I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
,
p
p
.
9
9
7
~
1
0
0
5
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
1
.
pp
9
9
7
-
1005
997
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Dete
c
ting
m
a
licio
us URLs
using
bi
na
ry
clas
sifica
tion throug
h
a
da
boo
st alg
o
rith
m
F
iro
z
K
ha
n
1
, J
ines
h Aha
m
e
d
2
,
Seif
edine K
a
dry
3
,
L
a
k
s
h
m
a
na
K
u
m
a
r
Ra
m
a
s
a
m
y
4
1,
2
Co
m
p
u
ter In
f
o
rm
a
ti
o
n
S
c
ien
c
e
De
p
a
rtme
n
t,
Hig
h
e
r
Co
ll
e
g
e
s o
f
T
e
c
h
n
o
lo
g
y
,
U
A
E
3
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s an
d
Co
m
p
u
t
e
r
S
c
ien
c
e
,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
,
Be
iru
t
A
ra
b
Un
iv
e
rsity
,
L
e
b
a
n
o
n
4
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter A
p
p
li
c
a
ti
o
n
s,
Hi
n
d
u
sth
a
n
Co
l
leg
e
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
1
4
,
2
0
1
9
R
ev
i
s
ed
J
u
n
2
9
,
2019
A
cc
ep
ted
Sep
2
7
,
2
0
1
9
M
a
li
c
io
u
s
Un
if
o
rm
Re
so
u
rc
e
L
o
c
a
to
r
(URL
)
is
a
f
re
q
u
e
n
t
a
n
d
se
v
e
re
m
e
n
a
c
e
to
c
y
b
e
rse
c
u
rit
y
.
M
a
li
c
io
u
s
URLs
a
re
u
se
d
to
e
x
trac
t
u
n
so
l
icited
i
n
f
o
rm
a
ti
o
n
a
n
d
tri
c
k
in
e
x
p
e
rien
c
e
d
e
n
d
u
se
rs
a
s
a
su
f
fe
re
r
o
f
sc
a
m
s
a
n
d
c
re
a
te
lo
ss
e
s
o
f
b
il
li
o
n
s
o
f
m
o
n
e
y
e
a
c
h
y
e
a
r.
I
t
is
c
ru
c
ial
to
id
e
n
ti
fy
a
n
d
a
p
p
ro
p
riate
ly
re
sp
o
n
d
to
s
u
c
h
URL
s.
Us
u
a
ll
y
,
th
is
d
isc
o
v
e
ry
is
m
a
d
e
b
y
th
e
p
ra
c
ti
c
e
a
n
d
u
se
o
f
b
lac
k
li
sts
in
th
e
c
y
b
e
r
w
o
rld
.
Ho
w
e
v
e
r,
b
lac
k
li
sts
c
a
n
n
o
t
b
e
e
x
h
a
u
stiv
e
,
a
n
d
c
a
n
n
o
t
re
c
o
g
n
ize
z
e
ro
-
d
a
y
m
a
li
c
io
u
s
URL
s.
S
o
to
i
n
c
re
a
se
th
e
o
b
se
rv
a
ti
o
n
o
f
m
a
li
c
io
u
s
URL
in
d
ica
to
rs,
m
a
c
h
in
e
lea
rn
in
g
p
ro
c
e
d
u
re
s
sh
o
u
l
d
b
e
i
n
c
o
rp
o
ra
ted
.
In
th
i
s
stu
d
y
,
w
e
h
a
v
e
d
e
v
e
lo
p
e
d
a
c
o
m
p
lete
p
ro
t
o
ty
p
e
o
f
M
a
li
c
io
u
s
URL
D
e
tec
ti
o
n
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
s.
In
p
a
rti
c
u
lar,
w
e
h
a
v
e
a
tt
e
m
p
te
d
a
n
e
x
a
c
t
f
o
r
m
u
latio
n
o
f
M
a
li
c
io
u
s
URL
e
x
p
o
su
re
f
ro
m
a
m
a
c
h
in
e
lea
rn
i
n
g
p
e
rsp
e
c
ti
v
e
a
n
d
p
ro
p
o
se
d
a
n
a
p
p
r
o
a
c
h
u
sin
g
th
e
A
d
a
Bo
o
st
a
lg
o
rit
h
m
-
th
e
p
ro
p
o
se
d
a
p
p
r
o
a
c
h
h
a
s
b
r
o
u
g
h
t
f
o
rw
a
rd
m
o
re
a
c
c
u
ra
c
y
th
a
n
o
th
e
r
e
x
isti
n
g
a
lg
o
rit
h
m
s
.
K
ey
w
o
r
d
s
:
A
d
aB
o
o
s
t a
lg
o
r
ith
m
B
in
ar
y
clas
s
i
f
icatio
n
p
r
o
b
le
m
B
lack
lis
t
s
Ma
ch
i
n
e
lear
n
i
n
g
Ma
licio
u
s
u
n
if
o
r
m
r
e
s
o
u
r
ce
lo
ca
to
r
Co
p
y
rig
h
t
©
2
0
2
0
I
n
stit
u
te o
f
Ad
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Seif
ed
i
n
e
Kad
r
y
,
Dep
ar
t
m
en
t o
f
M
ath
e
m
at
ics a
n
d
C
o
m
p
u
ter
Scien
ce
,
B
eir
u
t A
r
ab
Un
iv
er
s
it
y
,
B
eir
u
t,
L
eb
an
o
n
.
E
m
ail: s.
k
ad
r
y
@
b
au
.
ed
u
.
lb
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ar
r
iv
al
o
f
m
o
d
er
n
in
telli
g
en
ce
tec
h
n
o
lo
g
ies
b
r
i
n
g
s
a
n
en
o
r
m
o
u
s
in
f
l
u
e
n
ce
i
n
t
h
e
in
cr
ea
s
e
an
d
ad
v
an
ce
m
en
t
o
f
m
ar
k
ets
o
v
er
s
ev
er
al
ap
p
licatio
n
s
.
I
n
th
e
c
u
r
r
en
t
a
g
e,
it
is
n
ea
r
l
y
m
an
d
ato
r
y
f
o
r
an
o
r
g
an
izatio
n
to
h
a
v
e
an
o
n
l
in
e
p
r
esen
ce
to
h
a
v
e
a
s
u
cc
es
s
f
u
l
an
d
p
r
o
s
p
er
o
u
s
en
ter
p
r
is
e.
As
a
co
n
s
eq
u
en
ce
,
th
e
in
co
r
p
o
r
atio
n
o
f
th
e
W
o
r
ld
W
id
e
W
e
b
an
d
I
n
ter
n
et
in
to
th
e
o
p
er
atio
n
s
o
f
t
h
e
o
r
g
an
izatio
n
b
ec
o
m
e
s
ess
e
n
tial.
R
eg
r
ettab
l
y
,
th
e
tec
h
n
o
lo
g
ical
p
r
o
g
r
ess
io
n
s
co
m
e
w
i
th
s
ec
u
r
i
t
y
i
s
s
u
es
th
a
t
ar
e
u
s
ed
to
tr
ic
k
an
d
s
ca
m
en
d
u
s
er
s
.
S
u
ch
attac
k
s
co
n
s
i
s
t
o
f
il
leg
al
w
eb
s
ite
s
t
h
at
m
ar
k
et
f
o
r
g
ed
g
o
o
d
s
,
co
m
m
er
cial
f
r
au
d
co
n
d
u
cted
b
y
ch
ea
t
in
g
u
s
er
s
i
n
to
s
h
ar
in
g
d
elica
te
d
ata
w
it
h
th
e
u
lti
m
ate
ai
m
to
s
teal
m
o
n
e
y
o
r
id
en
tific
atio
n
,
o
r
also
p
lan
tin
g
a
b
ad
p
iece
o
f
co
d
e,
m
al
w
ar
e,
in
t
h
e
u
s
er
’
s
m
ac
h
in
e.
As
th
er
e
ar
e
a
d
iv
er
s
e
v
ar
iet
y
o
f
attac
k
s
p
o
s
s
ib
le,
an
d
th
e
v
ar
io
u
s
co
n
t
ex
ts
i
n
w
h
ic
h
s
u
ch
attac
k
s
ca
n
ar
is
e,
it
is
d
if
f
ic
u
lt
to
i
n
v
e
n
t
r
o
b
u
s
t
o
p
er
atio
n
s
to
id
en
ti
f
y
c
y
b
er
-
s
ec
u
r
it
y
cr
i
m
e
s
.
T
h
e
b
o
u
n
d
ar
ies
o
f
co
n
v
e
n
tio
n
al
s
ec
u
r
it
y
a
d
m
i
n
is
tr
atio
n
tech
n
o
lo
g
ie
s
ar
e
g
r
o
w
i
n
g
m
o
r
e
p
r
o
f
o
u
n
d
an
d
a
d
d
r
ess
in
g
th
i
s
ex
p
o
n
e
n
tia
l
in
c
r
ea
s
e
o
f
cu
r
r
en
t
s
ec
u
r
it
y
m
e
n
a
ce
s
w
it
h
th
e
h
elp
o
f
ac
ce
ler
ated
ad
v
an
ce
s
in
m
o
d
e
r
n
I
T
tech
n
o
lo
g
ie
s
.
Ho
w
ev
er
,
th
er
e
is
a
n
o
tab
le
d
e
f
icit
o
f
s
ec
u
r
it
y
s
p
ec
ial
is
t
s
w
h
o
ca
n
a
d
d
r
ess
t
h
is
s
i
g
n
if
ic
an
t
co
n
ce
r
n
.
T
h
e
m
o
s
t
s
ig
n
i
f
i
ca
n
t
o
f
t
h
ese
a
ttack
in
g
m
eth
o
d
s
ar
e
id
en
tif
ied
b
y
in
cr
ea
s
i
n
g
co
m
p
r
o
m
is
ed
U
R
L
s
[
1
]
.
UR
L
is
t
h
e
ac
r
o
n
y
m
o
f
U
n
i
f
o
r
m
R
e
s
o
u
r
ce
L
o
ca
to
r
,
w
h
ic
h
s
i
g
n
i
f
ie
s
th
e
U
n
i
v
er
s
al
lo
ca
tio
n
o
f
r
ec
o
r
d
s
an
d
o
th
er
s
o
u
r
ce
s
o
n
t
h
e
W
o
r
ld
W
id
e
W
eb
.
I
t
h
as
t
w
o
p
r
in
cip
al
ele
m
e
n
ts
:
(
i)
p
r
o
to
c
o
l
id
en
tifie
r
,
an
d
it
s
y
m
b
o
lizes
w
h
a
t
r
u
les
to
ap
p
l
y
,
(
ii)
r
eso
u
r
ce
n
a
m
e,
it
d
ef
i
n
es
t
h
e
I
P
ad
d
r
ess
o
r
th
e
d
o
m
ai
n
n
a
m
e
w
h
er
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
9
9
7
-
1005
998
th
e
s
o
u
r
ce
is
s
i
tu
ated
.
A
co
lo
n
an
d
t
w
o
f
o
r
w
ar
d
s
las
h
es
s
ep
ar
ate
th
e
p
r
o
to
co
l
id
en
tif
i
er
an
d
th
e
r
eso
u
r
ce
n
a
m
e.
A
s
a
m
p
le
i
s
d
is
p
la
y
ed
i
n
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
Un
i
f
o
r
m
r
eso
u
r
ce
lo
ca
to
r
R
esear
ch
h
a
s
f
o
u
n
d
th
a
t
n
e
ar
l
y
o
n
e
-
t
h
ir
d
o
f
all
s
ite
s
a
r
e
p
r
o
b
a
b
ly
m
al
icio
u
s
[
2
]
,
co
n
f
ir
m
i
n
g
a
s
ig
n
if
ican
t
u
s
e
o
f
m
al
icio
u
s
UR
L
s
to
p
er
f
o
r
m
c
y
b
er
-
cr
i
m
es.
A
UR
L
o
f
a
m
alic
io
u
s
w
e
b
s
ite
in
co
r
p
o
r
ates
s
o
m
e
t
y
p
e
o
f
f
r
ee
in
f
o
r
m
a
tio
n
to
attr
ac
t
e
n
d
u
s
er
s
u
s
i
n
g
s
p
am
,
p
h
is
h
i
n
g
,
o
r
d
r
iv
e
-
by
-
e
x
p
lo
its
to
o
r
ig
i
n
ate
attac
k
s
.
I
n
n
o
ce
n
t
en
d
u
s
er
s
n
a
v
ig
a
te
t
h
e
w
eb
s
ite
s
a
n
d
t
h
en
g
ets
v
ic
ti
m
ized
u
s
i
n
g
s
e
v
er
al
k
in
d
s
o
f
s
ca
m
s
a
n
d
m
al
w
ar
e.
Mo
d
er
n
ar
c
h
et
y
p
e
s
o
f
cr
i
m
es
p
r
ac
tici
n
g
m
alicio
u
s
UR
L
s
i
n
co
r
p
o
r
ate
Dr
iv
e
-
b
y
Do
w
n
lo
ad
,
P
h
is
h
in
g
an
d
So
cial
E
n
g
i
n
ee
r
in
g
,
an
d
Sp
am
[
3
]
.
Dr
iv
e
-
by
-
d
o
w
n
lo
ad
[
4
]
is
d
ef
in
ed
as
th
e
ac
cid
en
tal
d
o
w
n
lo
ad
o
f
m
a
l
w
ar
e
b
y
s
e
n
s
in
g
a
U
R
L
.
T
h
ese
attac
k
s
ar
e
t
y
p
icall
y
c
o
n
d
u
cted
b
y
e
m
p
lo
y
i
n
g
v
u
l
n
e
r
ab
ilit
ies
as
ad
d
-
o
n
s
o
r
in
j
ec
tin
g
a
m
alicio
u
s
p
i
ec
e
o
f
s
o
f
t
w
ar
e
w
r
itten
i
n
J
av
aScr
ip
t.
P
h
is
h
in
g
a
n
d
So
cial
E
n
g
i
n
ee
r
i
n
g
in
ter
v
e
n
tio
n
s
[
5
]
f
o
o
l
th
e
en
d
u
s
er
s
b
y
m
ak
i
n
g
th
e
m
e
x
c
h
an
g
e
p
er
s
o
n
al
o
r
s
en
s
iti
v
e
d
ata
b
y
r
ep
r
esen
tin
g
to
b
e
r
ea
l
w
eb
p
ag
es.
Sp
a
m
is
th
e
p
r
ef
er
r
ed
m
et
h
o
d
o
f
v
o
lu
n
teer
ed
co
m
m
u
n
icatio
n
s
u
s
ed
b
y
cr
i
m
i
n
als
to
p
r
o
m
o
te
th
ese
attac
k
s
o
r
co
n
d
u
ct
p
h
is
h
in
g
.
T
h
ese
k
i
n
d
s
o
f
cr
i
m
es
h
ap
p
en
in
m
a
s
s
i
v
e
a
m
o
u
n
ts
an
d
h
av
e
p
r
o
d
u
ce
d
b
illi
o
n
s
o
f
m
o
n
e
tar
y
v
al
u
e
o
f
lo
s
s
ea
c
h
y
ea
r
.
E
f
f
icie
n
t
p
r
ac
ti
ce
s
to
id
en
tify
s
u
ch
m
al
icio
u
s
UR
L
s
o
n
ti
m
e
ca
n
ef
f
ec
tiv
e
l
y
s
u
p
p
o
r
t
to
id
en
ti
f
y
a
s
u
b
s
tan
tial
a
m
o
u
n
t
o
f
a
n
d
a
k
i
n
d
o
f
c
y
b
er
-
s
ec
u
r
it
y
war
n
in
g
s
.
I
n
p
ar
allel,
r
esear
ch
er
s
an
d
p
r
ac
titi
o
n
er
s
h
av
e
ac
ted
o
n
d
ev
is
i
n
g
p
o
s
s
ib
le
r
eso
lu
tio
n
s
f
o
r
Ma
licio
u
s
UR
L
Dete
ctio
n
.
T
h
e
r
est
o
f
th
is
ar
ticle
is
o
r
g
an
ized
as
f
o
llo
w
s
.
Sectio
n
2
d
escr
ib
es
th
e
w
o
r
k
ca
r
r
ied
o
u
t
b
y
a
f
e
w
r
esear
ch
er
s
.
Sectio
n
3
o
u
tlin
e
s
o
u
r
m
e
th
o
d
o
lo
g
y
f
o
r
s
o
lv
in
g
th
e
m
a
licio
u
s
class
i
f
icatio
n
.
T
h
e
ex
p
er
i
m
en
ta
l
o
u
tc
o
m
es a
r
e
p
u
t
f
o
r
th
i
n
Sect
io
n
4
.
C
o
n
clu
d
i
n
g
r
e
m
ar
k
s
is
i
n
clu
d
ed
in
Sectio
n
5
.
2.
RE
L
AT
E
D
WO
RK
T
h
e
u
s
u
al
s
ta
n
d
ar
d
w
a
y
to
id
en
ti
f
y
m
alicio
u
s
UR
L
s
b
y
v
a
r
io
u
s
an
ti
v
ir
u
s
s
o
f
t
w
ar
e
is
th
e
b
lack
lis
t
ap
p
r
o
ac
h
.
A
ll
ar
e
p
r
in
cip
all
y
a
r
ep
o
s
ito
r
y
o
f
U
R
L
s
t
h
at
h
av
e
b
ee
n
v
er
i
f
ied
to
b
e
m
a
licio
u
s
i
n
h
is
to
r
y
.
T
h
is
co
llectio
n
is
v
er
if
ied
ac
r
o
s
s
ti
m
e
a
n
d
u
s
ed
to
tr
ac
k
if
th
e
UR
L
i
s
d
an
g
er
o
u
s
.
S
u
ch
a
s
y
s
te
m
i
s
f
a
s
t
b
y
b
eh
av
io
r
b
ec
au
s
e
o
f
i
ts
s
i
m
p
le
q
u
er
y
co
s
t
a
n
d
t
h
er
ef
o
r
e
is
v
er
y
s
i
m
p
le
to
ex
ec
u
te
.
Mo
r
eo
v
er
,
s
u
ch
a
p
r
o
ce
d
u
r
e
w
o
u
ld
p
r
o
d
u
ce
m
in
i
m
al
f
alse
-
p
o
s
iti
v
e
r
ates
(
E
v
en
th
o
u
g
h
it
h
a
s
b
ee
n
f
o
u
n
d
th
at
u
s
u
all
y
b
lack
lis
t
in
g
ca
n
e
n
d
u
r
e
n
o
n
-
t
r
iv
ial
f
a
ls
e
-
p
o
s
iti
v
e
r
ates
[
6
,
7
]
)
.
Ho
w
e
v
er
,
it
i
s
n
ea
r
l
y
i
m
p
r
o
b
a
b
le
to
k
ee
p
an
ex
h
a
u
s
tiv
e
r
ec
o
r
d
o
f
m
alicio
u
s
U
R
L
s
,
p
ar
tic
u
lar
l
y
f
o
r
d
is
ti
n
ct
U
R
L
s
w
h
ic
h
ar
e
cr
ea
ted
r
eg
u
lar
l
y
.
C
r
i
m
i
n
als
co
m
e
u
p
w
it
h
i
n
v
en
tiv
e
w
a
y
s
to
av
o
id
b
lac
k
lis
ts
a
n
d
tr
ic
k
en
d
u
s
er
s
b
y
alter
i
n
g
t
h
e
UR
L
to
lo
o
k
a
u
t
h
en
t
ic.
Gar
er
a
et
a
l.
[
8
]
h
av
e
class
i
f
i
ed
f
o
u
r
k
in
d
s
o
f
o
b
f
u
s
ca
tio
n
:
Ob
f
u
s
ca
tin
g
t
h
e
O
w
n
er
b
y
a
n
I
P
,
Ob
f
u
s
ca
ti
n
g
th
e
Ho
s
t
w
i
th
a
d
i
f
f
er
en
t
d
o
m
ain
,
Ob
f
u
s
ca
ti
n
g
t
h
e
h
o
s
t
w
it
h
g
r
ea
t
h
o
s
t
n
a
m
es,
an
d
m
i
s
s
p
el
lin
g
.
E
ac
h
o
f
t
h
ese
m
et
h
o
d
s
tr
ies to
co
n
ce
al
th
e
m
alicio
u
s
p
u
r
p
o
s
es o
f
th
e
w
eb
s
i
te
b
y
h
id
in
g
t
h
e
m
a
licio
u
s
UR
L
.
I
n
th
e
cu
r
r
en
t
n
e
w
tr
en
d
an
d
th
e
ex
p
an
d
i
n
g
d
e
m
a
n
d
o
f
UR
L
s
h
o
r
te
n
i
n
g
s
er
v
ices,
a
u
n
iq
u
e
an
d
co
m
p
r
e
h
en
s
iv
e
o
b
f
u
s
ca
tio
n
m
eth
o
d
is
b
ein
g
o
b
s
er
v
ed
[
9
,
1
0
]
.
I
f
th
e
UR
L
s
s
ee
m
r
eliab
le,
an
d
en
d
u
s
er
tr
u
s
ts
th
e
UR
L
,
a
n
attac
k
ca
n
b
e
s
tar
ted
.
Usu
all
y
,
t
h
e
cr
i
m
in
al
s
w
il
l
f
u
r
th
er
atte
m
p
t
to
co
n
f
u
s
e
th
e
co
d
e
to
lim
i
t
s
ig
n
at
u
r
e
-
b
ased
m
ec
h
a
n
i
s
m
s
f
r
o
m
e
x
p
o
s
in
g
t
h
e
m
.
C
r
i
m
in
al
s
d
o
s
ev
er
al
ad
d
itio
n
al
r
o
u
tin
es
to
av
o
id
b
lack
lis
t
s
th
r
o
u
g
h
w
h
ich
p
r
o
x
y
s
er
v
er
s
ar
e
au
to
m
atica
ll
y
f
o
r
m
ed
to
h
o
s
t
th
e
w
eb
-
p
a
g
e
.
Mo
r
eo
v
er
,
attac
k
er
s
u
s
u
a
ll
y
b
eg
in
f
u
r
t
h
er
attac
k
s
,
w
h
ich
ch
an
g
es
t
h
e
attac
k
-
s
i
g
n
a
tu
r
e,
m
ak
in
g
it
u
n
tr
ac
ea
b
le
b
y
d
ev
ices
th
at
d
ir
ec
t
o
n
p
ar
ticu
lar
s
i
g
n
atu
r
e
s
.
B
lack
li
s
t
in
g
s
y
s
te
m
s
h
av
e
r
ig
id
b
o
u
n
d
a
r
ies,
an
d
i
t
s
ee
m
s
r
elev
a
n
t
to
a
v
o
id
th
e
m
,
m
o
s
t
l
y
b
ec
au
s
e
b
lack
li
s
ts
ar
e
w
o
r
th
le
s
s
f
o
r
g
a
in
i
n
g
f
o
r
ec
ast
s
o
n
d
is
t
in
ct
U
R
L
s
T
h
e
r
esear
ch
er
s
Fo
s
s
i
et
al.
,
h
av
e
d
ev
elo
p
ed
an
ex
te
n
s
i
v
e
co
llectio
n
o
f
g
lo
b
al
th
r
ea
ts
th
at
co
v
er
s
co
r
p
o
r
ate
d
ata
g
ap
s
,
attac
k
s
o
n
b
r
o
w
s
er
s
an
d
w
eb
s
ites
,
s
p
ea
r
p
h
is
h
i
n
g
atte
m
p
ts
,
r
an
s
o
m
w
ar
e
an
d
d
if
f
er
en
t
k
in
d
s
o
f
f
r
au
d
u
len
t
c
y
b
er
ac
tio
n
s
[
1
1
]
.
T
h
e
r
esear
ch
also
r
e
v
ea
ls
r
ar
e
cy
b
er
s
k
ills
p
r
ac
tice
d
b
y
th
e
s
ca
m
m
er
s
.
On
e
ef
f
icie
n
t
p
r
o
ce
d
u
r
e
is
ch
ar
g
in
g
t
h
e
u
s
er
s
to
click
o
n
a
m
alicio
u
s
Un
if
o
r
m
R
eso
u
r
ce
L
o
ca
to
r
(
UR
L
)
,
w
h
ic
h
th
e
n
m
ak
e
s
t
h
e
s
y
s
te
m
ar
b
itra
ted
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Dete
ctin
g
ma
licio
u
s
UR
Ls
u
s
i
n
g
b
in
a
r
y
cla
s
s
ifica
tio
n
th
r
o
u
g
h
a
d
a
b
o
o
s
t a
lg
o
r
ith
m
(
F
ir
o
z
K
h
a
n
)
999
T
h
e
w
eb
s
ec
u
r
i
t
y
g
r
o
u
p
h
a
s
b
eg
u
n
b
lac
k
li
s
ti
n
g
s
er
v
ices
to
f
in
d
m
alicio
u
s
w
eb
s
ite
s
.
T
h
ese
b
lack
li
s
ts
ar
e
f
o
r
m
ed
b
y
u
s
in
g
m
u
l
tip
le
co
llectio
n
s
o
f
s
y
s
te
m
s
i
n
cl
u
d
in
g
m
a
n
u
a
l r
ep
o
r
tin
g
,
h
o
n
e
y
p
o
ts
,
an
d
w
eb
cr
a
w
ler
s
u
n
i
ted
w
it
h
lo
ca
lit
y
in
v
es
t
ig
at
io
n
[
1
2
-
13
]
.
W
h
ile
UR
L
b
lack
lis
tin
g
h
a
s
r
e
m
ai
n
ed
s
atis
f
ac
to
r
y
to
an
y
s
p
ac
e,
it
is
r
ea
s
o
n
ab
l
y
s
tr
aig
h
t
f
o
r
war
d
f
o
r
an
in
tr
u
d
er
to
f
o
o
l
th
e
s
y
s
te
m
b
y
li
g
h
tl
y
tr
a
n
s
f
o
r
m
in
g
o
n
e
o
r
m
o
r
e
ele
m
e
n
ts
o
f
t
h
e
UR
L
s
eq
u
e
n
c
e.
Fu
r
th
er
m
o
r
e,
s
e
v
er
al
m
al
ici
o
u
s
s
ite
s
ar
e
n
o
t
b
lack
lis
ted
b
ec
au
s
e
t
h
e
y
ar
e
to
o
n
e
w
o
r
w
er
e
w
r
o
n
g
l
y
as
s
es
s
ed
.
Stu
d
ies
co
n
d
u
cted
h
i
s
to
r
icall
y
ca
n
b
e
u
s
ed
to
co
n
f
ir
m
t
h
is
q
u
er
y
f
r
o
m
a
Ma
ch
in
e
L
ea
r
n
i
n
g
v
ie
w
p
o
in
t.
T
h
at
is
,
p
eo
p
le
co
llect
a
r
ec
o
r
d
o
f
UR
L
s
th
at
h
a
v
e
r
e
m
ai
n
ed
ca
teg
o
r
ized
as
eith
er
m
alic
io
u
s
o
r
f
a
v
o
r
ab
le
an
d
d
escr
ib
e
s
p
ec
if
ic
U
R
L
th
r
o
u
g
h
a
s
et
o
f
ch
ar
ac
ter
i
s
tics
.
C
las
s
i
f
icatio
n
alg
o
r
ith
m
s
ar
e
th
e
n
r
eq
u
ir
ed
to
d
ete
r
m
i
n
e
th
e
li
n
e
b
etw
ee
n
th
e
d
ec
is
io
n
s
et
s
.
T
h
e
au
th
o
r
s
class
if
ied
th
e
u
n
d
is
co
v
er
ed
m
a
licio
u
s
W
eb
s
ites
b
y
e
m
p
lo
y
i
n
g
t
h
e
ch
ar
ac
te
r
is
tics
o
f
t
h
e
n
et
w
o
r
k
ad
d
r
ess
[
14
-
15
]
.
T
h
e
m
o
ti
v
e
[
16
-
1
7]
o
f
th
is
r
e
s
ea
r
ch
is
to
an
al
y
ze
m
alicio
u
s
w
eb
s
i
tes
o
f
g
o
o
d
o
n
es
f
r
o
m
t
h
eir
UR
L
f
ea
t
u
r
es.
T
h
r
o
u
g
h
f
ea
tu
r
e
s
elec
tio
n
r
el
atin
g
to
P
ar
eto
GA
,
th
e
y
d
eli
v
er
ed
m
o
r
e
p
r
ec
is
io
n
an
d
F
-
s
co
r
e
w
ith
t
h
e
m
o
s
t
li
m
i
ted
a
m
o
u
n
t o
f
f
ea
t
u
r
es.
I
n
[
1
8
]
,
th
e
au
t
h
o
r
s
s
u
g
g
es
ted
a
s
o
lu
tio
n
to
o
v
er
co
m
e
th
e
p
r
o
b
lem
o
f
e
m
b
ed
d
i
n
g
m
al
w
ar
e
p
r
o
g
r
am
s
in
th
e
U
R
L
s
b
y
Ma
c
h
i
n
e
L
ea
r
n
in
g
.
T
h
e
au
t
h
o
r
s
[
1
9
]
,
m
ad
e
th
e
co
n
v
er
s
atio
n
o
n
t
h
e
ex
p
lo
r
ato
r
y
attac
k
,
w
h
ich
d
ec
eiv
es
th
e
j
u
d
g
m
e
n
t
o
f
t
h
e
class
i
f
ier
o
n
th
e
m
alicio
u
s
u
n
its
.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
ed
a
m
o
d
el
p
er
ce
iv
ed
as
th
e
attac
k
m
o
d
el,
w
h
ich
i
s
p
r
ac
tis
ed
to
attac
k
th
e
d
etec
tio
n
s
y
s
te
m
u
ti
lizin
g
S
u
p
p
o
r
t
V
ec
to
r
Ma
ch
in
e
an
d
Fis
h
er
Dis
cr
i
m
in
a
n
t
C
las
s
if
ier
.
I
n
[
2
0
]
,
th
e
w
o
r
k
w
as
p
er
f
o
r
m
ed
b
y
th
e
au
th
o
r
s
to
h
o
ld
th
e
s
p
a
m
ac
tio
n
an
d
f
u
r
t
h
er
to
r
e
m
o
v
e
t
h
e
s
p
a
m
co
n
ten
t a
n
d
m
alic
io
u
s
UR
L
s
i
n
E
m
ail.
T
h
e
y
h
a
v
e
p
r
ac
tis
ed
d
a
ta
m
i
n
i
n
g
ap
p
r
o
ac
h
,
w
h
ic
h
in
cr
ea
s
e
s
t
h
e
ef
f
icie
n
c
y
o
f
t
h
e
s
y
s
te
m
a
n
d
id
en
ti
f
i
es
m
o
r
e
v
o
l
u
m
e
o
f
s
p
a
m
an
d
m
a
licio
u
s
UR
L
s
.
DOS
attac
k
i
s
a
n
e
f
f
o
r
t
co
n
ce
iv
ed
b
y
t
h
e
in
tr
u
d
er
to
r
ef
u
s
e
s
er
v
ice
to
th
e
u
s
er
.
I
t
is
a
n
i
n
itiati
v
e
t
h
at
f
lo
o
d
s
th
e
v
icti
m
s
y
s
te
m
w
i
th
tr
af
f
i
c
tr
an
s
m
it
tin
g
m
alic
io
u
s
in
f
o
r
m
atio
n
w
h
ic
h
m
a
y
h
it
th
e
s
y
s
te
m
.
T
h
e
a
u
th
o
r
s
ap
p
lied
s
u
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
an
d
C
4
.
5
o
n
NSL_
KDD
Data
s
et
f
o
r
b
en
ef
icia
l
clas
s
i
f
icatio
n
o
f
D
OS
A
ttac
k
[
2
1
]
.
T
h
u
s
,
it
is
n
ec
es
s
ar
y
to
d
ev
elo
p
a
m
et
h
o
d
o
f
clas
s
i
f
y
i
n
g
m
alicio
u
s
ac
ce
s
s
es
au
to
m
atica
ll
y
f
r
o
m
v
ar
io
u
s
co
llected
d
ata,
in
clu
d
i
n
g
b
o
th
m
alicio
u
s
a
n
d
b
en
ig
n
ac
ce
s
s
es.
I
n
t
h
is
s
t
u
d
y
,
th
e
y
h
a
v
e
co
n
ce
n
tr
ated
o
n
th
e
d
is
co
v
er
y
o
f
cr
a
w
ler
s
,
w
h
o
s
e
ac
ce
s
s
es
h
as
b
ee
n
g
r
o
w
in
g
s
w
i
f
tl
y
[
2
2
]
.
P
h
is
h
i
n
g
h
as
p
r
o
g
r
ess
ed
r
e
m
a
r
k
ab
l
y
ac
r
o
s
s
th
e
last
f
e
w
y
ea
r
s
,
an
d
it
h
as
s
h
i
f
ted
a
cr
itical
w
ar
n
in
g
to
g
lo
b
al
s
ec
u
r
it
y
a
n
d
ec
o
n
o
m
y
.
T
h
e
au
th
o
r
s
ai
m
to
p
r
o
v
e
p
h
is
h
in
g
d
is
co
v
er
y
u
s
i
n
g
f
u
zz
y
lo
g
ic
a
n
d
i
n
ter
p
r
etin
g
o
u
tco
m
es
u
s
i
n
g
v
ar
io
u
s
d
ef
u
z
zif
icatio
n
tech
n
iq
u
e
s
[
2
3
]
.
B
iao
et
al.
[
2
4
]
p
r
o
p
o
s
ed
a
h
ier
ar
ch
ical
clu
s
ter
in
g
alg
o
r
ith
m
b
ased
o
n
tr
ee
ed
it
d
is
tan
ce
to
r
ec
o
g
n
ize
a
n
d
ca
te
g
o
r
ize
h
o
s
tile
J
av
aScr
ip
t.
A
s
o
cial
n
et
w
o
r
k
i
n
g
s
it
e
h
elp
s
m
illi
o
n
s
o
f
u
s
er
s
to
in
t
er
ac
t
o
n
lin
e,
an
d
a
s
u
b
s
tan
tia
l
v
o
lu
m
e
o
f
d
ata
h
as
b
ee
n
u
p
lo
ad
ed
ev
er
y
d
a
y
.
Hen
ce
i
n
ea
ch
s
ec
o
n
d
,
a
h
u
g
e
q
u
a
n
tit
y
o
f
d
ata
h
as
b
ee
n
ca
u
s
ed
th
r
o
u
g
h
o
u
t
t
h
e
w
o
r
ld
.
T
h
is
r
eq
u
ir
es
th
e
ad
o
p
tio
n
o
f
th
e
n
e
w
m
et
h
o
d
o
lo
g
y
to
p
r
o
v
id
e
s
ec
u
r
it
y
o
f
o
n
li
n
e
d
ata.
So
cial
n
et
w
o
r
k
u
s
er
s
ar
e
n
o
t
a
w
ar
e
o
f
t
h
e
v
ar
io
u
s
s
ec
u
r
it
y
t
h
r
e
ats,
an
d
th
e
as
s
o
ciate
d
r
is
k
s
ex
i
s
t
i
n
th
e
s
e
n
et
w
o
r
k
s
.
T
h
e
a
u
t
h
o
r
s
p
r
esen
t
a
m
et
h
o
d
o
lo
g
y
w
h
ic
h
s
u
p
p
o
r
ts
t
h
e
o
n
li
n
e
u
s
er
s
to
b
e
p
r
o
tecte
d
f
r
o
m
v
ar
io
u
s
f
r
au
d
u
le
n
t
an
d
m
alicio
u
s
ac
t
io
n
s
o
n
th
e
n
et
w
o
r
k
.
T
h
is
p
ap
er
p
r
esen
ts
a
n
ass
e
s
s
m
e
n
t
o
f
clas
s
if
ica
tio
n
d
if
f
er
en
t
s
o
cial
n
et
w
o
r
k
a
n
d
d
if
f
er
e
n
t
attac
k
s
p
r
e
s
en
t
o
n
t
h
o
s
e
s
o
cial
n
et
w
o
r
k
s
a
n
d
m
e
th
o
d
o
lo
g
y
h
as
b
ee
n
p
r
o
p
o
s
ed
w
h
ich
h
elp
th
e
o
n
li
n
e
u
s
er
s
to
b
e
s
af
e
f
r
o
m
n
u
m
er
o
u
s
f
r
au
d
u
len
t a
n
d
m
alicio
u
s
ac
ti
v
itie
s
o
n
th
e
w
eb
[
2
5
]
.
3.
M
E
T
H
O
DO
L
O
G
Y
B
o
o
s
tin
g
i
s
a
co
m
m
o
n
ap
p
r
o
ac
h
f
o
r
ac
q
u
ir
in
g
cla
s
s
i
f
ier
s
b
y
co
n
v
er
ti
n
g
w
ea
k
lear
n
er
to
s
tr
o
n
g
lear
n
er
.
T
h
e
id
ea
o
f
th
e
b
o
o
s
tin
g
tec
h
n
iq
u
e
i
s
to
g
et
a
w
ea
k
class
i
f
ier
an
d
p
r
ac
tice
it
to
d
ev
elo
p
an
ex
tr
e
m
el
y
b
en
ef
icia
l
class
if
ier
,
t
h
r
o
u
g
h
i
n
cr
ea
s
i
n
g
t
h
e
p
r
ed
i
ctio
n
o
f
t
h
e
w
ea
k
clas
s
if
icatio
n
al
g
o
r
ith
m
.
T
h
is
p
r
ed
ictio
n
is
p
r
ep
ar
e
d
b
y
eq
u
alizi
n
g
th
e
y
i
eld
s
o
f
m
a
n
y
w
ea
k
clas
s
i
f
ier
s
.
On
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
b
o
o
s
tin
g
alg
o
r
it
h
m
s
is
A
d
aB
o
o
s
t,
k
n
o
w
n
as
A
d
ap
tiv
e
B
o
o
s
tin
g
t
h
at
f
o
cu
s
s
es
o
n
class
i
f
icatio
n
p
r
o
b
le
m
s
th
a
t
b
u
i
ld
a
n
i
n
f
lu
e
n
tia
l
class
i
f
ier
f
r
o
m
m
a
n
y
w
ea
k
cl
ass
i
f
ier
s
.
I
t
i
s
ar
r
an
g
ed
b
y
d
e
v
elo
p
in
g
a
p
r
o
to
t
y
p
e
f
r
o
m
th
e
tr
ain
i
n
g
d
ata,
t
h
e
n
b
u
ild
in
g
a
s
ec
o
n
d
m
o
d
el
th
a
t
s
tr
iv
es
to
f
i
x
t
h
e
f
la
w
s
f
r
o
m
th
e
f
ir
s
t
m
o
d
el.
Mo
d
els
ar
e
ap
p
en
d
ed
u
n
til
th
e
tr
ain
in
g
s
et
i
s
d
ed
u
ce
d
,
o
r
th
e
m
o
s
t n
u
m
b
er
o
f
m
o
d
els ar
e
co
m
b
i
n
ed
.
A
d
aB
o
o
s
t
is
ex
tr
e
m
e
l
y
p
r
ac
tic
ed
to
in
cr
ea
s
e
th
e
p
r
o
d
u
ctio
n
o
f
d
ec
is
io
n
tr
ee
s
o
n
b
in
ar
y
cla
s
s
i
f
icatio
n
p
r
o
b
lem
s
.
T
h
e
r
ea
s
o
n
f
o
r
c
h
o
o
s
in
g
t
h
e
A
d
aB
o
o
s
t
alg
o
r
ith
m
is
t
h
at
it
ca
n
b
e
p
r
ac
ticed
to
in
cr
ea
s
e
th
e
p
er
f
o
r
m
an
ce
o
f
a
n
y
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
.
I
t
is
al
w
a
y
s
g
r
ea
t
w
h
en
d
o
n
e
a
m
o
n
g
w
ea
k
lear
n
er
s
.
T
h
e
co
n
v
en
tio
n
al
a
lg
o
r
it
h
m
a
p
p
lied
w
it
h
A
d
aB
o
o
s
t
is
d
ec
i
s
io
n
tr
ee
s
w
i
th
o
n
e
le
v
el.
T
h
e
tr
ee
s
ar
e
s
m
all
a
n
d
h
o
ld
o
n
e
d
ec
is
io
n
f
o
r
a
cla
s
s
,
an
d
h
en
ce
ar
e
r
ef
er
r
ed
to
a
s
d
ec
is
io
n
s
t
u
m
p
s
.
W
ea
k
m
o
d
els
ar
e
co
m
b
i
n
ed
s
eq
u
en
tiall
y
,
d
er
iv
ed
u
ti
lizin
g
th
e
w
ei
g
h
ted
tr
ain
in
g
d
ata.
T
h
e
m
et
h
o
d
co
n
ti
n
u
e
s
u
n
til
a
p
r
e
-
s
et
q
u
a
n
tit
y
o
f
w
ea
k
lear
n
er
s
h
as b
ee
n
p
r
o
d
u
c
ed
,
o
r
n
o
a
d
d
itio
n
al
d
ev
elo
p
m
en
t c
an
b
e
m
ad
e
o
n
t
h
e
tr
ain
in
g
d
ataset.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
9
9
7
-
1005
1000
In
ter
m
s
o
f
m
ac
h
i
n
e
lear
n
i
n
g
,
in
a
d
ec
is
io
n
tr
ee
,
ev
er
y
n
o
d
e
r
ep
r
esen
ts
a
s
ea
r
ch
o
n
an
attr
ib
u
te.
E
v
er
y
b
r
a
n
ch
d
escr
ib
es
t
h
e
r
e
s
u
lt
o
f
t
h
e
te
s
t,
a
n
d
t
h
e
lea
f
n
o
d
es
d
escr
ib
e
th
e
clas
s
lab
el
r
ec
eiv
ed
b
eh
i
n
d
al
l
j
u
d
g
m
e
n
ts
o
b
tain
ed
w
it
h
in
t
h
at
b
r
an
ch
.
T
h
e
w
a
y
s
f
r
o
m
th
e
r
o
o
t
to
leaf
p
r
o
v
id
es
a
class
i
f
icatio
n
r
u
le.
T
h
is
s
y
s
te
m
ai
m
s
to
r
ep
r
esen
t
th
e
in
f
o
r
m
at
io
n
w
h
ile
r
ed
u
ci
n
g
t
h
e
c
o
m
p
le
x
it
y
o
f
th
e
d
es
i
g
n
.
Fi
g
u
r
e
2
s
h
o
w
s
th
e
co
m
p
ar
is
o
n
b
et
w
ee
n
t
h
e
u
n
s
u
p
er
v
i
s
ed
an
d
s
u
p
er
v
is
e
d
m
ac
h
i
n
e
lear
n
in
g
.
T
h
e
m
a
licio
u
s
an
d
b
en
i
g
n
class
i
f
ier
s
ar
e
f
u
r
t
h
er
h
i
g
h
lig
h
ted
in
th
e
f
i
g
u
r
e.
F
ig
u
r
e
2.
Ma
ch
in
e
lear
n
i
n
g
co
m
p
ar
i
s
o
n
T
h
e
p
s
eu
d
o
co
d
e
o
f
t
h
e
A
d
a
B
o
o
s
t
alg
o
r
ith
m
is
a
s
f
o
llo
w
s
:
A
w
ea
k
cla
s
s
i
f
ier
i
s
ta
k
en
t
h
r
o
u
g
h
th
e
tr
ain
in
g
d
ata
u
s
i
n
g
t
h
e
s
a
m
p
les.
T
h
e
A
d
aB
o
o
s
t
alg
o
r
ith
m
s
u
p
p
o
r
ts
o
n
l
y
b
in
ar
y
clas
s
if
ica
tio
n
p
r
o
b
le
m
s
,
s
o
af
ter
ea
c
h
b
o
o
s
ti
n
g
iter
ati
o
n
,
th
e
co
m
p
o
n
e
n
t
cla
s
s
i
f
ier
w
a
s
d
is
co
v
er
ed
w
h
o
s
e
w
eig
h
ted
er
r
o
r
w
o
u
ld
b
e
b
etter
th
an
t
h
e
p
r
ev
io
u
s
o
n
e.
Alg
o
rit
h
m
-
1
Ad
a
B
o
o
s
t
a
lg
o
r
it
h
m
f
u
n
ctio
n
A
D
A
B
OOST
I
NG(
s
a
m
p
les,
A
,
H)
r
etu
r
n
s
a
w
eig
h
t
ed
-
m
aj
o
r
it
y
h
y
p
o
th
e
s
is
in
p
u
ts
:
s
a
m
p
le
s
,
s
et
o
f
N
la
b
eled
s
a
m
p
les (
x
1
,
y
1
)
,
…,
(
x
N
,
y
N)
A
,
a
n
al
g
o
r
ith
m
H,
th
e
h
y
p
o
th
e
s
es i
n
th
e
en
s
e
m
b
le
o
th
er
v
ar
iab
les:
a,
a
v
ec
to
r
o
f
N
ex
a
m
p
le
w
eig
h
t
s
,
in
it
iall
y
1
⁄
N
b
,
a
v
ec
to
r
o
f
H
h
y
p
o
t
h
eses
z,
a
v
ec
to
r
o
f
H
h
y
p
o
t
h
esi
s
w
eig
h
t
s
f
o
r
i =
1
to
H
d
o
b
[
i]
←
L
(
s
a
m
p
le
s
,
a)
er
r
o
r
←
0
f
o
r
j
=
1
to
N
d
o
i
f
b
[
i]
(
x
j
)
≠
y
j
th
e
n
er
r
o
r
←
er
r
o
r
+
a[
j
]
f
o
r
j
=
1
to
N
d
o
i
f
b
[
i]
(
x
j
)
=
y
j
th
en
a[
j
]
←
a[
j
]
•
er
r
o
r
⁄
(
1
−
er
r
o
r
)
a
←
NO
R
M
AL
I
Z
E
(
a)
c[
i]
←
lo
g
(
1
−
er
r
o
r
)
⁄
er
r
o
r
r
etu
r
n
M
A
J
OR
I
T
Y(
b
,
c)
4.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
NS
Fo
r
th
e
ex
p
er
i
m
e
n
tal
p
u
r
p
o
s
e,
w
e
h
av
e
d
ev
e
lo
p
ed
a
w
eb
-
b
ased
ap
p
licatio
n
w
i
th
j
av
a
p
lat
f
o
r
m
,
an
d
th
e
co
m
p
u
ter
s
f
o
r
t
h
is
e
x
p
er
im
en
t
h
a
v
e
t
h
e
s
a
m
e
co
n
f
ig
u
r
atio
n
:
I
n
tel
C
o
r
e
-
i7
2
.
4
0
GHz
(
4
C
P
U’
s
)
,
8
GB
R
A
M,
Mic
r
o
s
o
f
t
W
in
d
o
w
s
1
0
p
r
o
f
ess
io
n
al
6
4
b
it,
an
d
J
DK
1
.
7
.
T
h
e
ev
id
en
ce
f
o
r
th
is
r
ese
ar
ch
,
p
r
esen
ted
b
y
Ma
et
al.
[
1
3
]
,
co
n
tain
s
ar
o
u
n
d
1
2
1
s
ets
o
f
UR
L
s
,
an
d
ea
ch
is
class
i
f
ied
as
eit
h
er
m
alicio
u
s
o
r
b
en
ig
n
.
T
h
e
w
h
o
le
d
ataset
co
n
s
is
t
s
o
f
o
v
er
2
.
3
m
illi
o
n
UR
L
s
,
e
ac
h
p
r
o
d
u
cin
g
o
v
er
3
.
2
m
ill
io
n
ch
ar
ac
ter
is
tic
s
.
T
h
e
am
az
in
g
m
aj
o
r
ity
o
f
t
h
e
s
e
p
ec
u
liar
itie
s
ca
n
b
e
f
o
u
n
d
as
b
in
ar
y
p
r
o
p
er
ties
.
T
h
e
Ma
l
w
ar
e
cla
s
s
i
f
icatio
n
ch
ar
t
w
as s
h
o
w
n
i
n
T
ab
le
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Dete
ctin
g
ma
licio
u
s
UR
Ls
u
s
i
n
g
b
in
a
r
y
cla
s
s
ifica
tio
n
th
r
o
u
g
h
a
d
a
b
o
o
s
t a
lg
o
r
ith
m
(
F
ir
o
z
K
h
a
n
)
1001
T
ab
le
1
.
Ma
lw
ar
e
clas
s
i
f
icatio
n
ch
ar
t
M
a
l
w
a
r
e
Ty
p
e
C
o
u
n
t
d
i
r
e
c
t
s
t
o
T
r
o
j
a
n
1
T
o
r
j
a
n
24
R
F
I
1
c
o
mp
r
o
mi
se
d
s
i
t
e
/
R
e
d
i
r
e
c
t
s t
o
M
e
b
r
o
o
t
1
B
a
c
k
d
o
o
r
.
W
i
n
3
2
.
K
e
y
S
t
a
r
t
.
m
1
e
x
p
l
o
i
t
s/
me
b
r
o
o
t
13
M
e
b
r
o
o
t
c
a
l
l
s h
o
me
14
Ex
l
p
o
i
t
s
11
R
e
d
i
r
e
c
t
s
t
o
e
x
p
l
o
i
t
s
6
R
e
d
i
r
e
c
t
s
t
o
M
e
b
r
o
o
t
3
z
e
u
s v
1
t
r
o
j
a
n
23
t
r
o
j
a
n
d
o
w
n
l
o
a
d
e
r
1
z
e
u
s v
1
(
n
o
n
-
R
C
4
)
t
r
o
j
a
n
19
A
sp
r
o
x
/
D
a
n
me
c
13
e
x
p
l
o
i
t
s/
T
r
o
j
a
n
s
1
t
r
o
j
a
n
W
a
l
e
d
a
c
1
r
e
d
i
r
e
c
t
s t
o
L
u
c
k
y
sp
l
o
i
t
1
F
a
k
e
A
n
t
i
v
i
r
u
s
4
I
R
C
B
o
t
1
r
e
d
i
r
e
c
t
s t
o
me
b
r
o
o
t
a
n
d
o
t
h
e
r
e
x
p
l
o
i
t
s
1
M
a
l
w
a
r
e
c
a
l
l
s h
o
me
2
L
u
c
k
y
sp
l
o
i
t
8
e
x
p
l
o
i
t
s/
T
r
o
j
a
n
3
t
r
o
j
a
n
v
u
n
d
o
1
z
e
u
s v
1
(
n
o
n
-
R
C
4
)
c
o
n
f
i
g
f
i
l
e
15
z
e
u
s v
1
c
o
n
f
i
g
f
i
l
e
10
t
r
o
j
a
n
c
l
i
c
k
e
r
1
z
e
u
s T
r
o
j
a
n
1
A
p
r
o
to
ty
p
e
h
as
b
ee
n
d
ev
e
lo
p
ed
in
J
av
a
p
lat
f
o
r
m
u
s
i
n
g
t
h
e
A
d
aB
o
o
s
t
alg
o
r
it
h
m
[
1
4
,
1
5
]
.
T
h
e
s
cr
ee
n
s
h
o
t
b
elo
w
i
s
attac
h
ed
as
a
r
ef
er
en
ce
.
I
n
Fig
u
r
e
3
,
a
p
r
o
v
is
io
n
h
as
b
ee
n
p
r
o
v
id
ed
f
o
r
th
e
en
d
u
s
er
s
w
h
o
u
s
e
t
h
i
s
p
latf
o
r
m
,
a
n
d
th
e
y
ca
n
u
s
e
t
h
is
s
cr
ee
n
to
ad
d
th
e
d
etails
o
f
t
h
e
m
alicio
u
s
UR
L
d
etails
i
f
th
e
y
en
co
u
n
ter
an
y
.
T
h
is
p
r
o
v
is
io
n
w
a
s
in
co
r
p
o
r
ated
to
g
iv
e
a
w
ar
en
es
s
to
o
th
er
en
d
u
s
er
s
.
Fig
u
r
e
3.
P
r
o
v
is
io
n
f
o
r
ad
d
in
g
th
e
m
al
icio
u
s
s
ite
d
escr
ip
tio
n
I
n
Fi
g
u
r
e
4
,
a
s
a
m
p
le
o
f
Ma
li
cio
u
s
U
R
L
w
a
s
te
s
ted
,
an
d
t
h
e
class
i
f
icat
io
n
w
a
s
d
o
n
e.
I
n
t
h
e
ab
o
v
e
Fig
u
r
e,
w
e
h
av
e
te
s
ted
a
UR
L
ad
d
r
ess
ed
h
ttp
://f
r
ee
-
b
es
t
-
m
o
v
ies.co
m
/d
o
w
n
lo
ad
v
id
eo
1
7
6
3
7
/in
d
ex
.
h
t
m
l
,
an
d
it
w
a
s
class
if
ied
as
T
r
o
j
an
b
y
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
A
d
d
itio
n
a
ll
y
,
w
e
h
a
v
e
test
ed
t
h
e
to
o
l
w
ith
m
an
y
s
ite
s
,
an
d
a
f
e
w
r
esu
lts
h
av
e
b
ee
n
g
i
v
en
as
an
en
d
p
o
in
t
h
er
e.
As
w
e
h
av
e
p
lan
n
ed
to
tak
e
th
i
s
r
esea
r
ch
ah
ea
d
,
w
e
h
a
v
e
n
o
t d
is
cu
s
s
ed
o
u
r
co
m
p
r
eh
e
n
s
iv
e
d
etails.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
9
9
7
-
1005
1002
Fig
u
r
e
4
.
Ver
if
y
i
n
g
a
p
h
is
h
Fig
u
r
e
5
h
i
g
h
lig
h
t
s
t
h
e
n
u
m
b
er
o
f
m
al
w
ar
e
o
cc
u
r
r
en
c
es
an
d
o
u
r
p
r
o
p
o
s
ed
s
y
s
te
m
s
class
if
ies
th
e
m
al
w
ar
e
in
to
d
if
f
er
e
n
t
c
ateg
o
r
ies
li
k
e
Dir
ec
ts
to
T
r
o
jan
,
T
r
o
j
an
,
R
FI,
co
m
p
r
o
m
i
s
e
d
s
ite/R
ed
ir
ec
ts
to
Me
b
r
o
o
t,
B
ac
k
d
o
o
r
.
W
in
3
2
.
Ke
y
Star
t.
m
,
e
x
p
lo
its
/
m
eb
r
o
o
t,
Me
b
r
o
o
t c
alls
h
o
m
e,
E
x
p
lo
it
s
,
r
e
d
ir
ec
ts
to
ex
p
lo
it
s
,
R
ed
ir
ec
ts
to
Me
b
r
o
o
t,
ze
u
s
v
1
,
T
r
o
j
an
,
tr
o
j
an
d
o
w
n
lo
ad
er
,
ze
u
s
v
1
(
n
o
n
-
R
C
4
)
tr
o
j
a
n
,
A
s
p
r
o
x
/
Dan
m
ec
,
ex
p
lo
its
/T
r
o
j
an
s
,
tr
o
j
an
W
aled
ac
,
r
ed
ir
ec
ts
to
L
u
c
k
y
s
p
lo
it,
Fak
e
An
ti
v
ir
u
s
,
I
R
C
B
o
t
,
r
ed
i
r
e
cts
to
m
eb
r
o
o
t
an
d
o
th
er
ex
p
lo
its
,
Ma
l
w
ar
e
ca
lls
h
o
m
e,
L
u
c
k
y
s
p
lo
it,
e
x
p
lo
its
/
T
r
o
j
an
,
tr
o
j
an
Vu
n
d
o
,
ze
u
s
v
1
(
n
o
n
-
R
C
4
)
co
n
f
i
g
f
ile,
ze
u
s
v
1
co
n
f
i
g
f
ile,
tr
o
j
an
clic
k
er
,
ze
u
s
T
r
o
j
an
.
A
s
u
m
m
ar
y
tab
le
o
f
ca
ls
s
i
f
ied
m
a
l
war
es
ca
n
b
e
s
ee
n
in
Fig
u
r
e
6
.
T
h
e
r
ec
o
m
m
e
n
d
ed
m
et
h
o
d
class
i
f
ie
s
i
f
a
n
y
n
e
w
m
al
w
ar
e
w
a
s
id
en
t
if
ied
.
T
h
e
m
o
d
el
w
as tr
ai
n
ed
an
d
test
ed
in
s
u
c
h
a
w
a
y
,
an
d
t
h
e
t
esti
n
g
f
ile
is
m
e
n
tio
n
ed
b
elo
w
as in
Fi
g
u
r
e
7
.
Fig
u
r
e
5.
Occ
u
r
r
en
ce
o
f
d
if
f
er
en
t
m
a
l
w
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Dete
ctin
g
ma
licio
u
s
UR
Ls
u
s
i
n
g
b
in
a
r
y
cla
s
s
ifica
tio
n
th
r
o
u
g
h
a
d
a
b
o
o
s
t a
lg
o
r
ith
m
(
F
ir
o
z
K
h
a
n
)
1003
Fig
u
r
e
6
.
C
lass
if
ied
m
al
w
ar
es
r
ep
o
s
ito
r
y
Fig
u
r
e
7
.
T
esti
n
g
d
ata
5.
CO
NCLU
SI
O
N
Ma
licio
u
s
UR
L
d
i
s
co
v
er
y
is
a
s
i
g
n
if
ica
n
t
p
ar
t
o
f
n
u
m
er
o
u
s
c
y
b
er
s
ec
u
r
it
y
ap
p
licatio
n
s
,
an
d
it
i
s
ev
id
en
t
t
h
at
m
ac
h
i
n
e
lear
n
i
n
g
s
tr
ateg
ies
p
r
o
v
id
e
an
ass
u
r
in
g
m
et
h
o
d
to
in
co
r
p
o
r
ate
t
h
e
n
ee
d
ed
s
ec
u
r
it
y
m
ea
s
u
r
es.
I
n
t
h
is
s
t
u
d
y
,
w
e
h
a
v
e
d
ev
e
lo
p
ed
a
co
m
p
lete
p
r
o
to
ty
p
e
o
n
Ma
licio
u
s
UR
L
De
tectio
n
u
s
i
n
g
m
ac
h
in
e
lear
n
i
n
g
m
et
h
o
d
s
.
I
n
p
ar
ticu
lar
,
w
e
h
av
e
at
te
m
p
ted
an
ex
a
ct
f
o
r
m
u
latio
n
o
f
Ma
lici
o
u
s
UR
L
e
x
p
o
s
u
r
e
f
r
o
m
a
m
ac
h
i
n
e
lear
n
i
n
g
p
er
s
p
ec
tiv
e
a
n
d
p
r
o
p
o
s
ed
an
ap
p
r
o
a
ch
u
s
i
n
g
th
e
A
d
aB
o
o
s
t
al
g
o
r
it
h
m
—
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
h
as
b
r
o
u
g
h
t
f
o
r
w
ar
d
m
o
r
e
ac
cu
r
ac
y
t
h
an
o
t
h
er
e
x
is
t
in
g
al
g
o
r
ith
m
s
.
T
h
e
r
ea
s
o
n
f
o
r
ch
o
o
s
i
n
g
t
h
is
p
ar
ticu
lar
b
o
o
s
tin
g
tec
h
n
iq
u
e
is
th
a
t
th
e
A
d
aB
o
o
s
t
alg
o
r
it
h
m
ca
n
b
e
u
s
ed
w
it
h
a
n
y
o
t
h
e
r
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
9
9
7
-
1005
1004
RE
F
E
R
E
NC
E
S
[1
]
J.
Ho
n
g
,
―
T
h
e
sta
te o
f
p
h
is
h
in
g
a
t
tac
k
s,‖
Co
mm
u
n
ica
ti
o
n
s o
f
t
h
e
A
CM
,
v
o
l.
5
5
,
n
o
.
1
,
p
p
.
7
4
–
8
1
,
2
0
1
2
.
[2
]
B.
L
ian
g
,
J.
Hu
a
n
g
,
F
.
L
iu
,
D.
W
a
n
g
,
D.
Do
n
g
,
a
n
d
Z.
L
ian
g
,
―
M
a
li
c
io
u
s
w
e
b
p
a
g
e
s
d
e
tec
ti
o
n
b
a
se
d
o
n
a
b
n
o
rm
a
l
v
isib
il
it
y
re
c
o
g
n
it
io
n
,
‖
i
n
E
-
Bu
si
n
e
ss
a
n
d
In
fo
rm
a
t
io
n
S
y
ste
m
S
e
c
u
rity
,
2
0
0
9
.
EBIS
S
’
0
9
.
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
.
IEE
E
,
p
p
.
1
–
5
,
2
0
0
9
,
.
[3
]
D.
R.
P
a
ti
l
a
n
d
J.
P
a
ti
l,
―
S
u
rv
e
y
o
n
m
a
li
c
io
u
s
we
b
p
a
g
e
s
d
e
tec
ti
o
n
tec
h
n
iq
u
e
s,‖
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
u
-
a
n
d
e
-
S
e
rv
ice
,
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
v
o
l.
8
,
n
o
.
5
,
p
p
.
1
9
5
–
2
0
6
,
2
0
1
5
.
[4
]
M
.
Co
v
a
,
C.
Kru
e
g
e
l,
a
n
d
G
.
V
ig
n
a
,
―
De
tec
ti
o
n
a
n
d
a
n
a
ly
sis
o
f
d
ri
v
e
-
by
-
d
o
w
n
lo
a
d
a
tt
a
c
k
s
a
n
d
m
a
li
c
io
u
s
jav
a
sc
rip
t
c
o
d
e
,
‖
in
Pro
c
e
e
d
in
g
s o
f
th
e
1
9
th
in
ter
n
a
t
io
n
a
l
c
o
n
fer
e
n
c
e
o
n
W
o
rl
d
wid
e
we
b
.
A
CM
,
p
p
.
2
8
1
–
2
9
0
,
2
0
1
0
.
[5
]
R.
He
a
rtf
ield
a
n
d
G
.
L
o
u
k
a
s,
―
A
ta
x
o
n
o
m
y
o
f
a
tt
a
c
k
s
a
n
d
a
su
rv
e
y
o
f
d
e
f
e
n
c
e
m
e
c
h
a
n
is
m
s
f
o
r
se
m
a
n
ti
c
so
c
ial
e
n
g
in
e
e
rin
g
a
tt
a
c
k
s,‖
ACM
Co
mp
u
ti
n
g
S
u
rv
e
y
s (
CS
UR)
,
v
o
l.
4
8
,
n
o
.
3
,
p
.
3
7
,
2
0
1
5
.
[6
]
L
.
Op
e
n
DN
S
,
―
P
h
is
h
tan
k
:
A
n
a
n
t
i
-
p
h
is
h
in
g
site,‖
,
2
0
1
6
,
[
On
l
in
e
]
,
Av
a
il
a
b
le
:
h
tt
p
s://
w
ww
.
p
h
ish
tan
k
.
c
o
m
.
[7
]
S
.
S
in
h
a
,
M
.
Ba
il
e
y
,
a
n
d
F
.
Ja
h
a
n
ian
,
―
S
h
a
d
e
s
o
f
g
re
y
:
On
th
e
e
ffe
c
ti
v
e
n
e
s
s
o
f
re
p
u
tatio
n
-
b
a
se
d
―
b
lac
k
li
sts‖
,
‖
in
M
a
li
c
io
u
s
a
n
d
Un
wa
n
ted
S
o
ft
w
a
re
,
2
0
0
8
.
M
AL
W
AR
E
2
0
0
8
.
3
rd
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
.
IEE
E
,
p
p
.
5
7
–
64
,
2
0
0
8
.
[8
]
S
.
G
a
r
e
ra
,
N.
P
ro
v
o
s,
M
.
Ch
e
w,
a
n
d
A
.
D.
Ru
b
in
,
―
A
f
ra
m
e
wo
rk
f
o
r
d
e
te
c
ti
o
n
a
n
d
m
e
a
su
re
m
e
n
t
o
f
p
h
ish
in
g
a
tt
a
c
k
s
,
‖
in
Pro
c
e
e
d
in
g
s
o
f
t
h
e
2
0
0
7
ACM
w
o
rk
sh
o
p
o
n
Rec
u
rr
in
g
ma
lco
d
e
.
A
CM
,
p
p
.
1
–
8
,
2
0
0
7
.
[9
]
S
.
Ch
h
a
b
ra
,
A
.
A
g
g
a
r
wa
l,
F
.
Be
n
e
v
e
n
u
to
,
a
n
d
P
.
Ku
m
a
ra
g
u
ru
,
―
P
h
i.
s
h
/
$
o
c
ial:
th
e
p
h
ish
i
n
g
lan
d
sc
a
p
e
th
ro
u
g
h
sh
o
rt
u
rls,
‖
in
Pro
c
e
e
d
in
g
s
o
f
t
h
e
8
th
An
n
u
a
l
Co
ll
a
b
o
ra
ti
o
n
,
El
e
c
tro
n
i
c
me
s
sa
g
in
g
,
An
ti
-
Ab
u
se
a
n
d
S
p
a
m
Co
n
fer
e
n
c
e
.
A
CM
,
p
p
.
9
2
–
1
0
1
,
2
0
1
1
.
[1
0
]
Y.
A
lsh
b
o
u
l
,
R.
Ne
p
a
li
,
a
n
d
Y.
W
a
n
g
,
―
De
tec
ti
n
g
m
a
li
c
io
u
s sh
o
rt
u
rls
o
n
tw
it
ter,‖ 2
0
1
5
.
[1
1
]
F
o
ss
i,
M
.
,
Eg
a
n
,
G
.
,
Ha
le
y
,
K.,
J
o
h
n
s
o
n
,
E.
,
M
a
c
k
,
T
.
,
A
d
a
m
s,
T
.
,
a
n
d
W
o
o
d
,
P
.
,
S
y
ma
n
tec
in
ter
n
e
t
se
c
u
rity
th
re
a
t
re
p
o
rt
,
tren
d
s f
o
r
2
0
1
0
.
v
o
l
.
1
6
,
2
0
1
1
.
[1
2
]
P
ra
k
a
sh
P
a
w
a
n
,
M
a
n
ish
Ku
m
a
r
,
Ko
m
p
e
ll
a
R
a
m
a
n
a
,
G
u
p
ta
M
in
a
x
i,
―
P
h
ish
Ne
t:
P
re
d
ictiv
e
Blac
k
li
stin
g
to
De
tec
t
P
h
ish
i
n
g
A
tt
a
c
k
s
,
‖
INFOCOM
,
2
0
1
0
Pro
c
e
e
d
i
n
g
s IE
E
E
,
p
p
.
1
–
5
,
2
0
1
0
.
[1
3
]
J.
M
a
,
L
.
K.
S
a
u
l,
S
.
S
a
v
a
g
e
,
a
n
d
G
.
M
.
V
o
e
lk
e
r,
―
Id
e
n
ti
fy
in
g
S
u
sp
icio
u
s
URL
s:
A
n
A
p
p
li
c
a
ti
o
n
o
f
L
a
r
g
e
-
s
c
a
le
On
li
n
e
L
e
a
rn
in
g
,
‖
i
n
Pro
c
e
e
d
i
n
g
s
o
f
th
e
2
6
th
An
n
u
a
l
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
.
ACM
,
p
p
.
6
8
1
–
6
8
8
,
2
0
0
9
.
[1
4
]
A
sh
u
to
sh
M
a
ra
th
e
,
P
riy
a
Ja
in
,
V
i
b
h
a
V
y
a
s,
―
Itera
ti
v
e
i
m
p
ro
v
e
d
lea
rn
in
g
a
lg
o
rit
h
m
f
o
r
p
e
t
ro
g
ra
p
h
ic
im
a
g
e
c
las
si
f
ica
ti
o
n
a
c
c
u
ra
c
y
e
n
h
a
n
c
e
m
e
n
t
,‖
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
2
8
9
-
2
9
6
,
F
e
b
2
0
1
9
.
[1
5
]
Ko
m
a
l
Ku
m
a
rN,
R.
L
a
k
sh
m
i
T
u
las
i,
V
ig
n
e
sw
a
ri
D.,
―
A
n
e
n
se
m
b
le
m
u
lt
i
-
m
o
d
e
l
tec
h
n
iq
u
e
f
o
r
p
re
d
ictin
g
c
h
ro
n
ic
k
id
n
e
y
d
ise
a
se
,‖
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o.
2
,
p
p
.
1
3
2
1
-
1
3
2
6
,
A
p
r
2
0
1
9
.
[1
6
]
Y.
Na
k
a
m
u
ra
,
S
.
Ka
n
a
z
a
w
a
,
H.
I
n
a
m
u
ra
a
n
d
O.
T
a
k
a
h
a
sh
i,
"
Clas
s
if
ica
ti
o
n
o
f
Un
k
n
o
w
n
W
e
b
S
it
e
s
Ba
se
d
o
n
Ye
a
rly
Ch
a
n
g
e
s
o
f
Distrib
u
ti
o
n
In
f
o
rm
a
t
io
n
o
f
M
a
li
c
io
u
s
I
P
A
d
d
re
ss
e
s,"
2
0
1
8
9
th
IFI
P
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ne
w
T
e
c
h
n
o
l
o
g
ies
,
M
o
b
il
it
y
a
n
d
S
e
c
u
r
it
y
(
NT
M
S
)
,
P
a
ris,
p
p
.
1
-
4
,
2
0
1
8
.
[1
7
]
G
.
Ch
a
k
ra
b
o
rty
a
n
d
T
.
T
.
L
in
,
―
A
URL
a
d
d
re
ss
a
wa
re
c
las
si
f
ica
ti
o
n
o
f
m
a
li
c
io
u
s
w
e
b
sites
f
o
r
o
n
li
n
e
se
c
u
rit
y
d
u
rin
g
w
e
b
-
su
r
f
in
g
,
‖
2
0
1
7
IEE
E
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
Ne
two
rk
s
a
n
d
T
e
lec
o
mm
u
n
i
c
a
ti
o
n
s
S
y
ste
ms
(
ANT
S
)
,
Bh
u
b
a
n
e
sw
a
r
,
p
p
.
1
-
6
,
2
0
1
7
.
[1
8
]
A
.
S
.
M
a
n
jeri,
K.
R,
A
.
M
NV
a
n
d
P
.
C.
Na
ir,
―
A
M
a
c
h
in
e
L
e
a
r
n
in
g
A
p
p
ro
a
c
h
f
o
r
De
tec
ti
n
g
M
a
li
c
io
u
s
W
e
b
sites
u
sin
g
URL
F
e
a
tu
re
s,‖
2
0
1
9
3
rd
In
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
El
e
c
tro
n
ics
,
Co
mm
u
n
ica
ti
o
n
a
n
d
Aer
o
sp
a
c
e
T
e
c
h
n
o
l
o
g
y
(
ICECA
)
,
C
o
im
b
a
to
re
,
In
d
ia,
p
p
.
5
5
5
-
5
6
1
,
2
0
1
9
.
[1
9
]
M
a
n
li
n
W
a
n
g
,
F
e
i
Z
h
a
n
g
a
n
d
P
.
P
.
K.
C
h
a
n
,
―
M
a
li
c
io
u
s
w
e
b
site
d
e
tec
ti
o
n
u
n
d
e
r
th
e
e
x
p
l
o
ra
to
r
y
a
tt
a
c
k
,
‖
2
0
1
3
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
a
c
h
in
e
L
e
a
rn
i
n
g
a
n
d
Cy
b
e
rn
e
ti
c
s
,
T
ian
ji
n
,
p
p
.
5
6
5
-
5
7
0
,
2
0
1
3
.
[2
0
]
S
.
B.
Ra
th
o
d
a
n
d
T
.
M
.
P
a
tt
e
w
a
r,
―
A
c
o
m
p
a
ra
ti
v
e
p
e
r
f
o
r
m
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
c
o
n
ten
t
b
a
se
d
sp
a
m
a
n
d
m
a
li
c
io
u
s
URL
d
e
te
c
ti
o
n
in
E
-
m
a
il
,
‖
2
0
1
5
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
Gr
a
p
h
ics
,
Vi
sio
n
a
n
d
I
n
fo
rm
a
ti
o
n
S
e
c
u
rity (
CGVIS
)
,
Bh
u
b
a
n
e
sw
a
r,
p
p
.
4
9
-
54
,
2
0
1
5
.
[2
1
]
P
.
J.
S
h
in
d
e
a
n
d
M
.
C
h
a
tt
e
rjee
,
―
A
No
v
e
l
A
p
p
ro
a
c
h
f
o
r
Clas
si
f
ica
ti
o
n
a
n
d
De
tec
ti
o
n
o
f
DO
S
A
tt
a
c
k
s,
‖
2
0
1
8
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
ma
rt Ci
ty a
n
d
Eme
rg
i
n
g
T
e
c
h
n
o
l
o
g
y
(
ICS
CET
)
,
M
u
m
b
a
i,
p
p
.
1
-
6
,
2
0
1
8
.
[2
2
]
N.
Ku
z
e
,
S
.
Ish
ik
u
ra
,
T
.
Ya
g
i,
D.
Ch
ib
a
a
n
d
M
.
M
u
ra
ta,
―
Cra
w
ler
c
las
sif
ic
a
ti
o
n
u
si
n
g
a
n
t
-
b
a
se
d
c
lu
st
e
rin
g
sc
h
e
m
e
,
‖
2
0
1
5
1
0
t
h
I
n
ter
n
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
fo
r
In
ter
n
e
t
T
e
c
h
n
o
lo
g
y
a
n
d
S
e
c
u
re
d
T
ra
n
sa
c
ti
o
n
s
(
ICIT
S
T
)
,
L
o
n
d
o
n
,
p
p
.
8
4
-
89
,
2
0
1
5
.
[2
3
]
S
.
D.
S
h
irsa
t,
―
De
m
o
n
stra
ti
n
g
Diff
e
r
e
n
t
P
h
ish
i
n
g
A
tt
a
c
k
s
U
sin
g
F
u
z
z
y
L
o
g
i
c
,
‖
2
0
1
8
S
e
c
o
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
v
e
n
t
ive
Co
mm
u
n
ica
ti
o
n
a
n
d
Co
mp
u
t
a
ti
o
n
a
l
T
e
c
h
n
o
lo
g
ies
(
ICICCT
)
,
Co
im
b
a
to
re
,
p
p
.
5
7
-
61
,
2
0
1
8
.
[2
4
]
L
.
Biao
,
Z.
Ke
ju
n
,
F
.
H
u
a
m
in
,
Z.
Ke
j
u
n
,
F
.
Hu
a
m
in
a
n
d
L
.
Ya
n
g
,
―
A
n
e
w
a
p
p
ro
a
c
h
o
f
c
lu
ste
rin
g
m
a
li
c
io
u
s
Ja
v
a
S
c
rip
t
,
‖
2
0
1
4
IEE
E
5
th
I
n
t
e
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
o
ft
w
a
re
En
g
in
e
e
rin
g
a
n
d
S
e
rv
ice
S
c
ien
c
e
,
Be
ij
in
g
,
pp.
1
5
7
-
160
,
2
0
1
4
.
[2
5
]
M
.
Na
n
d
h
i
n
i
a
n
d
B.
B.
Da
s,
―
A
n
a
ss
e
ss
m
e
n
t
a
n
d
m
e
th
o
d
o
lo
g
y
f
o
r
f
r
a
u
d
d
e
tec
ti
o
n
in
o
n
li
n
e
so
c
ial
n
e
tw
o
rk
,
‖
2016
S
e
c
o
n
d
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
c
ien
c
e
T
e
c
h
n
o
l
o
g
y
En
g
i
n
e
e
rin
g
a
n
d
M
a
n
a
g
e
me
n
t
(
ICONS
T
EM
)
,
Ch
e
n
n
a
i,
p
p
.
1
0
4
-
108
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Dete
ctin
g
ma
licio
u
s
UR
Ls
u
s
i
n
g
b
in
a
r
y
cla
s
s
ifica
tio
n
th
r
o
u
g
h
a
d
a
b
o
o
s
t a
lg
o
r
ith
m
(
F
ir
o
z
K
h
a
n
)
1005
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Fi
r
o
z
K
h
a
n
wa
s
b
o
rn
in
Ke
ra
la,
In
d
ia,
i
n
1
9
7
4
.
He
re
c
e
iv
e
d
a
B
S
c
d
e
g
re
e
in
El
e
c
tro
n
ics
f
ro
m
th
e
Bh
a
ra
ti
y
a
a
r
Un
iv
e
rsit
y
,
Co
im
b
a
to
re
,
In
d
ia,
in
1
9
9
1
a
n
d
a
M
a
ste
rs
De
g
r
e
e
in
in
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
f
ro
m
Un
iv
e
r
sit
y
o
f
S
o
u
t
h
e
rn
Qu
e
e
n
sla
n
d
,
A
u
stra
li
a
,
a
n
d
a
n
o
th
e
r
M
a
ste
r’s
De
g
re
e
in
In
f
o
rm
a
ti
o
n
Ne
tw
o
rk
a
n
d
C
o
m
p
u
ter
S
e
c
u
rit
y
(w
it
h
Ho
n
o
rs)
f
ro
m
Ne
w
Yo
rk
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
A
b
u
Dh
a
b
i,
UA
E,
in
2
0
0
6
a
n
d
2
0
1
6
re
sp
e
c
ti
v
e
ly
.
H
e
is
c
u
rre
n
tl
y
w
o
rk
in
g
to
wa
rd
s
h
is
P
h
D
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
Brit
ish
U
n
iv
e
rsity
in
Du
b
a
i,
D
u
b
a
i,
UA
E.
In
2
0
0
1
,
h
e
jo
i
n
e
d
th
e
Hig
h
e
r
C
o
ll
e
g
e
s
o
f
T
e
c
h
n
o
lo
g
y
in
Co
m
p
u
ter
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
d
e
p
a
rtm
e
n
t
a
s
a
T
e
a
c
h
in
g
T
e
c
h
n
icia
n
c
o
n
t
in
u
e
d
o
n
to
b
e
c
o
m
e
a
F
a
c
u
lt
y
m
e
m
b
e
r
in
2
0
0
5
.
He
is
c
u
rre
n
t
ly
h
o
l
d
in
g
th
e
p
o
siti
o
n
o
f
a
Lec
tu
re
r,
w
it
h
se
c
u
rit
y
a
n
d
n
e
tw
o
rk
in
g
b
e
in
g
h
is
p
rim
a
r
y
a
re
a
s
o
f
tea
c
h
in
g
.
His
c
u
rre
n
t
re
se
a
rc
h
f
ie
ld
s
in
c
l
u
d
e
c
o
m
p
u
ter
se
c
u
rit
y
,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
i
n
g
a
n
d
c
o
m
p
u
ter n
e
tw
o
rk
in
g
.
Mr
.
J
in
e
sh
Aha
m
e
d
w
a
s
b
o
rn
in
Ke
ra
la,
In
d
ia
in
1
9
7
9
.
He
c
o
m
p
lete
d
h
is
b
a
c
h
e
l
o
r
d
e
g
re
e
in
P
h
y
sic
s
f
ro
m
Un
iv
e
r
sit
y
o
f
C
a
li
c
u
t
in
2
0
0
0
.
He
c
o
m
p
lete
d
h
is
M
a
ste
r’s
d
e
g
re
e
,
M
S
c
in
c
o
m
p
u
ter
c
o
m
m
u
n
ica
ti
o
n
a
n
d
n
e
tw
o
rk
in
g
f
ro
m
P
e
riy
a
r
u
n
iv
e
rsity
in
2
0
0
2
a
n
d
M
a
ste
rs
in
Ne
tw
o
rk
e
n
g
in
e
e
rin
g
f
ro
m
V
IT
Un
iv
e
rsi
ty
in
2
0
0
5
.
He
h
a
s
b
e
e
n
tea
c
h
in
g
in
v
a
rio
u
s
i
n
tern
a
ti
o
n
a
l
u
n
iv
e
rsiti
e
s
f
o
r
th
e
las
t
1
3
y
e
a
r
s.
Cu
rre
n
tl
y
h
e
is
w
o
rk
in
g
a
s
Lec
tu
re
r
in
CIS
d
e
p
a
rtm
e
n
t
i
n
Hig
h
e
r
c
o
ll
e
g
e
o
f
tec
h
n
o
lo
g
y
t
e
a
c
h
in
g
v
a
rio
u
s
c
o
u
rse
s
in
n
e
tw
o
rk
in
g
.
Jin
e
sh
is
p
u
rsu
i
n
g
h
is
P
h
D
in
c
o
m
p
u
ter
sc
ien
c
e
f
ro
m
T
h
e
B
rit
ish
u
n
iv
e
rsity
in
Du
b
a
i,
UA
E.
His
r
e
se
a
rc
h
a
re
a
s
in
c
lu
d
e
Io
T
tec
h
n
o
l
o
g
ies
,
se
c
u
rit
y
a
n
d
a
rti
f
ici
a
l
in
telli
g
e
n
c
e
.
Dr
.
S
e
ifed
i
n
e
K
a
d
r
y
h
a
s
a
Ba
c
h
e
lo
r
d
e
g
re
e
in
a
p
p
li
e
d
m
a
th
e
m
a
ti
c
s
in
1
9
9
9
f
ro
m
L
e
b
a
n
e
se
Un
iv
e
rsit
y
,
M
S
d
e
g
re
e
in
c
o
m
p
u
tatio
n
in
2
0
0
2
f
ro
m
Re
i
m
s
U
n
iv
e
rsity
(F
ra
n
c
e
)
a
n
d
EP
F
L
(L
a
u
sa
n
n
e
),
P
h
.
D.
in
a
p
p
li
e
d
st
a
ti
stics
in
2
0
0
7
f
ro
m
Bl
a
ise
P
a
sc
a
l
Un
iv
e
rsit
y
(F
ra
n
c
e
),
HD
R
d
e
g
re
e
in
2
0
1
7
f
ro
m
Ro
u
e
n
Un
iv
e
rsit
y
.
A
t
p
re
s
e
n
t,
h
isre
se
a
rc
h
f
o
c
u
se
s
o
n
e
d
u
c
a
ti
o
n
u
sin
g
tec
h
n
o
l
o
g
y
,
s
y
ste
m
p
ro
g
n
o
stics
,
sto
c
h
a
stic
sy
ste
m
s,
a
n
d
p
ro
b
a
b
il
it
y
a
n
d
re
li
a
b
il
i
ty
a
n
a
l
y
sis.
He
is
a
n
A
BE
T
p
ro
g
ra
m
e
v
a
lu
a
to
r.
He
is
a
n
a
ss
o
c
iate
p
ro
f
e
s
so
r
a
t
th
e
d
e
p
a
rm
t
e
n
t
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Co
m
p
u
ter S
c
ien
c
e
,
Be
iru
t
A
ra
b
Un
iv
e
rsity
,
L
e
b
a
n
o
n
.
Dr
.
La
k
sh
m
a
n
a
K
u
m
a
r
Ra
m
a
s
a
m
y
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
As
sist
a
n
t
P
ro
f
e
ss
o
r
c
u
m
T
e
c
h
n
ica
l
T
ra
in
e
r
in
Hin
d
u
sth
a
n
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
C
o
im
b
a
to
re
.
T
a
m
il
Na
d
u
.
He
is
a
g
lo
b
a
l
c
h
a
p
ter
L
e
a
d
f
o
rM
LCS
[
M
a
c
h
i
n
e
L
e
a
rn
in
g
f
o
r
C
y
b
e
r
S
e
c
u
rit
y
]
.
F
in
d
h
im
@
h
tt
p
:
//
m
lcs
g
lo
b
a
l.
o
rg
/ch
a
p
ters
-
a
c
ro
ss
-
g
lo
b
e
/.
He
isc
u
rre
n
t
ly
a
l
li
e
d
w
it
h
c
o
m
p
a
n
y
sp
e
c
i
f
ic t
ra
in
in
g
o
f
In
f
o
s
y
s
Ca
m
p
u
s
Co
n
n
e
c
t,
Ora
c
le
W
DP
a
n
d
P
a
lo
A
lt
o
n
e
tw
o
rk
s.
He
d
id
h
is
UG
in
P
S
G
g
ro
u
p
o
f
In
stit
u
t
io
n
s
a
n
d
c
o
m
p
lete
d
h
is
P
G
in
Ka
las
a
li
n
g
a
m
Un
iv
e
rsit
y
a
n
d
P
h
D
u
n
d
e
r
A
n
n
a
Un
iv
e
rsit
y
,
Ch
e
n
n
a
i
a
n
d
h
is
re
se
a
rc
h
is
o
n
se
m
a
n
ti
c
we
b
se
rv
ice
s.
He
h
a
s
a
p
a
ss
io
n
to
w
a
rd
sd
e
v
e
lo
p
m
e
n
t
a
n
d
h
e
h
o
l
d
s
th
e
In
tern
a
ti
o
n
a
l
c
e
rti
f
ica
ti
o
n
o
n
S
CJ
P
(S
u
n
Ce
rti
f
ica
ted
Ja
v
a
P
r
o
g
ra
m
m
e
r)
a
n
d
S
CJW
CD (S
u
n
Ce
rti
f
ica
t
e
Ja
v
a
Web
Co
m
p
o
n
e
n
t
De
v
e
lo
p
e
r).
He
is
m
e
ti
c
u
lo
u
s
w
it
h
p
ro
g
ra
m
m
in
g
lan
g
u
a
g
e
s
li
k
e
Ja
v
a
,
P
y
t
h
o
n
a
n
d
P
H
P
.
He
h
im
se
lf
in
v
o
lv
e
s
in
re
se
a
rc
h
a
n
d
e
x
p
e
rti
se
in
d
istri
b
u
te
d
c
o
m
p
u
ti
n
g
.
He
h
o
ld
s
th
e
c
e
rti
f
ica
ti
o
n
in
Da
ta
S
c
ien
c
e
f
ro
m
Jo
h
n
Ho
p
k
in
s
Un
iv
e
rsit
y
,
Un
it
e
d
S
tate
s.
He
a
ls
o
h
o
l
d
s
th
e
Am
a
z
o
n
Clo
u
d
A
rc
h
it
e
c
t
c
e
rti
f
ica
ti
o
n
f
ro
m
Am
a
z
o
n
W
e
b
S
e
rv
ic
e
s.
He
h
o
ld
s
th
e
p
riv
il
e
g
e
d
G
o
ld
lev
e
l
p
a
rtn
e
rsh
ip
a
wa
rd
f
ro
m
In
f
o
s
y
s
f
o
r
b
rid
g
in
g
th
e
g
a
p
b
e
tw
e
e
n
in
d
u
stry
a
n
d
a
c
a
d
e
m
ia i
n
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.