s
ets.
Fu
tu
r
e
wo
r
k
s
h
o
u
l
d
ex
p
lo
r
e
ad
d
itio
n
al
d
atasets
an
d
ad
v
a
n
ce
d
alg
o
r
ith
m
s
to
en
h
an
ce
p
h
is
h
in
g
d
etec
tio
n
ac
cu
r
ac
y
an
d
ap
p
licab
ilit
y
ac
r
o
s
s
d
iv
er
s
e
s
ce
n
ar
io
s
[2
7
]
.
T
h
e
p
ap
er
in
tr
o
d
u
ce
d
a
m
ac
h
in
e
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
f
o
r
r
ea
l
-
tim
e
p
h
is
h
in
g
web
s
ite
d
etec
t
io
n
,
u
tili
zin
g
h
y
b
r
i
d
f
ea
tu
r
es
f
r
o
m
UR
L
s
an
d
h
y
p
er
lin
k
s
with
o
u
t
r
ely
in
g
o
n
th
ir
d
-
p
ar
ty
s
y
s
tem
s
.
B
y
av
o
id
in
g
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
m
eth
o
d
s
lik
e
b
lack
lis
ts
an
d
h
eu
r
is
tics
,
th
is
ap
p
r
o
ac
h
en
h
a
n
ce
d
d
etec
tio
n
ac
cu
r
ac
y
.
E
x
p
er
im
en
ts
co
n
d
u
cted
with
a
n
ewly
d
ev
elo
p
ed
d
atasets
d
em
o
n
s
tr
ated
th
e
m
et
h
o
d
’
s
ef
f
ec
tiv
en
ess
,
ac
h
iev
in
g
a
h
ig
h
d
etec
tio
n
ac
cu
r
ac
y
o
f
9
9
.
1
7
% u
s
in
g
XGBo
o
s
t,
s
u
r
p
as
s
in
g
co
n
v
e
n
tio
n
al
tech
n
i
q
u
es
[
28
]
.
T
h
e
ev
alu
atio
n
f
o
c
u
s
ed
o
n
g
r
ad
ien
t
b
o
o
s
tin
g
class
if
ier
,
r
an
d
o
m
f
o
r
est,
an
d
d
ec
is
io
n
tr
ee
m
o
d
els
f
o
r
Ph
is
h
in
g
d
etec
tio
n
,
u
s
in
g
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
s
s
u
ch
as
SelectBe
s
t
an
d
C
h
i
-
Sq
u
ar
e.
A
co
m
p
r
eh
e
n
s
iv
e
s
et
o
f
3
0
f
ea
tu
r
es
ac
h
iev
ed
a
b
as
elin
e
ac
cu
r
ac
y
o
f
9
7
.
4
%,
wh
i
ch
s
lig
h
tly
d
ec
r
ea
s
ed
to
9
6
.
6
%
af
ter
s
elec
tin
g
1
3
k
ey
f
ea
tu
r
es.
T
h
is
wo
r
k
em
p
h
asized
th
e
s
ig
n
if
ican
ce
o
f
f
e
atu
r
e
s
elec
tio
n
in
e
m
p
h
asized
th
e
s
ig
n
if
ican
ce
o
f
f
ea
tu
r
e
s
elec
tio
n
in
en
h
a
n
cin
g
p
h
is
h
in
g
d
etec
tio
n
ac
c
u
r
ac
y
a
n
d
m
ain
tain
in
g
m
o
d
el
in
ter
p
r
e
tab
ilit
y
,
ad
v
an
cin
g
cy
b
er
d
e
f
en
s
e
ca
p
ab
ilit
ies
[
29
]
.
T
h
e
s
tu
d
y
in
tr
o
d
u
ce
d
p
r
ed
ict
iv
e
q
u
e
u
in
g
an
aly
s
is
to
f
o
r
ec
ast
n
etwo
r
k
p
er
f
o
r
m
an
ce
f
o
r
SD
-
UAV
n
etwo
r
k
,
en
h
a
n
cin
g
s
ec
u
r
ity
a
g
ain
s
t
ze
r
o
-
d
ay
cy
b
er
attac
k
s
.
Me
tr
ics
s
u
ch
a
in
te
r
ar
r
iv
al
tim
es
an
d
p
ac
k
et
c
o
u
n
t
s
u
p
p
o
r
ted
m
ac
h
in
e
lear
n
in
g
f
o
r
an
o
m
aly
d
etec
tio
n
.
Fu
tu
r
e
wo
r
k
aim
s
to
in
teg
r
ate
th
is
with
an
I
DS
f
o
r
r
ea
l
tim
e
th
r
ea
t
m
itig
atio
n
[3
0
]
.
T
h
e
r
esear
ch
em
p
h
asized
th
e
g
r
o
win
g
n
ee
d
f
o
r
I
DS
d
u
e
to
r
is
in
g
cy
b
er
th
r
ea
ts
,
en
h
an
cin
g
SVM
with
PS
O.
R
esu
lts
u
s
in
g
th
e
KDD
-
C
UP
9
9
d
ataset
d
em
o
n
s
tr
ate
d
im
p
r
o
v
e
d
p
e
r
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
cy
b
e
r
-
attac
k
ty
p
e
[3
1
]
.
-
Deep
lear
n
in
g
b
ased
tech
n
i
q
u
es
:
i
n
th
is
s
ec
tio
n
,
v
ar
io
u
s
d
e
ep
lear
n
in
g
tech
n
iq
u
es
f
o
r
d
et
ec
tin
g
p
h
is
h
in
g
UR
L
attac
k
s
ar
e
d
escr
ib
ed
.
A
d
etailed
in
v
esti
g
atio
n
is
p
r
esen
ted
b
elo
w,
o
u
tlin
in
g
th
e
d
if
f
er
en
t
m
eth
o
d
u
s
ed
to
id
en
tify
an
d
p
r
e
v
en
t
s
u
ch
attac
k
s
.
T
h
e
an
aly
s
is
co
v
er
s
m
u
ltip
le
ap
p
r
o
ac
h
es,
ex
am
in
in
g
th
eir
im
p
lem
en
tatio
n
.
T
h
e
f
in
d
in
g
s
p
r
o
v
id
e
in
s
ig
h
ts
in
to
s
tr
en
g
th
s
an
d
lim
itatio
n
s
o
f
e
ac
h
tech
n
iq
u
e,
co
n
tr
ib
u
tin
g
to
th
e
o
n
g
o
in
g
d
e
v
elo
p
m
en
t
o
f
r
o
b
u
s
t p
h
is
h
in
g
d
etec
tio
n
m
o
d
els.
T
h
e
r
esear
ch
p
r
o
p
o
s
ed
a
m
u
lt
i
-
lay
er
ad
a
p
tiv
e
f
r
a
m
ewo
r
k
th
at
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
th
e
d
etec
tio
n
r
ate
o
f
p
h
is
h
in
g
attac
k
s
b
y
in
c
o
r
p
o
r
ati
n
g
OC
R
f
o
r
im
ag
e
r
ec
o
g
n
itio
n
an
d
s
y
n
th
esizin
g
s
p
e
ec
h
f
r
o
m
d
ee
p
f
ak
e
v
id
eo
s
.
I
t
o
v
er
ca
m
e
th
e
lim
itatio
n
s
o
f
ex
is
tin
g
AI
-
b
ased
a
p
p
r
o
ac
h
es,
wh
ich
wer
e
p
r
im
ar
ily
tex
t
o
r
UR
L
b
ased
.
T
h
e
s
tu
d
y
’
s
lim
itatio
n
s
in
clu
d
ed
r
elian
ce
o
n
s
im
u
lated
d
ata
f
o
r
im
ag
e
a
n
d
v
id
eo
-
b
ased
p
h
is
h
in
g
,
an
d
f
u
tu
r
e
wo
r
k
s
u
g
g
ested
r
e
d
u
cin
g
co
m
p
u
tatio
n
al
a
n
d
s
er
v
e
r
r
e
s
p
o
n
s
e
tim
e
s
[3
2
]
.
A
h
y
b
r
id
c
o
n
v
o
lu
ti
o
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN
)
-
lo
n
g
s
h
o
r
t
-
t
er
m
m
em
o
r
y
n
etwo
r
k
(
L
ST
M
)
m
o
d
el
ac
h
iev
ed
9
8
.
9
%
ac
cu
r
ac
y
f
o
r
UR
L
s
p
o
o
f
in
g
,
s
u
r
p
ass
in
g
in
d
iv
id
u
al
m
o
d
els.
Desp
ite
its
h
ig
h
p
er
f
o
r
m
an
ce
,
r
ea
l
-
tim
e
ap
p
licatio
n
ch
allen
g
es
r
em
ain
.
Fu
t
u
r
e
w
o
r
k
s
h
o
u
ld
en
h
an
ce
s
p
ee
d
a
n
d
b
r
o
ad
en
d
atasets
ev
alu
atio
n
s
[3
3
]
.
T
h
e
r
esear
ch
attain
ed
9
8
.
7
4
%
ac
cu
r
ac
y
with
a
C
NN
-
b
ased
m
o
d
el,
p
r
o
ce
s
s
in
g
o
v
er
5
.
2
m
illi
o
n
UR
L
s
.
Desp
i
te
its
s
tr
en
g
th
s
in
r
ea
l
-
tim
e
an
d
lan
g
u
ag
e
in
d
e
p
en
d
en
ce
,
it
n
ee
d
s
im
p
r
o
v
e
m
en
ts
in
co
m
p
u
tatio
n
al
ef
f
i
cien
cy
an
d
d
atasets
h
an
d
lin
g
[3
4
]
.
Dev
elo
p
ed
an
in
tellig
en
t
p
h
is
h
in
g
d
etec
tio
n
s
y
s
tem
u
s
in
g
d
ee
p
lear
n
in
g
m
o
d
els,
in
clu
d
in
g
C
NN,
L
STM
,
an
d
h
y
b
r
id
m
o
d
els.
B
y
ap
p
ly
in
g
f
ea
tu
r
e
s
elec
tio
n
a
n
d
d
ata
b
ala
n
cin
g
tech
n
iq
u
es,
th
e
s
y
s
tem
ac
h
iev
e
d
an
ac
cu
r
ac
y
r
an
g
e
o
f
9
4
.
1
2
%
to
9
6
.
8
8
%
[3
5
]
.
I
n
tr
o
d
u
ce
d
th
r
ee
d
ee
p
lea
r
n
in
g
ap
p
r
o
ac
h
es
C
NN,
L
STM
,
an
d
L
STM
+CNN
f
o
r
p
h
is
h
in
g
web
s
ite
d
etec
tio
n
.
T
h
e
C
NN
m
o
d
el
ac
h
iev
e
d
th
e
h
ig
h
est
ac
cu
r
ac
y
at
9
9
.
2
%,
f
o
llo
wed
b
y
L
STM
-
C
NN
at
9
7
.
6
%
an
d
L
STM
at
9
6
.
8
%.
wh
ile
th
e
m
o
d
els
d
em
o
n
s
tr
a
ted
h
ig
h
ac
cu
r
ac
y
,
f
u
tu
r
e
wo
r
k
s
h
o
u
ld
a
d
d
r
ess
p
o
ten
tial
lim
itatio
n
s
in
g
en
e
r
aliza
b
ilit
y
an
d
r
e
al
-
tim
e
p
er
f
o
r
m
an
ce
.
E
n
h
an
ce
m
en
t
co
u
ld
in
clu
d
e
in
teg
r
ati
n
g
ad
d
itio
n
al
f
ea
tu
r
es a
n
d
o
p
tim
izin
g
f
o
r
d
iv
e
r
s
e
d
atasets
[3
6
]
.
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
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
726
-
1
7
3
3
1730
T
h
e
s
tu
d
y
p
r
o
p
o
s
ed
an
en
h
a
n
ce
d
p
h
is
h
in
g
d
etec
tio
n
m
o
d
el
in
teg
r
atin
g
v
ar
iatio
n
al
au
t
o
en
co
d
e
r
s
(
VAN)
with
d
ee
p
n
eu
r
al
n
et
wo
r
k
(
DNN)
,
ac
h
i
e
v
in
g
a
m
ax
im
u
m
ac
cu
r
ac
y
o
f
9
7
.
4
5
%
.
wh
ile
th
e
m
o
d
el
im
p
r
o
v
e
d
d
etec
tio
n
a
n
d
r
esp
o
n
s
e
tim
e,
its
lim
itatio
n
was
in
p
o
ten
tially
h
an
d
lin
g
em
e
r
g
in
g
p
h
is
h
in
g
tactics.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
ad
ap
tin
g
th
e
m
o
d
el
to
n
ew
p
h
is
h
in
g
m
eth
o
d
s
a
n
d
f
u
r
th
er
o
p
tim
izin
g
r
e
s
p
o
n
s
e
tim
e
[3
7
]
.
T
h
e
p
r
o
p
o
s
ed
d
etec
tio
n
m
ec
h
an
is
m
f
o
r
m
alicio
u
s
UR
L
s
u
s
in
g
L
STM
,
B
i
-
L
STM
,
an
d
GR
U
m
o
d
els
ac
h
iev
ed
ac
cu
r
ac
ies
o
f
9
7
.
0
%,
9
9
.
0
%,
an
d
9
7
.
5
%,
r
esp
ec
tiv
ely
.
Ho
wev
er
,
th
e
r
esea
r
ch
was
lim
ited
b
y
p
o
ten
tial
m
o
d
el
o
v
er
f
itti
n
g
an
d
th
e
n
ee
d
f
o
r
a
b
o
r
d
er
d
atase
t
to
en
h
an
ce
g
en
e
r
aliza
b
ilit
y
.
Fu
tu
r
e
wo
r
k
c
o
u
ld
h
av
e
f
o
c
u
s
ed
o
n
in
co
r
p
o
r
ati
n
g
r
ea
l
-
tim
e
d
etec
tio
n
ca
p
a
b
ilit
ies
an
d
ex
p
lo
r
in
g
h
y
b
r
id
m
o
d
els
to
f
u
r
th
er
im
p
r
o
v
e
ac
c
u
r
ac
y
an
d
r
o
b
u
s
tn
ess
ag
ain
s
t e
v
o
lv
in
g
p
h
is
h
in
g
t
ec
h
n
iq
u
es
[
38
]
.
T
h
e
s
tu
d
y
’
s
m
ain
f
in
d
in
g
was
th
at
th
e
p
r
o
p
o
s
ed
ODAE
-
W
PDC
m
o
d
el
ef
f
ec
tiv
ely
d
etec
ted
p
h
is
h
in
g
web
s
ites
with
a
m
ax
im
u
m
ac
cu
r
ac
y
o
f
9
9
.
2
8
%.
Ho
wev
e
r
,
th
e
r
esear
ch
was
lim
ited
b
y
i
ts
r
elian
ce
o
n
p
r
e
-
p
r
o
ce
s
s
in
g
an
d
s
p
ec
if
ic
alg
o
r
i
th
m
s
,
wh
ich
m
ay
n
o
t
g
en
er
ali
ze
well
to
all
d
atasets
.
Fu
tu
r
e
wo
r
k
c
o
u
ld
ex
p
lo
r
e
b
r
o
a
d
e
r
d
a
t
a
s
e
t
s
a
n
d
m
o
r
e
a
d
a
p
t
a
b
l
e
a
l
g
o
r
i
t
h
m
s
t
o
i
m
p
r
o
v
e
p
e
r
f
o
r
m
a
n
c
e
a
c
r
o
s
s
d
i
v
e
r
s
e
p
h
i
s
h
i
n
g
t
e
c
h
n
i
q
u
e
s
[
39
]
.
I
n
tr
o
d
u
ce
d
a
n
o
v
el
p
h
is
h
in
g
d
etec
tio
n
tech
n
iq
u
e
u
s
in
g
B
E
R
T
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
d
ee
p
lear
n
in
g
,
ac
h
iev
in
g
9
6
.
6
6
%
a
cc
u
r
ac
y
.
Ho
wev
er
,
th
e
s
tu
d
y
was
lim
ited
b
y
its
r
elian
ce
o
n
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es,
wh
ich
m
ay
n
o
t
f
u
lly
ca
p
tu
r
e
all
p
h
is
h
in
g
s
tr
ateg
ies
[4
0
]
.
T
h
e
s
tu
d
y
f
o
u
n
d
th
at
d
ee
p
lear
n
in
g
tech
n
iq
u
es
s
h
o
wed
p
r
o
m
is
e
f
o
r
p
h
is
h
in
g
d
etec
tio
n
b
u
t
s
tr
u
g
g
led
w
ith
m
an
u
al
p
ar
am
eter
-
tu
n
n
in
g
,
lo
n
g
tr
ain
in
g
tim
es,
an
d
ac
cu
r
ac
y
is
s
u
es
[4
1
]
.
Dev
elo
p
ed
a
n
d
o
p
tim
ized
d
e
ep
lear
n
in
g
m
o
d
els
f
o
r
p
h
is
h
in
g
web
s
ite
d
etec
tio
n
,
ac
h
iev
in
g
a
b
est
ac
cu
r
ac
y
o
f
9
7
.
3
7
%.
Hy
p
e
r
p
ar
am
eter
o
p
tim
izatio
n
u
s
in
g
GR
I
D
s
ea
r
ch
an
d
g
en
etic
al
g
o
r
it
hm
im
p
r
o
v
ed
ac
cu
r
ac
y
b
y
0
.
1
%
-
1
%.
H
o
wev
er
,
g
a
p
s
r
em
ain
e
d
in
u
n
d
e
r
s
tan
d
in
g
th
e
r
o
b
u
s
tn
ess
o
f
t
h
ese
m
o
d
els
[4
2
]
.
R
esear
ch
er
s
d
ev
elo
p
ed
a
p
h
i
s
h
in
g
ap
p
r
o
ac
h
u
s
in
g
Var
iatio
n
al
Au
to
e
n
co
d
e
r
s
an
d
d
ee
p
n
eu
r
al
n
etwo
r
k
s
,
ac
h
iev
in
g
9
7
.
4
5
%
ac
cu
r
ac
y
an
d
a
r
esp
o
n
s
e
tim
e
o
f
1
.
9
s
ec
o
n
d
s
,
s
u
r
p
ass
in
g
tr
ad
itio
n
al
b
lack
lis
t
-
b
ased
m
eth
o
d
s
[
39
]
.
T
h
e
r
esear
ch
p
r
o
p
o
s
ed
a
m
o
d
el
u
s
in
g
C
NNs
to
class
if
y
web
p
ag
es
as
b
en
ig
n
o
r
p
h
is
h
in
g
b
ased
o
n
UR
L
s
an
d
im
ag
es,
ac
h
ie
v
in
g
9
9
.
6
7
% a
cc
u
r
ac
y
[4
3
]
.
C
o
m
p
ar
ed
C
NN,
L
STM
-
C
NN,
an
d
L
ST
M
f
o
r
p
h
is
h
in
g
d
etec
tio
n
,
ac
h
iev
in
g
9
9
.
2
%,
9
7
.
6
%,
a
n
d
9
6
.
8
%
ac
cu
r
ac
y
,
r
esp
ec
tiv
ely
;
C
NN
p
er
f
o
r
m
e
d
b
est
[4
4
]
.
T
h
e
s
tu
d
y
d
ev
elo
p
ed
a
s
u
p
er
v
i
s
ed
lear
n
in
g
m
o
d
el
f
o
r
An
d
r
o
id
m
alwa
r
e
d
etec
tio
n
,
o
u
tp
er
f
o
r
m
in
g
e
x
is
tin
g
m
et
h
o
d
s
in
p
r
ec
is
io
n
,
ef
f
icien
c
y
,
a
n
d
p
r
ec
is
i
on
[4
5
]
.
T
h
e
p
ap
e
r
p
r
esen
ted
a
C
NN
-
b
ased
p
h
is
h
in
g
d
etec
tio
n
m
et
h
o
d
with
an
8
6
.
6
3
%
tr
u
e
d
et
ec
tio
n
r
ate
an
d
3
0
%
f
aster
ex
ec
u
tio
n
o
n
a
R
asp
b
er
r
y
Pi.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
in
teg
r
atin
g
d
e
ep
lear
n
in
g
m
o
d
els
f
o
r
web
p
a
g
e
co
n
ten
t
an
al
y
s
is
[4
6
]
.
I
n
tr
o
d
u
ce
d
T
h
e
ODAE
-
W
PD
C
f
o
r
p
h
is
h
in
g
d
etec
tio
n
,
ac
h
iev
in
g
9
9
.
2
8
%
ac
cu
r
ac
y
with
d
ee
p
au
to
e
n
co
d
er
s
an
d
o
p
tim
ize
d
f
ea
tu
r
e
s
e
lectio
n
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
im
p
r
o
v
in
g
r
ea
l
-
tim
e
ap
p
licatio
n
a
n
d
ad
a
p
tab
ilit
y
[
47
].
2.
SUM
M
AR
I
Z
I
NG
K
E
Y
F
I
N
DING
S
Key
f
in
d
in
g
s
fr
o
m
an
ti
-
p
h
is
h
in
g
r
esear
ch
r
e
v
ea
l
th
at
b
lack
lis
t
-
b
ased
tech
n
iq
u
es
ac
h
iev
ed
h
ig
h
ac
cu
r
ac
y
(
u
p
t
o
9
9
%)
b
u
t
s
tr
u
g
g
led
with
DNS
s
p
o
o
f
in
g
a
n
d
d
ataset
r
elian
ce
,
s
u
g
g
esti
n
g
f
u
tu
r
e
wo
r
k
s
h
o
u
ld
en
h
an
ce
h
eu
r
is
tic
m
eth
o
d
s
a
n
d
in
te
g
r
ate
I
P
ad
d
r
ess
es.
H
eu
r
is
tic
-
b
ased
m
e
th
o
d
s
d
em
o
n
s
tr
ated
u
p
to
9
7
%
ac
cu
r
ac
y
in
d
etec
tin
g
n
ew
p
h
is
h
in
g
s
ites
b
u
t
f
ac
ed
lim
itatio
n
s
with
s
o
p
h
is
ticated
tact
ics,
r
ec
o
m
m
en
d
in
g
f
u
r
th
er
ex
p
lo
r
atio
n
o
f
n
ew
f
e
atu
r
es
an
d
r
ea
l
-
tim
e
d
etec
tio
n
.
Vis
u
al
s
im
ilar
ity
tech
n
iq
u
es,
ac
h
iev
in
g
u
p
to
9
8
.
7
4
%
ac
cu
r
ac
y
,
e
n
co
u
n
ter
e
d
d
if
f
icu
lties
with
d
etec
tin
g
h
ig
h
ly
d
is
s
im
ilar
p
h
is
h
in
g
s
ites
,
in
d
icatin
g
a
n
ee
d
f
o
r
im
p
r
o
v
e
d
r
o
b
u
s
tn
ess
an
d
b
o
r
d
e
r
ap
p
licatio
n
.
Ma
ch
i
n
e
lear
n
in
g
m
eth
o
d
s
,
i
n
clu
d
in
g
r
an
d
o
m
f
o
r
est
an
d
XGBo
o
s
t,
r
ea
ch
ed
u
p
to
9
9
.
9
3
%
ac
cu
r
ac
y
b
u
t
h
ad
is
s
u
es
with
f
e
atu
r
e
d
ep
en
d
en
ce
a
n
d
s
ca
lab
ilit
y
,
with
f
u
tu
r
e
wo
r
k
f
o
c
u
s
in
g
o
n
d
ataset
d
iv
er
s
ity
an
d
ad
v
an
ce
d
al
g
o
r
ith
m
s
.
Dee
p
lear
n
in
g
ap
p
r
o
ac
h
e
s
,
s
u
ch
as
C
NNs
an
d
L
STM
s
,
ex
h
ib
ited
h
ig
h
ac
c
u
r
ac
y
(
u
p
to
9
9
.
6
7
%)
b
u
t
f
ac
ed
ch
allen
g
es
in
r
ea
l
-
tim
e
ap
p
licatio
n
an
d
g
en
er
aliza
b
ilit
y
,
h
i
g
h
lig
h
tin
g
t
h
e
n
ee
d
f
o
r
e
n
h
an
ce
d
ad
a
p
tab
i
lity
an
d
in
teg
r
ati
o
n
o
f
d
iv
e
r
s
e
d
atasets
.
3.
I
NT
E
RP
R
E
T
I
NG
RE
SUL
T
S
T
h
e
an
aly
s
is
o
f
an
ti
-
p
h
is
h
in
g
t
ec
h
n
iq
u
es,
as
illu
s
tr
ated
in
Fi
g
u
r
e
1
,
r
ev
e
als
s
u
b
s
tan
tial
d
if
f
er
en
ce
s
in
d
etec
tio
n
ac
cu
r
ac
y
ac
r
o
s
s
v
ar
i
o
u
s
m
eth
o
d
s
.
T
h
e
d
ee
p
lear
n
i
n
g
-
b
ased
ap
p
r
o
ac
h
,
p
ar
ticu
la
r
ly
th
e
C
NN
m
o
d
els,
ac
h
iev
ed
t
h
e
h
i
g
h
est
ac
cu
r
ac
y
o
f
9
9
.
6
7
%,
d
em
o
n
s
tr
atin
g
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
d
etec
ti
o
n
p
h
is
h
in
g
th
r
ea
ts
with
m
in
im
al
f
alse
p
o
s
itiv
es
an
d
n
eg
ativ
es,
wh
ile
s
ti
ll
ef
f
ec
tiv
e,
ex
h
ib
it
lo
wer
ac
c
u
r
ac
ies
d
u
e
to
lim
itatio
n
s
in
th
eir
s
co
p
e
an
d
ad
a
p
tab
ilit
y
.
T
h
is
co
m
p
ar
is
o
n
h
ig
h
lig
h
ts
th
e
ad
v
an
ce
d
ca
p
ab
ilit
y
o
f
d
ee
p
le
ar
n
in
g
m
o
d
els
an
d
ex
p
lo
r
in
g
h
y
b
r
id
m
o
d
els
th
at
in
teg
r
ate
th
ese
with
h
eu
r
is
tic
an
d
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
to
ad
d
r
ess
th
eir
in
d
iv
id
u
al
lim
itatio
n
s
.
Su
ch
in
teg
r
atio
n
is
lik
ely
to
p
r
o
v
id
e
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
an
d
r
esil
ien
t
d
ef
en
s
e
ag
ain
s
t e
v
o
lv
in
g
p
h
is
h
in
g
tactics.
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
E
vo
lvin
g
s
tr
a
teg
ies in
a
n
ti
-
p
h
is
h
in
g
:
a
n
in
-
d
e
p
th
a
n
a
lysi
s
o
f d
etec
tio
n
tech
n
iq
u
es
…
(
P
r
ee
ti
)
1731
Fig
u
r
e
1
.
Acc
u
r
ac
y
c
o
m
p
ar
is
o
n
o
f
v
ar
io
u
s
an
ti
-
p
h
is
h
in
g
tec
h
n
iq
u
es: b
lack
lis
t
-
b
ased
,
h
e
u
r
is
tic
-
b
ased
,
v
is
u
al
s
im
ilar
ity
-
b
ased
,
m
ac
h
i
n
e
lear
n
in
g
-
b
ased
,
a
n
d
d
ee
p
l
ea
r
n
in
g
-
b
ased
ap
p
r
o
ac
h
es
4.
ADDR
E
SS
I
NG
L
I
M
I
T
A
T
I
O
N
B
lack
lis
t
-
b
ased
tech
n
iq
u
es
f
ac
e
ch
allen
g
es
in
d
etec
tin
g
n
ew
o
r
ev
o
l
v
in
g
p
h
is
h
in
g
th
r
ea
ts
d
u
e
to
th
eir
r
elian
ce
o
n
p
r
ec
o
m
p
iled
lis
ts
th
at
m
ay
n
o
t
in
clu
d
e
th
e
latest
p
h
is
h
in
g
s
ites
.
T
h
is
m
eth
o
d
also
s
tr
u
g
g
les
with
is
s
u
es
lik
e
DNS
s
p
o
o
f
in
g
an
d
p
h
is
h
in
g
h
o
s
ted
o
n
leg
itima
te
d
o
m
ain
s
.
Heu
r
is
tic
-
b
ased
tech
n
iq
u
es,
wh
ile
u
s
ef
u
l
f
o
r
i
d
en
tify
in
g
s
u
s
p
icio
u
s
p
atter
n
s
,
m
ay
f
alter
a
g
ai
n
s
t
s
o
p
h
is
ticated
p
h
is
h
in
g
att
em
p
ts
th
at
clo
s
ely
m
im
ic
leg
itima
te
s
ite
s
an
d
ar
e
less
ad
ap
tab
le
to
ev
o
lv
in
g
th
r
ea
ts
.
Vis
u
al
s
im
ilar
i
ty
-
b
ased
tech
n
iq
u
es,
wh
ich
ass
es
s
v
is
u
al
f
ea
tu
r
es
o
f
web
p
ag
es,
m
ay
m
is
s
p
h
is
h
in
g
atta
ck
s
th
at
d
o
n
o
t
v
is
u
ally
r
esem
b
le
le
g
itima
te
s
ites
,
esp
ec
ially
th
o
s
e
u
s
in
g
ad
v
an
ce
d
d
esig
n
s
.
Ad
d
itio
n
ally
,
th
ese
m
eth
o
d
s
m
ay
n
o
t
h
an
d
le
r
ea
l
tim
e
th
r
ea
ts
ef
f
ec
tiv
ely
.
Ma
ch
i
n
e
lear
n
i
n
g
an
d
d
ee
p
lear
n
in
g
a
p
p
r
o
ac
h
es,
th
o
u
g
h
p
r
o
m
is
in
g
,
ca
n
b
e
lim
ited
b
y
d
ataset
b
iases
,
co
m
p
u
tatio
n
al
r
eso
u
r
ce
d
em
an
d
s
,
an
d
ch
allen
g
es
in
r
ea
l
tim
e
ap
p
licatio
n
,
n
ec
ess
itatin
g
f
u
tu
r
e
o
p
tim
izatio
n
an
d
ad
ap
tatio
n
to
en
h
an
ce
o
v
er
all
p
h
is
h
in
g
d
etec
tio
n
ca
p
ab
ilit
ies.
5.
I
M
P
L
I
CA
T
I
O
N
S F
O
R
F
UT
URE R
E
S
E
ARCH
Ou
r
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
d
ee
p
lear
n
i
n
g
-
b
ased
tech
n
iq
u
es,
p
ar
ticu
lar
ly
th
o
s
e
u
s
in
g
C
NNs
an
d
L
STM
s
,
ex
h
ib
it
s
u
p
er
i
o
r
ac
c
u
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
in
p
h
is
h
in
g
d
etec
tio
n
c
o
m
p
ar
e
d
to
h
eu
r
is
tic
-
b
ased
an
d
b
lack
lis
t
-
b
ased
m
eth
o
d
s
.
Fu
tu
r
e
r
esear
ch
co
u
ld
ex
p
lo
r
e
en
h
an
cin
g
th
ese
tech
n
iq
u
es
b
y
in
t
eg
r
atin
g
a
d
d
itio
n
al
f
ea
tu
r
es
an
d
d
e
v
elo
p
in
g
m
o
r
e
ef
f
icien
t
m
o
d
els
to
h
a
n
d
le
d
i
v
er
s
e
p
h
is
h
in
g
s
ce
n
ar
io
s
.
Sp
ec
if
ically
,
in
v
esti
g
atin
g
th
e
co
m
b
in
atio
n
o
f
d
ee
p
lear
n
in
g
with
o
th
er
d
etec
tio
n
m
eth
o
d
s
,
s
u
ch
as
v
is
u
al
s
im
ilar
ity
an
d
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
,
co
u
l
d
p
r
o
v
id
e
a
m
o
r
e
co
m
p
r
eh
en
s
iv
e
d
ef
e
n
s
e
ag
ai
n
s
t
ev
o
lv
i
n
g
p
h
is
h
in
g
th
r
ea
ts
.
Ad
d
itio
n
ally
,
f
o
cu
s
in
g
o
n
o
p
tim
izin
g
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
an
d
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
ca
p
ab
ilit
ies
will
b
e
cr
u
cial
f
o
r
im
p
r
o
v
in
g
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
an
d
r
ea
l
-
to
m
e
p
r
o
ce
s
s
in
g
ca
p
ab
il
ities
wi
ll
b
e
cr
u
cial
f
o
r
im
p
r
o
v
i
n
g
th
e
p
r
ac
tical
d
ep
lo
y
m
e
n
t
o
f
th
ese
ad
v
a
n
c
ed
tech
n
iq
u
es.
Feasib
le
way
to
p
r
o
d
u
ce
t
h
ese
im
p
r
o
v
em
e
n
ts
in
clu
d
e
le
v
er
ag
in
g
tr
an
s
f
er
lea
r
n
in
g
,
r
ef
i
n
in
g
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
,
a
n
d
ex
p
lo
r
in
g
n
o
v
el
h
y
b
r
id
m
o
d
els
to
ac
h
ie
v
e
h
i
g
h
er
d
etec
tio
n
ac
cu
r
ac
y
an
d
r
ed
u
ce
d
f
als
e
p
o
s
itiv
e
in
d
y
n
am
ic,
r
ea
l
-
wo
r
ld
en
v
ir
o
n
m
en
ts
.
6.
CO
NCLU
SI
O
N
I
n
r
ev
iewin
g
th
e
liter
atu
r
e
o
n
an
ti
-
p
h
is
h
in
g
tech
n
iq
u
es,
it
b
e
co
m
es
ev
id
en
t
th
at
d
ee
p
lea
r
n
in
g
-
b
ased
m
eth
o
d
s
,
p
ar
ticu
lar
ly
C
NNs,
o
f
f
er
th
e
h
ig
h
est
d
etec
tio
n
ac
c
u
r
ac
y
,
r
ea
ch
i
n
g
u
p
to
9
9
.
6
7
%.
T
h
is
s
u
r
p
ass
es
th
e
ef
f
ec
tiv
en
ess
o
f
o
th
e
r
tech
n
i
q
u
es,
in
clu
d
in
g
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
es
th
at
ac
h
iev
e
u
p
to
9
9
.
9
3
%
ac
cu
r
ac
y
an
d
h
e
u
r
is
tic
-
b
ased
m
eth
o
d
s
.
T
h
e
s
u
p
er
i
o
r
ity
o
f
d
ee
p
lea
r
n
in
g
m
o
d
els
in
ac
c
u
r
ac
y
i
d
en
tify
in
g
p
h
is
h
in
g
attem
p
ts
h
ig
h
lig
h
ts
th
eir
r
o
b
u
s
t
n
ess
an
d
ef
f
ec
tiv
e
n
ess
in
m
in
im
izin
g
d
etec
tio
n
er
r
o
r
s
.
T
o
a
d
d
r
ess
th
e
ev
o
lv
in
g
n
atu
r
e
o
f
p
h
is
h
in
g
attac
k
s
,
it
i
s
cr
u
cial
f
o
r
f
u
tu
r
e
r
esear
ch
t
o
f
o
cu
s
o
n
o
p
tim
izin
g
th
ese
ad
v
an
ce
d
m
o
d
els
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
an
d
to
ex
p
lo
r
e
th
eir
p
o
ten
tial
in
teg
r
atio
n
w
ith
o
th
er
d
etec
tio
n
s
tr
ateg
ies.
E
n
h
an
cin
g
th
ese
tech
n
iq
u
es
an
d
th
eir
a
d
ap
tab
ilit
y
will
b
e
ess
en
tial
in
s
tr
en
g
th
e
n
in
g
d
ef
e
n
s
es
ag
ain
s
t
in
cr
ea
s
in
g
ly
s
o
p
h
is
ticated
p
h
is
h
in
g
th
r
ea
ts
.
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
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
726
-
1
7
3
3
1732
RE
F
E
R
E
NC
E
S
[
1
]
V
.
B
h
a
v
s
a
r
,
A
.
K
a
d
l
a
k
,
a
n
d
S
.
S
h
a
r
ma,
“
S
t
u
d
y
o
n
p
h
i
s
h
i
n
g
a
t
t
a
c
k
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
2
,
n
o
.
3
3
,
p
p
.
2
7
–
2
9
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
5
1
2
0
/
i
j
c
a
2
0
1
8
9
1
8
2
8
6
.
[
2
]
Z.
A
l
k
h
a
l
i
l
,
C
.
H
e
w
a
g
e
,
L
.
N
a
w
a
f
,
a
n
d
I
.
K
h
a
n
,
“
P
h
i
s
h
i
n
g
a
t
t
a
c
k
s
:
a
r
e
c
e
n
t
c
o
m
p
r
e
h
e
n
s
i
v
e
st
u
d
y
a
n
d
a
n
e
w
a
n
a
t
o
my
,”
Fro
n
t
i
e
r
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
9
/
f
c
o
mp
.
2
0
2
1
.
5
6
3
0
6
0
.
[
3
]
S
.
S
h
e
n
g
,
B
.
W
a
r
d
m
a
n
,
G
.
W
a
r
n
e
r
,
L.
F
.
C
r
a
n
o
r
,
J.
H
o
n
g
,
a
n
d
C
.
Z
h
a
n
g
,
“
A
n
e
m
p
i
r
i
c
a
l
a
n
a
l
y
s
i
s
o
f
p
h
i
s
h
i
n
g
b
l
a
c
k
l
i
st
s,
”
i
n
6
t
h
C
o
n
f
e
r
e
n
c
e
o
n
Em
a
i
l
a
n
d
A
n
t
i
-
S
p
a
m
,
C
E
AS
2
0
0
9
,
2
0
0
9
.
[
4
]
A
.
V
.
R
.
M
a
y
u
r
i
,
M
.
Te
c
h
,
a
n
d
D
.
P
h
,
“
P
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
v
i
su
a
l
-
si
m
i
l
a
r
i
t
y
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
t
i
f
i
c
a
n
d
En
g
i
n
e
e
ri
n
g
Re
s
e
a
rc
h
(
I
J
S
ER)
,
v
o
l
.
3
,
n
o
.
3
,
p
p
.
1
–
5
,
2
0
1
2
.
[
5
]
C
.
M
.
R
.
d
a
S
i
l
v
a
,
E.
L.
F
e
i
t
o
sa
,
a
n
d
V
.
C
.
G
a
r
c
i
a
,
“
H
e
u
r
i
st
i
c
-
b
a
s
e
d
s
t
r
a
t
e
g
y
f
o
r
P
h
i
s
h
i
n
g
p
r
e
d
i
c
t
i
o
n
:
A
s
u
r
v
e
y
o
f
U
R
L
-
b
a
se
d
a
p
p
r
o
a
c
h
,
”
C
o
m
p
u
t
e
rs
&
S
e
c
u
r
i
t
y
,
v
o
l
.
8
8
,
p
.
1
0
1
6
1
3
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se.
2
0
1
9
.
1
0
1
6
1
3
.
[
6
]
R
.
K
i
r
u
t
h
i
g
a
a
n
d
D
.
A
k
i
l
a
,
“
P
h
i
s
h
i
n
g
w
e
b
s
i
t
e
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
R
e
c
e
n
t
T
e
c
h
n
o
l
o
g
y
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
8
,
n
o
.
2
S
p
e
c
i
a
l
I
ssu
e
1
1
,
p
p
.
1
1
1
–
1
1
4
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
3
5
9
4
0
/
i
j
r
t
e
.
B
1
0
1
8
.
0
9
8
2
S
1
1
1
9
.
[
7
]
V
.
R
a
v
i
,
S
.
S
r
i
n
i
v
a
sa
n
,
S
.
K
p
,
a
n
d
M
.
A
l
a
z
a
b
,
“
M
a
l
i
c
i
o
u
s
U
R
L
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
.
”
p
p
.
1
–
9
,
Jan
.
1
1
,
2
0
2
0
.
d
o
i
:
1
0
.
3
6
2
2
7
/
t
e
c
h
r
x
i
v
.
1
1
4
9
2
6
2
2
.
v
1
.
[
8
]
A
.
B
e
l
a
b
e
d
,
E.
A
ï
me
u
r
,
a
n
d
A
.
C
h
i
k
h
,
“
A
p
e
r
so
n
a
l
i
z
e
d
w
h
i
t
e
l
i
st
a
p
p
r
o
a
c
h
f
o
r
p
h
i
sh
i
n
g
w
e
b
p
a
g
e
d
e
t
e
c
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
2
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Av
a
i
l
a
b
i
l
i
t
y
,
Re
l
i
a
b
i
l
i
t
y
a
n
d
S
e
c
u
r
i
t
y
,
AR
ES
2
0
1
2
,
I
EEE,
A
u
g
.
2
0
1
2
,
p
p
.
2
4
9
–
2
5
4
.
d
o
i
:
1
0
.
1
1
0
9
/
A
R
ES.
2
0
1
2
.
5
4
.
[
9
]
P
.
P
r
a
k
a
s
h
,
M
.
K
u
mar,
R
.
R
a
o
K
o
mp
e
l
l
a
,
a
n
d
M
.
G
u
p
t
a
,
“
P
h
i
sh
N
e
t
:
p
r
e
d
i
c
t
i
v
e
b
l
a
c
k
l
i
s
t
i
n
g
t
o
d
e
t
e
c
t
p
h
i
s
h
i
n
g
a
t
t
a
c
k
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
I
EEE
I
N
FO
C
O
M
,
I
EEE,
M
a
r
.
2
0
1
0
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
N
F
C
O
M
.
2
0
1
0
.
5
4
6
2
2
1
6
.
[
1
0
]
N
.
M
.
S
h
e
k
o
k
a
r
,
C
.
S
h
a
h
,
M
.
M
a
h
a
j
a
n
,
a
n
d
S
.
R
a
c
h
h
,
“
A
n
i
d
e
a
l
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
o
f
p
h
i
s
h
i
n
g
a
t
t
a
c
k
s
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
4
9
,
n
o
.
1
,
p
p
.
8
2
–
9
1
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
5
.
0
4
.
2
3
0
.
[
1
1
]
E.
S
.
A
u
n
g
,
T.
Z
a
n
,
a
n
d
H
.
Y
a
man
a
,
“
A
s
u
r
v
e
y
o
f
U
R
L
-
b
a
se
d
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
,
”
D
EM
F
o
r
u
m
.
p
p
.
1
–
8
,
2
0
1
9
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
d
b
-
e
v
e
n
t
.
j
p
n
.
o
r
g
/
d
e
i
m
2
0
1
9
/
p
o
s
t
/
p
a
p
e
r
s/
2
0
1
.
p
d
f
[
1
2
]
K
.
S
.
A
d
e
w
o
l
e
,
A
.
G
.
A
k
i
n
t
o
l
a
,
S
.
A
.
S
a
l
i
h
u
,
N
.
F
a
r
u
k
,
a
n
d
R
.
G
.
Ji
m
o
h
,
“
H
y
b
r
i
d
r
u
l
e
-
b
a
se
d
m
o
d
e
l
f
o
r
p
h
i
sh
i
n
g
U
R
Ls
d
e
t
e
c
t
i
o
n
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
o
f
t
h
e
I
n
s
t
i
t
u
t
e
f
o
r
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s,
S
o
c
i
a
l
-
I
n
f
o
rm
a
t
i
c
s
a
n
d
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
E
n
g
i
n
e
e
ri
n
g
,
L
N
I
C
S
T
,
v
o
l
.
2
8
5
,
2
0
1
9
,
p
p
.
1
1
9
–
1
3
5
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
2
3
9
4
3
-
5
_
9
.
[
1
3
]
Q
.
L.
R
a
m
B
.
B
a
s
n
e
t
,
A
n
d
r
e
w
H
.
S
u
n
g
,
“
R
u
l
e
-
b
a
s
e
d
p
h
i
s
h
i
n
g
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
e
c
u
ri
t
y
a
n
d
Ma
n
a
g
e
m
e
n
t
-
S
AM
’
1
1
,
2
0
1
1
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
c
s.
n
mt
.
e
d
u
/
~
r
b
a
sn
e
t
/
r
e
sea
r
c
h
.
h
t
ml
[1
4
]
A
.
B
e
g
u
m
a
n
d
S
.
B
a
d
u
g
u
,
“
A
st
u
d
y
o
f
ma
l
i
c
i
o
u
s
U
R
L
d
e
t
e
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
h
e
u
r
i
s
t
i
c
a
p
p
r
o
a
c
h
e
s
,”
i
n
L
e
a
rn
i
n
g
a
n
d
A
n
a
l
y
t
i
c
s i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
4
,
2
0
2
0
,
p
p
.
5
8
7
–
5
9
7
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
2
4
3
1
8
-
0
_
6
8
.
[1
5
]
R
.
S
.
R
a
o
a
n
d
S
.
T.
A
l
i
,
“
P
h
i
s
h
S
h
i
e
l
d
:
a
d
e
sk
t
o
p
a
p
p
l
i
c
a
t
i
o
n
t
o
d
e
t
e
c
t
p
h
i
sh
i
n
g
w
e
b
p
a
g
e
s
t
h
r
o
u
g
h
h
e
u
r
i
st
i
c
a
p
p
r
o
a
c
h
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
4
,
p
p
.
1
4
7
–
1
5
6
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.2
0
1
5
.
0
6
.
0
1
7
.
[1
6
]
L.
A
.
T
.
N
g
u
y
e
n
,
B
.
L.
T
o
,
H
.
K
.
N
g
u
y
e
n
,
a
n
d
M
.
H
.
N
g
u
y
e
n
,
“
D
e
t
e
c
t
i
n
g
p
h
i
s
h
i
n
g
w
e
b
si
t
e
s
:
a
h
e
u
r
i
st
i
c
U
R
L
-
b
a
sed
a
p
p
r
o
a
c
h
,
”
i
n
2
0
1
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
ATC
2
0
1
3
)
,
I
EEE,
O
c
t
.
2
0
1
3
,
p
p
.
5
9
7
–
6
0
2
.
d
o
i
:
1
0
.
1
1
0
9
/
A
TC
.
2
0
1
3
.
6
6
9
8
1
8
5
.
[1
7
]
R
.
A
l
m
e
i
d
a
a
n
d
C
.
W
e
st
p
h
a
l
l
,
“
H
e
u
r
i
st
i
c
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
a
n
d
U
R
L
c
h
e
c
k
i
n
g
met
h
o
d
o
l
o
g
y
b
a
se
d
o
n
s
c
r
a
p
i
n
g
a
n
d
w
e
b
c
r
a
w
l
i
n
g
,
”
i
n
2
0
2
0
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
e
c
u
ri
t
y
I
n
f
o
rm
a
t
i
c
s
(
I
S
I
)
,
I
EEE,
N
o
v
.
2
0
2
0
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
I
4
9
8
2
5
.
2
0
2
0
.
9
2
8
0
5
4
9
.
[1
8
]
J.
S
o
l
a
n
k
i
a
n
d
R
.
G
.
V
a
i
s
h
n
a
v
,
“
W
e
b
si
t
e
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
u
s
i
n
g
h
e
u
r
i
s
t
i
c
b
a
s
e
d
a
p
p
r
o
a
c
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
R
e
sea
r
c
h
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
p
p
.
2
0
4
4
–
2
0
4
8
,
2
0
1
6
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
w
w
w
.
i
r
j
e
t
.
n
e
t
[1
9
]
F
.
Ji
e
t
a
l
.
,
“
Ev
a
l
u
a
t
i
n
g
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
a
n
d
r
o
b
u
st
n
e
ss
o
f
v
i
su
a
l
si
m
i
l
a
r
i
t
y
-
b
a
se
d
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
m
o
d
e
l
s
.
”
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s
/
2
4
0
5
.
1
9
5
9
8
[2
0
]
S
.
A
b
d
e
l
n
a
b
i
,
K
.
K
r
o
mb
h
o
l
z
,
a
n
d
M
.
F
r
i
t
z
,
“
V
i
s
u
a
l
P
h
i
s
h
N
e
t
:
z
e
r
o
-
d
a
y
p
h
i
s
h
i
n
g
w
e
b
s
i
t
e
d
e
t
e
c
t
i
o
n
b
y
v
i
s
u
a
l
si
mi
l
a
r
i
t
y
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
S
e
c
u
ri
t
y
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
O
c
t
.
2
0
2
0
,
p
p
.
1
6
8
1
–
1
6
9
8
.
d
o
i
:
1
0
.
1
1
4
5
/
3
3
7
2
2
9
7
.
3
4
1
7
2
3
3
.
[2
1
]
Y
.
Z
h
o
u
,
Y
.
Z
h
a
n
g
,
J.
X
i
a
o
,
Y
.
W
a
n
g
,
a
n
d
W
.
Li
n
,
“
V
i
s
u
a
l
S
i
mi
l
a
r
i
t
y
b
a
s
e
d
a
n
t
i
-
p
h
i
sh
i
n
g
w
i
t
h
t
h
e
c
o
m
b
i
n
a
t
i
o
n
o
f
l
o
c
a
l
a
n
d
g
l
o
b
a
l
f
e
a
t
u
r
e
s
,
”
i
n
2
0
1
4
I
E
EE
1
3
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
T
ru
s
t
,
S
e
c
u
r
i
t
y
a
n
d
Pri
v
a
c
y
i
n
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
I
EEE,
S
e
p
.
2
0
1
4
,
p
p
.
1
8
9
–
1
9
6
.
d
o
i
:
1
0
.
1
1
0
9
/
Tr
u
st
C
o
m.
2
0
1
4
.
2
8
.
[2
2
]
J.
M
a
o
,
P
.
L
i
,
K
.
Li
,
T.
W
e
i
,
a
n
d
Z.
Li
a
n
g
,
“
B
a
i
t
A
l
a
r
m:
d
e
t
e
c
t
i
n
g
p
h
i
s
h
i
n
g
si
t
e
s
u
s
i
n
g
s
i
mi
l
a
r
i
t
y
i
n
f
u
n
d
a
m
e
n
t
a
l
v
i
su
a
l
f
e
a
t
u
r
e
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
N
e
t
w
o
rk
i
n
g
a
n
d
C
o
l
l
a
b
o
r
a
t
i
v
e
S
y
s
t
e
m
s,
I
N
C
o
S
2
0
1
3
,
I
EEE,
S
e
p
.
2
0
1
3
,
p
p
.
7
9
0
–
7
9
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
N
C
o
S
.
2
0
1
3
.
1
5
1
.
[2
3
]
V
i
sh
e
sh
B
h
a
r
u
k
a
,
A
l
l
a
n
A
l
m
e
i
d
a
,
a
n
d
S
h
a
r
v
a
r
i
P
a
t
i
l
,
“
P
h
i
sh
i
n
g
d
e
t
e
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
i
e
n
t
i
f
i
c
R
e
se
a
rc
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
3
4
3
–
3
4
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
2
6
2
8
/
c
s
e
i
t
2
4
1
0
2
2
8
.
[2
4
]
E.
K
o
c
y
i
g
i
t
,
M
.
K
o
r
k
ma
z
,
O
.
K
.
S
a
h
i
n
g
o
z
,
a
n
d
B
.
D
i
r
i
,
“
E
n
h
a
n
c
e
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
u
si
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
f
o
r
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
h
i
s
h
i
n
g
U
R
L
d
e
t
e
c
t
i
o
n
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
1
4
,
p
.
6
0
8
1
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
4
1
4
6
0
8
1
.
[2
5
]
A
.
K
.
Ja
i
n
a
n
d
B
.
B
.
G
u
p
t
a
,
“
P
H
I
S
H
-
S
A
F
E:
U
R
L
f
e
a
t
u
r
e
s
-
b
a
s
e
d
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
s
y
st
e
m
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
Ad
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
2
9
,
2
0
1
8
,
p
p
.
4
6
7
–
4
7
4
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
10
-
8
5
3
6
-
9
_
4
4
.
[2
6
]
R
.
J
a
y
a
r
a
j
,
A
.
P
u
sh
p
a
l
a
t
h
a
,
K
.
S
a
n
g
e
e
t
h
a
,
T.
K
a
m
a
l
e
sh
w
a
r
,
S
.
U
d
h
a
y
a
S
h
r
e
e
,
a
n
d
D
.
D
a
mo
d
a
r
a
n
,
“
I
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
w
i
t
h
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
M
e
a
su
r
e
m
e
n
t
:
S
e
n
so
rs
,
v
o
l
.
3
1
,
p
.
1
0
1
0
0
3
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
a
s
e
n
.
2
0
2
3
.
1
0
1
0
0
3
.
[2
7
]
G
.
R
.
K
u
mar,
S
.
G
u
n
a
s
e
k
a
r
a
n
,
N
.
R
,
S
.
P
.
K
,
S
.
G
,
a
n
d
V
.
A
.
S
,
“
U
r
l
p
h
i
s
h
i
n
g
d
a
t
a
a
n
a
l
y
s
i
s
a
n
d
d
e
t
e
c
t
i
n
g
p
h
i
s
h
i
n
g
a
t
t
a
c
k
s
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
i
n
n
l
p
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
r
i
n
g
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
1
0
,
p
p
.
2
6
–
3
1
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
5
6
4
/
i
j
e
a
s
t
.
2
0
1
9
.
v
0
3
i
1
0
.
0
0
7
.
[
28
]
S
.
D
a
s
G
u
p
t
t
a
,
K
.
T.
S
h
a
h
r
i
a
r
,
H
.
A
l
q
a
h
t
a
n
i
,
D
.
A
l
sa
l
ma
n
,
a
n
d
I
.
H
.
S
a
r
k
e
r
,
“
M
o
d
e
l
i
n
g
h
y
b
r
i
d
f
e
a
t
u
r
e
-
b
a
se
d
p
h
i
s
h
i
n
g
w
e
b
si
t
e
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
A
n
n
a
l
s
o
f
D
a
t
a
S
c
i
e
n
c
e
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
2
1
7
–
2
4
2
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
7
4
5
-
022
-
0
0
3
7
9
-
8.
[
29
]
S
.
H
.
N
a
l
l
a
m
a
l
a
,
K
.
N
a
mi
t
h
a
,
K
.
R
a
v
i
t
e
j
a
,
K
.
S
.
S
u
ma
n
t
h
,
a
n
d
J.
S
.
K
o
t
a
,
“
P
h
i
s
h
i
n
g
U
R
L
d
e
t
e
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
f
o
r
Re
s
e
a
r
c
h
i
n
A
p
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
n
o
.
3
,
p
p
.
1
9
8
4
–
1
9
9
5
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
2
2
2
1
4
/
i
j
r
a
s
e
t
.
2
0
2
4
.
5
9
2
6
1
.
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
E
vo
lvin
g
s
tr
a
teg
ies in
a
n
ti
-
p
h
is
h
in
g
:
a
n
in
-
d
e
p
th
a
n
a
lysi
s
o
f d
etec
tio
n
tech
n
iq
u
es
…
(
P
r
ee
ti
)
1733
[3
0
]
D
.
A
g
n
e
w
,
A
.
D
e
l
A
g
u
i
l
a
,
a
n
d
J
.
M
c
n
a
i
r
,
“
En
h
a
n
c
e
d
n
e
t
w
o
r
k
m
e
t
r
i
c
p
r
e
d
i
c
t
i
o
n
f
o
r
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
c
y
b
e
r
se
c
u
r
i
t
y
o
f
a
so
f
t
w
a
r
e
-
d
e
f
i
n
e
d
UAV
r
e
l
a
y
n
e
t
w
o
r
k
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
5
4
2
0
2
–
5
4
2
1
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
8
7
7
2
8
.
[3
1
]
N
.
O
mer,
A
.
H
.
S
a
m
a
k
,
A
.
I
.
Ta
l
o
b
a
,
a
n
d
R
.
M
.
A
b
d
El
-
A
z
i
z
,
“
C
y
b
e
r
s
e
c
u
r
i
t
y
T
h
r
e
a
t
s d
e
t
e
c
t
i
o
n
u
s
i
n
g
o
p
t
i
mi
z
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
s
,
”
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
8
,
n
o
.
1
,
p
p
.
7
8
–
9
5
,
2
0
2
4
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
ss
e
.
2
0
2
3
.
0
3
9
2
6
5
.
[3
2
]
T.
I
g
e
,
C
.
K
i
e
k
i
n
t
v
e
l
d
,
a
n
d
A
.
P
i
p
l
a
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
sp
e
e
c
h
a
n
d
v
i
s
i
o
n
s
y
n
t
h
e
si
s
t
o
i
m
p
r
o
v
e
p
h
i
sh
i
n
g
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
a
mu
l
t
i
-
l
a
y
e
r
a
d
a
p
t
i
v
e
f
r
a
m
e
w
o
r
k
.
”
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s
/
2
4
0
2
.
1
7
2
4
9
[3
3
]
D
.
M
i
n
h
L
i
n
h
,
H
.
D
.
H
u
n
g
,
H
.
M
i
n
h
C
h
a
u
,
Q
.
S
y
V
u
,
a
n
d
T
.
-
N
.
Tr
a
n
,
“
R
e
a
l
-
t
i
me
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
s
b
y
e
x
t
e
n
s
i
o
n
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
4
,
n
o
.
3
,
p
.
3
0
2
1
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
3
0
2
1
-
3
0
3
5
.
[3
4
]
R
.
A
l
i
S
h
a
h
e
t
a
l
.
,
“
E
n
h
a
n
c
i
n
g
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
,
l
e
v
e
r
a
g
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
Ar
t
i
c
l
e
i
n
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
&
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
2
0
2
4
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
r
e
s
e
a
r
c
h
g
a
t
e
.
n
e
t
/
p
u
b
l
i
c
a
t
i
o
n
/
3
7
8
9
6
4
4
0
4
[3
5
]
R
.
Z
a
i
m
i
,
M
.
H
a
a
d
i
,
L.
M
a
h
n
a
n
e
,
M
.
H
a
f
i
d
i
,
a
n
d
M
.
L
a
mi
a
,
“
A
p
e
r
m
u
t
a
i
o
n
i
mp
o
r
t
a
n
c
e
b
a
se
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
met
h
o
d
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
t
o
d
e
t
e
c
t
p
h
i
s
h
i
n
g
w
e
b
si
t
e
s
.
”
F
e
b
.
1
3
,
2
0
2
4
.
d
o
i
:
1
0
.
2
1
2
0
3
/
r
s.3
.
r
s
-
3
9
4
3
0
4
9
/
v
1
.
[3
6
]
U
.
G
.
C
h
e
t
a
c
h
i
,
O
.
N
.
H
e
n
r
y
,
a
n
d
O
.
A
.
A
g
b
u
g
b
a
,
“
I
n
t
e
l
l
i
g
e
n
t
p
h
i
sh
i
n
g
w
e
b
s
i
t
e
d
e
t
e
c
t
i
o
n
m
o
d
e
l
p
o
w
e
r
e
d
b
y
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
Asi
a
n
J
o
u
r
n
a
l
o
f
Re
s
e
a
rc
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
7
1
–
8
5
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
9
7
3
4
/
a
j
r
c
o
s
/
2
0
2
4
/
v
1
7
i
1
4
1
4
.
[3
7
]
M
.
K
.
P
r
a
b
a
k
a
r
a
n
,
P
.
M
e
e
n
a
k
sh
i
S
u
n
d
a
r
a
m,
a
n
d
A
.
D
.
C
h
a
n
d
r
a
s
e
k
a
r
,
“
A
n
e
n
h
a
n
c
e
d
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
mec
h
a
n
i
sm
t
o
e
f
f
e
c
t
i
v
e
l
y
i
d
e
n
t
i
f
y
m
a
l
i
c
i
o
u
s
U
R
Ls
u
s
i
n
g
v
a
r
i
a
t
i
o
n
a
l
a
u
t
o
e
n
c
o
d
e
r
s,
”
I
ET
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
ri
t
y
,
v
o
l
.
1
7
,
n
o
.
3
,
p
p
.
4
2
3
–
4
4
0
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
4
9
/
i
se
2
.
1
2
1
0
6
.
[
38
]
S
.
S
.
R
o
y
,
A
.
I
.
A
w
a
d
,
L.
A
.
A
m
a
r
e
,
M
.
T
.
Er
k
i
h
u
n
,
a
n
d
M
.
A
n
a
s,
“
M
u
l
t
i
m
o
d
e
l
p
h
i
s
h
i
n
g
U
R
L
d
e
t
e
c
t
i
o
n
u
si
n
g
LST
M
,
b
i
d
i
r
e
c
t
i
o
n
a
l
LST
M
,
a
n
d
G
R
U
m
o
d
e
l
s,”
F
u
t
u
r
e
I
n
t
e
r
n
e
t
,
v
o
l
.
1
4
,
n
o
.
1
1
,
p
.
3
4
0
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
f
i
1
4
1
1
0
3
4
0
.
[
39
]
H
.
A
l
q
a
h
t
a
n
i
e
t
a
l
.
,
“
E
v
o
l
u
t
i
o
n
a
r
y
a
l
g
o
r
i
t
h
m w
i
t
h
d
e
e
p
a
u
t
o
e
n
c
o
d
e
r
n
e
t
w
o
r
k
b
a
se
d
w
e
b
si
t
e
p
h
i
sh
i
n
g
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
,”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
1
5
,
p
.
7
4
4
1
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
5
7
4
4
1
.
[4
0
]
M
.
El
sa
d
i
g
e
t
a
l
.
,
“
I
n
t
e
l
l
i
g
e
n
t
d
e
e
p
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
y
b
e
r
p
h
i
s
h
i
n
g
U
R
L
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
B
E
R
T
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
i
o
n
,
”
El
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
2
2
,
p
.
3
6
4
7
,
N
o
v
.
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
2
2
3
6
4
7
.
[4
1
]
N
.
Q
.
D
o
,
A
.
S
e
l
a
ma
t
,
O
.
K
r
e
j
c
a
r
,
E.
H
e
r
r
e
r
a
-
V
i
e
d
m
a
,
a
n
d
H
.
F
u
j
i
t
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
:
t
a
x
o
n
o
my
,
c
u
r
r
e
n
t
c
h
a
l
l
e
n
g
e
s a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s
,”
I
E
E
E
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
3
6
4
2
9
–
3
6
4
6
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
2
.
3
1
5
1
9
0
3
.
[4
2
]
M
.
A
l
m
o
u
sa
,
T.
Z
h
a
n
g
,
A
.
S
a
r
r
a
f
z
a
d
e
h
,
a
n
d
M
.
A
n
w
a
r
,
“
P
h
i
s
h
i
n
g
w
e
b
si
t
e
d
e
t
e
c
t
i
o
n
:
h
o
w
e
f
f
e
c
t
i
v
e
a
r
e
d
e
e
p
l
e
a
r
n
i
n
g
‐
b
a
s
e
d
mo
d
e
l
s
a
n
d
h
y
p
e
r
p
a
r
a
m
e
t
e
r
o
p
t
i
m
i
z
a
t
i
o
n
?
,
”
S
e
c
u
ri
t
y
a
n
d
Pr
i
v
a
c
y
,
v
o
l
.
5
,
n
o
.
6
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
s
p
y
2
.
2
5
6
.
[4
3
]
S
.
A
l
-
A
h
m
a
d
i
a
n
d
Y
.
A
l
h
a
r
b
i
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
f
o
r
w
e
b
p
h
i
sh
i
n
g
d
e
t
e
c
t
i
o
n
c
o
m
b
i
n
e
d
U
R
L
f
e
a
t
u
r
e
s
a
n
d
v
i
s
u
a
l
si
mi
l
a
r
i
t
y
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
j
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
N
e
t
w
o
r
k
s
&
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
,
n
o
.
5
,
p
p
.
4
1
–
5
4
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
5
1
2
1
/
i
j
c
n
c
.
2
0
2
0
.
1
2
5
0
3
.
[4
4
]
Z.
A
l
sh
i
n
g
i
t
i
,
R
.
A
l
a
q
e
l
,
J
.
A
l
-
M
u
h
t
a
d
i
,
Q
.
E
.
U
.
H
a
q
,
K
.
S
a
l
e
e
m,
a
n
d
M
.
H
.
F
a
h
e
e
m,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
sy
st
e
m
u
si
n
g
C
N
N
,
LS
TM
,
a
n
d
LSTM
-
C
N
N
,
”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
2
3
2
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
2
0
1
0
2
3
2
.
[4
5
]
A
.
G
ó
m
e
z
a
n
d
A
.
M
u
ñ
o
z
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
a
n
d
r
o
i
d
d
e
v
i
c
e
s
,
”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
1
5
,
p
.
3
2
5
3
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
1
5
3
2
5
3
.
[4
6
]
B
.
W
e
i
e
t
a
l
.
,
“
A
d
e
e
p
-
l
e
a
r
n
i
n
g
-
d
r
i
v
e
n
l
i
g
h
t
-
w
e
i
g
h
t
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
s
e
n
so
r
,
”
S
e
n
so
r
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
9
,
n
o
.
1
9
,
p
.
4
2
5
8
,
S
e
p
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
1
9
4
2
5
8
.
[
47
]
P
.
Y
i
,
Y
.
G
u
a
n
,
F
.
Zo
u
,
Y
.
Y
a
o
,
W
.
W
a
n
g
,
a
n
d
T
.
Z
h
u
,
“
W
e
b
p
h
i
sh
i
n
g
d
e
t
e
c
t
i
o
n
u
s
i
n
g
a
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
,
”
Wi
re
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
M
o
b
i
l
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
1
8
,
n
o
.
1
,
Ja
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
8
/
4
6
7
8
7
4
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ms.
Pre
e
ti
M
.
Tec
h
.
,
P
h
.
D
.
P
u
rsu
in
g
fr
o
m
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s,
M
.
D.
Un
i
v
e
rsity
,
Ro
h
tak
.
S
h
e
h
a
s
p
u
b
l
ish
e
d
m
o
r
e
th
a
n
1
6
p
u
b
li
c
a
ti
o
n
s
i
n
v
a
rio
u
s
j
o
u
r
n
a
ls
/
m
a
g
a
z
in
e
s
o
f
n
a
ti
o
n
a
l
a
n
d
in
ter
n
a
ti
o
n
a
l
re
p
u
te.
H
e
r
a
re
a
o
f
re
se
a
r
c
h
in
c
lu
d
e
s
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
i
n
g
,
a
n
d
c
y
b
e
r
se
c
u
rit
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
isk
h
o
k
h
a
r1
2
1
@
g
m
a
il
.
c
o
m
.
Dr
.
Priti
S
h
a
r
m
a
M
CA,
P
h
.
D
.
(
c
o
m
p
u
te
sc
i
e
n
c
e
)
is
wo
rk
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s,
M
.
D.
Un
iv
e
rsit
y
,
R
o
h
tak
.
S
h
e
h
a
s
p
u
b
l
ish
e
d
m
o
re
t
h
a
n
6
0
p
u
b
li
c
a
ti
o
n
s
in
v
a
ri
o
u
s
jo
u
rn
a
ls
/ma
g
a
z
in
e
s
o
f
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
re
p
u
te.
S
h
e
is
e
n
g
a
g
e
d
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
fro
m
th
e
las
t
1
5
y
e
a
rs.
He
r
a
re
a
o
f
re
se
a
rc
h
in
c
l
u
d
e
s
d
a
ta
m
in
i
n
g
,
b
i
g
d
a
ta,
so
ftwa
re
e
n
g
in
e
e
rin
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
e
e
p
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
rit
i@m
d
u
r
o
h
tak
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.