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
2020
,
p
p
.
275
~
287
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
1
.
pp
2
7
5
-
287
275
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
Security
t
echni
qu
es for
i
n
telligent
s
pa
m
s
ensi
ng
and
a
no
m
a
ly
d
etec
tion in
o
nlin
e
s
o
cia
l
p
la
tf
o
r
m
s
M
o
nther
Aldw
a
iri
1
,
L
o
’
a
i T
a
w
a
lbeh
2
1
Ne
tw
o
rk
En
g
in
e
e
rin
g
a
n
d
S
e
c
u
ri
ty
D
e
p
a
rt
m
e
n
t,
Jo
rd
a
n
Un
iv
e
rsity
o
f
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Jo
rd
a
n
1
Co
ll
e
g
e
o
f
T
e
c
h
n
o
lo
g
ica
l
In
n
o
v
a
ti
o
n
,
Zay
e
d
Un
iv
e
rsit
y
,
U
A
E
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
t
in
g
a
n
d
C
y
b
e
r
S
e
c
u
rit
y
,
Tex
a
s A&
M
Un
iv
e
rsity
-
S
a
n
A
n
to
n
i
o
,
USA
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
23
,
201
8
R
ev
i
s
ed
A
u
g
2
1
,
20
19
A
cc
ep
ted
A
u
g
30
,
2
0
19
T
h
e
re
c
e
n
t
a
d
v
a
n
c
e
s
in
c
o
m
m
u
n
ica
ti
o
n
a
n
d
m
o
b
il
e
tec
h
n
o
l
o
g
ies
m
a
d
e
it
e
a
sie
r
to
a
c
c
e
ss
a
n
d
sh
a
re
in
f
o
r
m
a
ti
o
n
f
o
r
m
o
st
p
e
o
p
le
w
o
rld
w
id
e
.
Am
o
n
g
th
e
m
o
st
p
o
w
e
r
f
u
l
in
f
o
r
m
a
ti
o
n
sp
re
a
d
in
g
p
latf
o
rm
s
a
r
e
th
e
On
li
n
e
S
o
c
ial
Ne
tw
o
rk
s
(OSN)s
th
a
t
a
ll
o
w
I
n
tern
et
-
c
o
n
n
e
c
ted
u
se
rs
to
s
h
a
r
e
d
if
f
e
r
e
n
t
in
f
o
rm
a
ti
o
n
su
c
h
a
s
in
sta
n
t
m
e
ss
a
g
e
s,
t
w
e
e
ts,
p
h
o
t
o
s
,
a
n
d
v
i
d
e
o
s
.
A
d
d
in
g
to
th
a
t
m
a
n
y
g
o
v
e
rn
m
e
n
tal
a
n
d
p
ri
v
a
te
in
stit
u
ti
o
n
s
u
se
t
h
e
OSNs
su
c
h
a
s
Tw
it
ter
f
o
r
o
ff
icia
l
a
n
n
o
u
n
c
e
m
e
n
t
s.
Co
n
se
q
u
e
n
tl
y
,
th
e
re
is
a
tr
e
m
e
n
d
o
u
s
n
e
e
d
to
p
ro
v
i
d
e
th
e
re
q
u
ired
lev
e
l
o
f
se
c
u
rit
y
f
o
r
OSN
u
se
rs.
Ho
we
v
e
r,
th
e
re
a
re
m
a
n
y
c
h
a
ll
e
n
g
e
s
d
u
e
to
t
h
e
d
i
ff
e
r
e
n
t
p
ro
to
c
o
ls
a
n
d
v
a
riet
y
o
f
m
o
b
il
e
a
p
p
s
u
se
d
to
a
c
c
e
ss
OSNs.
T
h
e
re
f
o
re
,
trad
it
io
n
a
l
se
c
u
rit
y
tec
h
n
iq
u
e
s
f
a
il
to
p
ro
v
id
e
t
h
e
n
e
e
d
e
d
se
c
u
rit
y
a
n
d
p
riv
a
c
y
,
a
n
d
m
o
re
in
telli
g
e
n
c
e
is
re
q
u
ired
.
Co
m
p
u
tatio
n
a
l
in
telli
g
e
n
c
e
a
d
d
s
h
ig
h
-
sp
e
e
d
c
o
m
p
u
tati
o
n
,
f
a
u
lt
to
lera
n
c
e
,
a
d
a
p
tab
il
it
y
,
a
n
d
e
rr
o
r
re
sili
e
n
c
e
w
h
e
n
u
se
d
to
e
n
su
re
se
c
u
rit
y
in
OSN
a
p
p
s.
T
h
is
re
se
a
rc
h
p
ro
v
id
e
s
a
c
o
m
p
re
h
e
n
siv
e
re
late
d
w
o
rk
su
rv
e
y
a
n
d
in
v
e
stig
a
t
e
s
th
e
a
p
p
li
c
a
ti
o
n
o
f
a
rti
f
i
c
ial
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
i
n
tru
sio
n
d
e
tec
ti
o
n
s
y
ste
m
s
a
n
d
s
p
a
m
f
il
terin
g
f
o
r
OSNs
.
In
a
d
d
it
i
o
n
,
w
e
u
se
th
e
c
o
n
c
e
p
t
o
f
so
c
ial
g
ra
p
h
s
a
n
d
w
e
ig
h
ted
c
li
q
u
e
s
in
t
h
e
d
e
tec
ti
o
n
o
f
su
sp
icio
u
s
b
e
h
a
v
io
r
o
f
c
e
rtain
o
n
li
n
e
g
ro
u
p
s
a
n
d
to
p
re
v
e
n
t
f
u
rth
e
r
p
la
n
n
e
d
a
c
ti
o
n
s
su
c
h
a
s
c
y
b
e
r/t
e
rro
rist
a
tt
a
c
k
s
b
e
f
o
re
th
e
y
h
a
p
p
e
n
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
I
n
telli
g
en
t
s
p
a
m
s
en
s
in
g
Ma
ch
i
n
e
l
ea
r
n
i
n
g
Ma
licio
u
s
o
n
lin
e
c
o
m
m
u
n
iti
es
On
li
n
e
s
o
cial
n
et
w
o
r
k
s
P
r
iv
ac
y
Co
p
y
rig
h
t
©
2
0
2
0
In
stit
u
te o
f
A
d
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
:
L
o
’
ai
T
a
w
a
lb
eh
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ti
n
g
an
d
C
y
b
er
Secu
r
it
y
,
T
ex
as A&
M
U
n
iv
er
s
it
y
-
San
An
to
n
io
,
T
X,
7
8
2
5
9
,
USA
.
E
m
ail:
lta
w
a
lb
eh
@
ta
m
u
s
a.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
R
ec
en
t
ad
v
a
n
ce
s
in
m
o
b
ile
tec
h
n
o
lo
g
ies
,
f
as
ter
I
n
ter
n
et
co
n
n
ec
tiv
it
y
a
n
d
w
id
er
ac
ce
s
s
p
r
o
v
id
ed
v
as
t
n
u
m
b
er
o
f
ap
p
licatio
n
s
an
d
s
er
v
ices
i
n
d
i
f
f
er
en
t
li
f
e
s
ec
to
r
s
in
cl
u
d
i
n
g
ed
u
ca
tio
n
,
in
d
u
s
t
r
y
,
s
o
cial
l
if
e,
a
n
d
h
ea
lt
h
s
ec
to
r
[
1
]
.
A
l
s
o
,
t
h
e
w
i
d
e
s
p
r
ea
d
o
f
t
h
e
I
n
ter
n
et
m
ad
e
it e
a
s
ier
to
ac
ce
s
s
i
n
f
o
r
m
atio
n
an
d
n
e
w
s
f
o
r
m
o
s
t
o
f
t
h
e
p
eo
p
le
all
o
v
er
th
e
w
o
r
ld
.
Mo
r
eo
v
er
,
th
e
u
n
co
n
tr
o
lle
d
d
ev
elo
p
m
en
t
i
n
t
h
e
w
eb
-
b
as
ed
lif
e
ap
p
licatio
n
s
co
m
in
g
f
r
o
m
th
e
co
m
p
et
i
tio
n
b
et
w
ee
n
t
h
e
i
n
ter
n
atio
n
al
o
r
g
an
iza
tio
n
s
in
t
h
e
f
ield
o
f
s
o
c
ial
co
r
r
esp
o
n
d
en
ce
,
m
ad
e
s
h
ar
i
n
g
an
d
s
p
r
ea
d
in
g
o
f
an
y
i
n
f
o
r
m
atio
n
a
lo
t s
i
m
p
ler
a
nd
ag
r
ee
ab
le
[
1
]
.
I
n
ad
d
itio
n
,
t
h
e
d
i
v
er
s
e
a
n
d
g
r
o
w
i
n
g
n
u
m
b
er
o
f
i
n
d
u
s
tr
y
p
lay
er
s
i
n
t
h
e
f
ield
o
f
n
e
w
s
w
r
iti
n
g
a
n
d
s
p
r
ea
d
in
g
lead
s
to
cr
ea
tin
g
o
f
n
e
w
s
ar
tic
les
t
h
at
ar
e
n
o
t
to
tal
l
y
o
b
v
io
u
s
o
r
ev
e
n
to
tall
y
f
als
e.
I
t
is
p
o
s
s
ib
le
t
h
at
th
e
cr
ea
tio
n
o
f
t
h
is
t
y
p
e
of
ar
ticles
h
a
s
b
ee
n
m
ad
e
b
y
m
is
ta
k
e,
o
n
th
e
o
th
er
h
a
n
d
s
o
m
e
ti
m
es
t
h
er
e
ar
e
m
an
y
d
elib
er
ate
an
d
s
p
ec
ialized
s
ites
f
o
r
s
p
r
ea
d
in
g
f
a
k
e
n
e
w
s
,
to
ac
h
iev
e
p
o
liti
ca
l,
ec
o
n
o
m
i
c,
s
o
cial,
cu
ltu
r
al,
s
ec
u
r
it
y
an
d
o
th
er
g
o
als [
2
]
.
Mo
r
eo
v
er
,
am
o
n
g
t
h
e
m
o
s
t
p
o
w
er
f
u
l
in
f
o
r
m
at
io
n
s
p
r
ea
d
in
g
p
lat
f
o
r
m
s
ar
e
t
h
e
On
l
i
n
e
So
cial
Net
w
o
r
k
s
t
h
at
allo
w
I
n
ter
n
et
-
co
n
n
ec
ted
u
s
er
s
to
s
h
ar
e
all
d
if
f
er
en
t
k
in
d
s
o
f
i
n
f
o
r
m
atio
n
at
an
y
ti
m
e
a
n
d
f
r
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
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
:
275
-
287
276
an
y
w
h
er
e.
W
ith
t
h
e
s
p
r
ea
d
o
f
OSNs
,
o
n
li
n
e
co
m
m
u
n
ities
a
r
is
e,
th
at
s
h
ar
e
cu
r
r
en
t
s
tat
u
s
e
s
,
m
o
o
d
,
th
o
u
g
h
t
s
,
in
s
ta
n
t
m
es
s
ag
e
s
,
t
w
ee
ts
,
p
h
o
t
o
s
,
v
id
eo
s
,
an
d
o
th
er
in
f
o
r
m
a
t
io
n
.
C
o
n
s
eq
u
en
tl
y
,
a
n
d
as
s
o
cial
n
et
w
o
r
k
s
r
ea
c
h
s
p
r
ea
d
s
ex
p
o
n
en
tiall
y
,
th
e
r
i
s
k
o
f
ca
tast
r
o
p
h
ic
i
m
p
ac
ts
o
f
th
e
r
ap
id
s
p
r
ea
d
o
f
f
alse
n
e
w
s
is
i
n
cr
ea
s
i
n
g
d
r
am
at
icall
y
.
I
n
th
e
s
a
m
e
co
n
te
x
t,
f
a
ls
e
n
e
w
s
al
w
a
y
s
lead
s
to
m
i
s
i
n
f
o
r
m
o
f
th
e
g
en
er
al
p
u
b
lic
an
d
s
tir
u
p
s
tr
if
e
an
d
p
r
o
b
lem
s
.
I
n
p
ar
ticu
lar
,
in
th
e
las
t
f
e
w
y
ea
r
s
th
e
s
p
r
ea
d
in
g
o
f
f
a
k
e
in
f
o
r
m
a
tio
n
a
n
d
s
p
a
m
on
th
e
I
n
ter
n
et
h
as
d
r
a
w
n
e
x
p
an
d
in
g
co
n
s
id
er
atio
n
a
n
d
h
a
s
a
ch
iev
ed
th
e
p
u
r
p
o
s
e
o
f
i
m
p
a
ctin
g
p
o
liti
ca
l
a
n
d
s
o
cial
s
u
b
s
ta
n
ce
s
.
I
n
f
ac
t,
s
p
r
ea
d
in
g
f
al
s
e
a
n
d
f
ak
e
(
s
p
a
m
)
in
f
o
r
m
atio
n
is
a
w
o
r
ld
w
id
e
is
s
u
e
a
n
d
tr
e
m
e
n
d
o
u
s
ef
f
o
r
t
s
s
h
o
u
ld
co
m
e
to
g
et
h
e
r
to
li
m
it
o
r
s
to
p
th
e
s
p
r
ea
d
o
f
m
is
i
n
f
o
r
m
atio
n
a
n
d
u
ti
lize
t
h
e
n
ec
ess
ar
y
co
u
n
ter
m
ea
s
u
r
es
to
p
r
ev
en
t
th
is
i
n
cr
ea
s
i
n
g
tr
e
n
d
.
Am
o
n
g
t
h
e
co
u
n
ter
m
ea
s
u
r
e
t
h
at
ca
n
b
e
u
s
ed
is
th
e
cr
y
p
to
g
r
ap
h
ic
al
g
o
r
it
h
m
s
s
u
itab
le
f
o
r
w
ir
eles
s
en
v
ir
o
n
m
e
n
ts
[
3
]
.
T
h
er
e
ar
e
m
a
n
y
f
ac
to
r
s
co
n
tr
i
b
u
ted
to
th
e
w
id
e
s
p
r
ea
d
o
f
th
e
o
n
lin
e
s
o
cial
n
et
w
o
r
k
s
(
OS
Ns).
Am
o
n
g
th
ese,
ar
e
th
e
i
n
cr
ea
s
i
n
g
p
o
p
u
lar
it
y
o
f
m
o
b
ile
s
m
ar
t
d
e
v
ic
es,
ea
s
y
ac
ce
s
s
to
th
e
I
n
ter
n
e
t,
an
d
ad
v
an
ce
s
in
w
ir
ele
s
s
co
m
m
u
n
icatio
n
s
a
n
d
m
o
b
ile
clo
u
d
co
m
p
u
tin
g
s
er
v
ices
[
4
]
.
T
h
e
OSNs
u
s
er
s
’
p
u
b
licl
y
s
h
ar
e
t
h
eir
p
h
o
to
s
,
lo
ca
tio
n
s
,
ac
tiv
itie
s
,
an
d
ev
en
s
o
m
eti
m
es
cr
u
cia
l
p
er
s
o
n
al
in
f
o
r
m
atio
n
.
L
i
k
e
an
y
n
e
w
tec
h
n
o
lo
g
y
,
OSNs
ar
e
e
x
p
ec
ted
to
h
a
v
e
th
eir
f
air
s
h
ar
e
o
f
v
u
l
n
er
ab
ilit
ie
s
an
d
s
u
b
j
ec
t
to
ex
p
lo
it
s
t
h
at
m
i
g
h
t
co
m
p
r
o
m
i
s
e
th
e
s
ec
u
r
it
y
o
f
u
s
er
’
s
d
ata.
E
s
p
ec
iall
y
b
ec
au
s
e
OSN
m
o
b
il
e
u
s
er
s
ar
e
al
w
a
y
s
lo
g
g
ed
in
an
d
co
n
n
ec
ted
to
I
n
ter
n
et
th
r
o
u
g
h
m
o
b
ile
d
e
v
i
ce
s
.
Fo
r
ex
a
m
p
le,
OS
N
u
s
er
s
m
a
y
b
e
a
n
o
n
y
m
o
u
s
,
b
u
t
at
th
e
s
a
m
e
ti
m
e,
th
is
an
o
n
y
m
i
t
y
m
a
k
es
t
h
e
m
m
o
r
e
liab
le
to
b
e
at
r
is
k
o
f
ea
v
esd
r
o
p
p
in
g
an
d
s
p
o
o
f
i
n
g
.
T
h
er
ef
o
r
e,
s
ec
u
r
it
y
ch
alle
n
g
e
s
,
p
r
iv
ac
y
is
s
u
e
s
,
an
d
id
en
tit
y
a
u
th
e
n
tica
tio
n
ar
e
m
u
c
h
m
o
r
e
co
m
p
licated
f
o
r
s
o
cial
n
et
w
o
r
k
s
co
m
p
ar
ed
to
o
th
er
t
y
p
es o
f
n
et
w
o
r
k
s
[
5
]
.
S
ec
u
r
it
y
a
n
d
p
r
iv
ac
y
is
s
u
e
s
ar
e
cr
itical
w
h
e
n
it
co
m
e
s
to
OS
Ns
,
b
ec
au
s
e
s
e
n
s
i
tiv
e
i
n
f
o
r
m
atio
n
i
s
in
v
o
l
v
ed
.
I
n
m
o
b
ile
s
o
cial
n
et
w
o
r
k
s
,
th
ese
i
s
s
u
es
ar
e
ev
en
m
o
r
e
cr
itical
,
b
ec
au
s
e
m
is
b
eh
a
v
io
r
is
v
er
y
co
m
m
o
n
b
et
w
ee
n
teen
a
g
er
s
an
d
th
o
s
e
w
h
o
th
i
n
k
th
ei
r
an
o
n
y
m
it
y
s
h
ield
th
e
m
f
r
o
m
r
esp
o
n
s
ib
ilit
y
.
Misb
eh
a
v
io
r
in
OS
Ns
i
n
c
l
u
d
es
s
h
ar
in
g
o
r
p
o
s
ti
n
g
v
er
b
al,
w
r
itte
n
,
i
m
a
g
es,
co
m
m
en
ts
a
n
d
as
s
au
l
ts
v
id
eo
s
’
,
w
h
ic
h
m
ig
h
t r
es
u
lt
in
d
r
a
m
a
ti
c
n
eg
at
iv
e
i
m
p
ac
t o
n
y
o
u
n
g
u
s
er
s
.
Mo
r
eo
v
er
,
n
o
v
ice
u
s
er
s
o
f
ten
s
h
ar
e
i
m
p
o
r
ta
n
t
p
r
iv
ate
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
ir
d
ail
y
liv
e
s
s
u
c
h
as
t
h
eir
id
en
tit
y
,
f
a
m
il
y
,
co
n
tac
ts
,
an
d
l
o
ca
tio
n
.
T
h
er
ef
o
r
e,
p
r
iv
ac
y
a
n
d
s
ec
u
r
it
y
o
f
O
SNs
ar
e
co
n
s
id
er
ed
a
v
ita
l
r
esear
c
h
ar
ea
.
Ma
n
y
cla
s
s
ic
s
ec
u
r
it
y
p
o
licies
ar
e
u
s
ed
to
p
r
o
tect
d
ata
an
d
u
s
er
s
o
v
er
m
o
b
ile
s
o
cial
n
et
w
o
r
k
s
s
u
c
h
as a
cc
ess
co
n
tr
o
l a
n
d
id
en
t
it
y
m
a
n
ag
e
m
e
n
t
[
6
]
.
Ho
w
e
v
er
,
class
ical
tec
h
n
iq
u
e
s
an
d
p
o
licies
d
o
n
o
t
p
r
o
v
id
e
th
e
r
eq
u
ir
ed
lev
el
o
f
p
r
o
tectio
n
,
an
d
th
er
e
ar
e
al
w
a
y
s
n
e
w
v
u
ln
er
ab
ili
ti
es
th
a
t
o
p
en
t
h
e
p
o
s
s
ib
ilit
y
f
o
r
n
e
w
at
tack
s
.
C
o
m
p
u
tatio
n
I
n
te
llig
e
n
ce
(
C
I
)
tech
n
iq
u
es
ar
e
v
er
y
p
r
o
m
i
s
i
n
g
to
ac
h
ie
v
e
t
h
e
n
ee
d
ed
h
i
g
h
e
r
lev
el
s
o
f
p
r
o
tectio
n
.
C
I
m
et
h
o
d
s
i
n
clu
d
e
Fu
zz
y
S
y
s
te
m
s
,
A
r
ti
f
icial
I
m
m
u
n
e
S
y
s
te
m
s
a
n
d
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
s
[
7
]
.
C
I
ar
e
u
s
ed
in
d
e
v
elo
p
in
g
th
e
I
n
tr
u
s
io
n
Dete
ct
io
n
S
y
s
te
m
s
(
I
DS
s
)
f
o
r
Mo
b
ile
So
cial
Net
w
o
r
k
s
(
MS
Ns)
b
ased
o
n
th
eir
ca
p
ab
ilit
y
to
class
i
f
y
s
ec
u
r
i
t
y
attac
k
s
a
n
d
th
en
g
e
n
er
ate
r
u
le
s
o
r
s
ig
n
atu
r
e
s
to
d
escr
ib
e
th
e
m
.
I
n
tr
u
s
io
n
Dete
ctio
n
S
y
s
te
m
s
ar
e
u
s
ed
to
p
r
o
tect
n
et
w
o
r
k
s
f
r
o
m
s
ec
u
r
it
y
v
io
latio
n
s
a
n
d
m
alicio
u
s
b
eh
av
io
r
b
y
s
p
o
tti
n
g
atte
m
p
t
s
to
co
m
p
r
o
m
i
s
e
t
h
e
s
ec
u
r
it
y
o
f
p
r
o
tecte
d
n
et
w
o
r
k
s
.
I
DSs
g
e
n
er
ate
r
ep
o
r
ts
ab
o
u
t
ev
er
y
v
io
la
tio
n
t
h
at
o
cc
u
r
s
o
n
th
e
n
et
w
o
r
k
.
C
o
m
p
u
tat
io
n
al
i
n
telli
g
en
ce
tech
n
iq
u
e
s
a
r
e
v
er
y
s
u
itab
le
to
m
o
n
ito
r
,
d
etec
t,
an
a
l
y
ze
a
n
d
r
esp
o
n
d
to
u
n
a
u
t
h
o
r
ized
ac
tiv
it
y
i
n
d
y
n
a
m
ic
an
d
c
h
a
n
g
i
n
g
m
ed
iu
m
s
s
u
ch
a
s
Mo
b
ile
So
cial
Net
w
o
r
k
s
[
8
]
.
I
n
t
h
is
w
o
r
k
,
w
e
f
o
cu
s
o
n
t
w
o
tech
n
iq
u
e
s
o
f
C
o
m
p
u
tat
io
n
al
I
n
telli
g
en
ce
;
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
s
(
A
NN
s
)
an
d
Ma
c
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
a
n
d
th
eir
u
s
e
f
o
r
class
i
f
y
in
g
,
s
elec
tin
g
a
n
d
r
es
p
o
n
d
in
g
to
p
o
s
s
ib
le
attac
k
s
o
n
On
l
in
e
So
cial
Ne
t
w
o
r
k
s
.
A
NN
s
ar
e
n
et
w
o
r
k
s
o
f
m
as
s
i
v
e
n
u
m
b
er
o
f
ar
ti
f
icial
n
e
u
r
o
n
s
t
h
at
g
en
er
ate,
p
r
o
ce
s
s
a
n
d
an
al
y
ze
d
is
tr
ib
u
ted
i
n
f
o
r
m
atio
n
.
A
N
Ns
ar
e
a
s
e
lf
-
lear
n
in
g
a
n
d
s
el
f
-
o
r
g
a
n
izi
n
g
n
et
w
o
r
k
s
,
w
h
ich
m
ak
e
th
e
m
s
u
itab
le
to
m
a
k
e
d
ec
is
io
n
s
q
u
ick
l
y
a
n
d
s
o
lv
e
p
r
o
b
le
m
s
o
f
h
ig
h
a
m
b
i
g
u
i
t
y
.
M
ac
h
i
n
e
lear
n
i
n
g
tec
h
n
iq
u
es
ar
e
also
s
tu
d
ied
in
th
is
w
o
r
k
an
d
th
e
p
o
s
s
ib
ilit
y
o
f
ap
p
ly
in
g
t
h
e
m
i
n
s
p
a
m
d
etec
t
io
n
(
m
ai
n
l
y
f
a
k
e
n
e
w
s
is
in
v
e
s
ti
g
ated
)
.
T
h
e
co
n
tr
ib
u
tio
n
s
o
f
th
is
p
ap
e
r
ar
e
ad
d
r
ess
in
g
h
o
w
o
n
li
n
e
s
o
cial
n
et
w
o
r
k
s
ca
n
b
e
s
tr
u
ct
u
r
e
d
as so
cial
g
r
ap
h
s
w
i
th
t
h
e
u
s
er
s
r
ep
r
ese
n
ted
as
n
o
d
es
o
n
t
h
e
g
r
ap
h
.
Mo
r
eo
v
er
,
b
ased
o
n
th
e
o
b
s
er
v
atio
n
t
h
at
ce
r
tain
co
m
m
u
n
it
y
o
r
g
r
o
u
p
o
v
er
an
OS
N
ca
n
f
o
r
m
a
n
e
n
ti
t
y
w
i
th
th
e
ir
s
o
cial
ac
t
iv
it
i
es,
w
e
p
r
o
p
o
s
ed
th
e
tr
u
s
t
w
o
r
th
i
n
es
s
co
n
ce
p
t
to
id
en
tify
th
e
co
m
m
u
n
itie
s
/e
n
ti
ties
w
it
h
m
ali
c
io
u
s
ac
ti
v
it
ies
.
A
l
s
o
,
w
e
p
r
o
p
o
s
ed
n
e
w
ap
p
r
o
ac
h
t
h
at
u
s
e
s
t
h
e
c
o
n
ce
p
t
o
f
w
ei
g
h
ted
cliq
u
es
i
n
th
e
d
etec
t
io
n
o
f
s
u
s
p
icio
u
s
b
eh
av
io
r
o
f
ce
r
tai
n
o
n
lin
e
g
r
o
u
p
s
a
n
d
to
p
r
ev
en
t f
u
r
th
er
p
lan
n
ed
ac
tio
n
s
s
u
c
h
as
cy
b
er
/ter
r
o
r
is
t a
ttac
k
s
b
ef
o
r
e
t
h
e
y
h
ap
p
en
.
T
h
e
f
o
llo
w
i
n
g
s
ec
t
io
n
ex
p
lai
n
s
r
elate
d
w
o
r
k
in
d
etail.
Secti
o
n
3
d
escr
ib
es
th
e
s
o
lu
tio
n
s
c
u
r
r
en
tl
y
in
u
s
e
f
o
r
d
etec
tin
g
s
p
a
m
a
n
d
f
a
k
e
n
e
w
s
b
ased
o
n
Ma
c
h
in
e
L
ea
r
n
in
g
tec
h
n
iq
u
es
o
v
er
OSN
s
.
Sectio
n
4
d
ef
i
n
e
s
A
r
ti
f
icial
Neu
r
al
Ne
t
w
o
r
k
s
co
n
ce
p
ts
f
o
llo
w
ed
b
y
t
h
e
u
s
e
o
f
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
s
f
o
r
I
n
tr
u
s
io
n
Dete
ctio
n
an
d
Sp
a
m
Fil
ter
i
n
g
o
v
er
On
lin
e
So
cial
Net
w
o
r
k
s
in
Sectio
n
5
.
I
n
Sectio
n
6
,
w
e
p
r
esen
t
m
alicio
u
s
ac
tiv
itie
s
d
etec
tio
n
tec
h
n
iq
u
e
s
o
v
er
OS
N
s
u
s
in
g
t
h
e
s
o
cial
g
r
ap
h
s
an
d
t
h
e
w
e
ig
h
ted
c
liq
u
e
s
.
Sec
tio
n
7
co
n
clu
d
es t
h
is
w
o
r
k
.
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
S
ec
u
r
ity
tech
n
iq
u
es fo
r
in
tellig
en
t sp
a
m
s
en
s
in
g
a
n
d
a
n
o
ma
ly
d
ete
ctio
n
in
o
n
lin
e
...
(
Mo
n
th
er A
ld
w
a
ir
i)
277
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
On
li
n
e
So
cial
Net
w
o
r
k
s
allo
w
I
n
ter
n
et
-
co
n
n
ec
ted
u
s
er
s
to
s
h
ar
e
all
d
if
f
er
en
t
k
i
n
d
s
o
f
in
f
o
r
m
atio
n
a
t
an
y
ti
m
e
a
n
d
f
r
o
m
an
y
w
h
er
e.
W
ith
t
h
e
s
p
r
ea
d
o
f
OSN
s
,
o
n
li
n
e
co
m
m
u
n
ities
ar
is
e,
t
h
at
s
h
ar
e
s
tatu
s
,
m
o
o
d
,
th
o
u
g
h
ts
,
i
n
s
ta
n
t
m
es
s
ag
e
s
,
t
w
ee
t
s
,
p
h
o
to
s
,
v
id
eo
s
,
a
n
d
o
th
er
in
f
o
r
m
atio
n
.
Ho
w
ev
er
,
s
o
m
e
p
ar
tie
s
m
i
s
u
s
e
w
h
at
is
s
h
ar
ed
o
v
er
OSNs
ac
co
r
d
in
g
to
th
e
ch
o
s
en
p
r
iv
a
c
y
s
etti
n
g
s
[9
]
.
T
h
e
OSN
o
w
n
er
s
b
en
e
f
it
f
r
o
m
co
llectin
g
th
e
s
h
ar
ed
in
f
o
r
m
atio
n
an
d
d
eliv
er
i
n
g
tar
g
ete
d
ad
v
er
tis
e
m
e
n
t.
T
h
o
s
e
ad
s
an
d
th
e
as
s
o
ciate
d
in
f
o
r
m
atio
n
co
n
s
tit
u
te
a
r
is
k
t
o
ev
er
y
o
n
e’
s
p
r
iv
ac
y
.
Mo
r
eo
v
er
,
th
e
p
r
iv
ac
y
s
etti
n
g
s
p
r
o
tect
th
e
u
s
er
’
s
in
f
o
r
m
atio
n
f
r
o
m
o
th
er
u
s
er
s
,
b
u
t
n
o
t
f
r
o
m
t
h
e
ad
m
i
n
i
s
tr
ato
r
s
an
d
o
w
n
er
s
o
f
th
at
s
o
cial
n
et
w
o
r
k
.
Ma
n
y
p
r
ev
io
u
s
r
elate
d
w
o
r
k
s
d
is
c
u
s
s
ed
u
s
er
’
s
p
r
iv
ac
y
is
s
u
e
s
an
d
s
ec
u
r
it
y
co
n
ce
r
n
s
i
n
s
o
cial
n
et
w
o
r
k
s
an
d
p
r
o
p
o
s
ed
s
o
m
e
s
o
l
u
tio
n
s
[
1
0
]
.
C
o
n
s
eq
u
en
tl
y
,
t
h
e
r
ap
id
s
p
r
ea
d
o
f
OSNs
,
t
h
e
lack
o
f
p
r
o
p
er
p
r
iv
ac
y
s
etti
n
g
s
an
d
t
h
e
s
h
ar
i
n
g
o
f
s
en
s
iti
v
e
i
n
f
o
r
m
atio
n
leav
e
th
e
u
s
er
s
ex
p
o
s
ed
to
v
ar
io
u
s
k
i
n
d
s
o
f
th
r
ea
t
s
[1
1
]
.
W
h
at
m
a
k
es
m
a
tter
s
w
o
r
s
e
i
s
th
at
OSN
u
s
er
s
ad
d
p
eo
p
le
th
e
y
d
o
n
o
t
k
n
o
w
to
th
eir
n
e
t
wo
r
k
s
,
f
o
r
ex
a
m
p
le,
8
0
%
o
f
Fa
ce
b
o
o
k
u
s
er
s
ac
ce
p
t
all
f
r
ie
n
d
r
eq
u
ests
ev
e
n
f
r
o
m
co
m
p
lete
s
tr
an
g
er
s
.
A
d
d
i
n
g
s
t
r
an
g
er
s
i
s
r
is
k
y
b
ec
au
s
e
y
o
u
d
is
clo
s
e
y
o
u
r
p
r
iv
ate
d
ata
to
s
tr
an
g
er
s
,
an
d
y
o
u
p
u
t
y
o
u
r
leg
iti
m
ate
f
r
ie
n
d
s
at
r
is
k
as
w
e
ll [
1
2
].
As
s
o
cial
n
e
t
w
o
r
k
s
r
ea
ch
,
s
p
r
ea
d
s
ex
p
o
n
en
tial
l
y
,
s
o
i
s
th
e
d
an
g
er
s
o
f
i
n
tr
u
s
io
n
s
,
v
ir
u
s
es,
click
-
j
ac
k
in
g
,
p
h
i
s
h
in
g
-
attac
k
,
s
p
a
m
,
s
o
cial
b
o
ts
,
Sy
b
il
attac
k
,
clo
n
e
an
d
id
en
ti
t
y
t
h
e
f
t
attac
k
s
to
ac
ce
s
s
in
te
llect
u
al
p
r
o
p
er
ty
p
u
b
lis
h
ed
co
n
te
n
ts
[
1
3
]
.
E
v
er
y
OSN
u
s
er
m
a
y
b
e
s
u
s
ce
p
tib
le
to
m
al
w
ar
e
in
f
ec
tio
n
s
f
r
o
m
s
o
cial
m
ed
ia
s
ite
s
an
d
ap
p
licatio
n
s
a
s
Dr
iv
e
b
y
Do
w
n
lo
ad
[1
4
]
.
A
cc
o
r
d
in
g
to
[
1
5
]
,
m
o
r
e
th
a
n
h
alf
o
f
t
h
e
attac
k
s
o
n
Face
b
o
o
k
co
m
e
f
r
o
m
th
ir
d
-
p
ar
t
y
ap
p
licatio
n
s
t
h
at
n
o
ti
f
y
a
n
d
attr
ac
t
u
s
er
s
t
o
o
p
en
li
n
k
s
th
at
o
p
en
v
ir
u
s
es.
Fo
r
ex
a
m
p
le,
2
0
%
o
f
th
e
s
e
a
p
p
licatio
n
s
tr
y
t
o
tell
t
h
e
u
s
er
s
th
e
y
p
r
o
v
id
e
f
u
n
ctio
n
a
liti
e
s
th
at
Face
b
o
o
k
d
o
es
n
o
t
o
f
f
er
,
s
u
ch
a
s
ap
p
licatio
n
s
th
at
s
h
o
w
w
h
o
v
ie
w
ed
y
o
u
r
Face
b
o
o
k
p
r
o
f
ile
an
d
h
o
w
m
a
n
y
ti
m
e
s
.
I
n
click
-
j
ac
k
in
g
a
ttack
,
m
al
icio
u
s
li
n
k
s
o
f
d
i
f
f
er
e
n
t
co
n
ten
t
f
r
o
m
wh
at
t
h
e
u
s
er
e
x
p
ec
ts
ar
e
i
n
t
er
p
o
lated
o
n
to
s
o
cial
n
et
w
o
r
k
s
ite
s
.
S
u
ch
li
n
k
s
tr
ic
k
OSN
u
s
er
s
to
i
n
s
er
t
t
h
eir
co
n
f
id
en
t
ial
i
n
f
o
r
m
atio
n
,
to
co
n
tr
o
l
th
eir
co
m
p
u
ter
s
,
o
r
to
s
teal
th
eir
ac
co
u
n
ts
.
I
n
o
n
lin
e
s
o
cial
n
et
w
o
r
k
s
,
p
h
is
h
in
g
attac
k
s
o
cc
u
r
b
y
cr
ea
ti
n
g
f
a
k
e
ac
co
u
n
ts
to
i
m
p
er
s
o
n
ate
tr
u
s
t
w
o
r
t
h
y
t
h
ir
d
p
ar
ty
to
g
a
in
ac
ce
s
s
to
u
s
er
s
’
s
en
s
it
iv
e
i
n
f
o
r
m
atio
n
[
1
6
]
.
A
cc
o
r
d
in
g
to
s
p
ec
if
ic
an
al
y
s
i
s
o
f
m
a
n
y
s
t
u
d
ies
o
n
p
h
is
h
i
n
g
attac
k
s
o
n
s
ev
er
al
d
ataset
s
,
f
r
au
d
s
ter
s
r
eg
ar
d
s
o
cial
m
ed
ia
as
th
e
e
asies
t
p
latf
o
r
m
to
p
er
f
o
r
m
p
h
is
h
i
n
g
attac
k
s
.
T
h
e
r
esu
lts
s
h
o
w
th
at
p
h
i
s
h
in
g
attac
k
s
o
n
s
o
cial
m
ed
ia
h
a
v
e
t
h
e
h
i
g
h
est
c
h
an
ce
o
f
s
u
cc
ess
[
1
6
]
.
Oth
er
s
tu
d
ies
s
h
o
w
th
a
t
al
m
o
s
t
o
n
e
t
h
ir
d
o
f
p
h
is
h
in
g
attac
k
s
tar
g
et
s
o
cia
l
n
et
w
o
r
k
i
n
g
,
w
h
ile
th
e
r
est
o
f
th
e
attac
k
s
tar
g
e
t
f
i
n
an
c
ial
an
d
e
-
p
a
y
m
en
t
co
m
p
a
n
ies.
I
n
s
o
cial
n
et
w
o
r
k
s
,
th
e
d
an
g
er
o
f
s
p
a
m
m
er
s
in
cr
ea
s
es
w
h
e
n
u
s
er
s
f
o
llo
w
s
o
m
an
y
u
s
er
s
w
h
o
p
o
s
t
m
es
s
ag
e
s
w
it
h
co
m
m
er
cial
U
R
L
s
.
Fo
llo
w
i
n
g
s
u
ch
u
s
er
s
ca
u
s
e
s
d
is
t
u
r
b
an
ce
i
n
u
s
er
s
’
ac
ti
v
itie
s
o
v
er
t
h
e
s
o
cial
n
et
w
o
r
k
a
n
d
lead
s
to
a
s
i
g
n
i
f
ican
t
m
is
u
n
d
er
s
ta
n
d
i
n
g
o
f
s
ev
er
al
m
e
s
s
a
g
es
a
n
d
p
o
s
ts
,
w
h
ic
h
r
es
u
lts
in
p
er
n
icio
u
s
b
eh
a
v
io
r
.
T
h
er
e
a
r
e
m
a
n
y
tec
h
n
iq
u
es
p
r
o
p
o
s
ed
to
d
etec
t
an
d
id
en
tify
s
u
c
h
w
id
e
s
p
ec
tr
u
m
o
f
attac
k
s
o
v
er
n
et
w
o
r
k
s
[
1
7
]
.
User
s
’
p
r
iv
ac
y
o
v
er
s
o
cial
n
et
w
o
r
k
s
ca
n
b
e
p
r
o
tecte
d
b
y
an
o
n
y
m
izatio
n
,
t
h
at
i
s
“
s
to
p
s
h
ar
in
g
p
r
iv
at
e
in
f
o
r
m
atio
n
s
u
c
h
as
n
a
m
es
an
d
ad
d
r
ess
es
w
it
h
s
tr
an
g
er
s
”
[
1
8
]
.
User
’
s
d
ata
is
d
ea
n
o
n
y
m
i
z
ed
an
d
s
h
ar
ed
w
ith
th
ir
d
p
ar
ties
f
o
r
r
esear
ch
a
n
d
ad
v
er
tis
i
n
g
p
u
r
p
o
s
es
.
No
n
eth
e
less
,
t
h
at
p
o
s
e
s
a
s
er
io
u
s
th
r
ea
t
to
u
s
er
’
s
p
r
iv
ac
y
.
I
n
S
y
b
i
l
attac
k
u
s
er
s
a
s
s
u
m
e
f
a
k
e
id
en
ti
ties
to
r
u
in
a
v
o
tin
g
ap
p
licatio
n
,
ch
a
n
g
e
its
r
esu
lt
s
,
s
w
i
n
g
t
h
e
co
n
v
er
s
atio
n
m
o
o
d
an
d
d
a
m
a
g
e
t
h
e
s
o
cial
n
et
w
o
r
k
o
r
p
ag
e
/
ac
co
u
n
t
r
ep
u
tatio
n
.
T
h
er
ef
o
r
e,
th
er
e
is
a
n
ee
d
f
o
r
a
r
esil
ien
t a
n
d
r
o
b
u
s
t
ap
p
licatio
n
s
an
d
p
latf
o
r
m
s
to
d
ef
e
n
d
ag
ain
s
t s
u
c
h
p
o
s
s
ib
le
attac
k
s
[
2
0
,
2
1
]
.
Mo
r
e
r
ec
en
tl
y
,
s
o
cial
b
o
ts
,
a
n
e
w
t
y
p
e
o
f
I
n
ter
n
e
t
b
o
ts
,
w
h
ic
h
ar
e
s
o
f
t
w
ar
e
s
cr
ip
ts
au
to
m
atica
ll
y
p
er
f
o
r
m
in
g
s
i
m
p
le
ac
tio
n
s
.
S
o
cial
bot
s
ar
e
in
telli
g
en
t
p
r
o
g
r
am
m
in
g
m
i
m
ic
k
i
n
g
h
u
m
a
n
b
eh
av
io
r
an
d
p
er
f
o
r
m
s
i
m
p
le
tas
k
s
s
u
ch
as
s
i
m
p
le
c
u
s
to
m
er
s
er
v
ice,
o
n
li
n
e
c
h
ec
k
-
in
,
d
eliv
er
y
ad
d
r
ess
,
etc
[
2
2
]
.
An
o
th
er
s
er
io
u
s
a
n
d
d
an
g
er
o
u
s
t
h
r
ea
t
i
s
th
e
clo
n
e
an
d
id
en
tit
y
t
h
ef
t
at
tack
.
T
h
is
attac
k
ta
k
es
p
lace
b
y
d
u
p
lica
tin
g
a
s
p
ec
if
ic
u
s
er
ac
co
u
n
t
o
v
er
t
h
e
s
a
m
e
s
o
cial
n
et
w
o
r
k
o
r
a
d
i
f
f
er
e
n
t
o
n
e
a
n
d
r
ep
ea
tin
g
all
o
f
h
is
ac
t
iv
i
t
ies
at
s
i
m
ilar
ti
m
es
[
2
3
]
.
I
n
o
th
er
w
o
r
d
s
,
it
is
clo
n
in
g
t
h
e
p
r
esen
ce
o
f
a
s
p
ec
if
i
c
o
n
lin
e
u
s
er
o
n
a
s
o
cial
n
et
w
o
r
k
to
d
ec
eiv
e
th
e
ac
tu
al
f
r
ien
d
s
,
p
o
ten
tial
f
r
ie
n
d
s
o
r
f
o
llo
w
er
s
to
co
n
ti
n
u
e
th
e
t
r
u
s
t r
elatio
n
s
h
ip
w
i
th
t
h
e
clo
n
ed
ac
co
u
n
t
[
2
3
]
.
B
ased
o
n
th
e
ab
o
v
e
r
e
lated
wo
r
k
r
ev
ie
w
t
h
at
i
n
d
icate
s
t
h
e
i
n
cr
ea
s
i
n
g
q
u
an
tit
y
an
d
q
u
al
it
y
o
f
c
y
b
er
-
attac
k
s
o
n
th
e
d
if
f
er
en
t
o
n
li
n
e
s
o
cial
n
e
t
w
o
r
k
s
,
w
e
ca
n
s
ee
t
h
er
e
i
s
a
n
i
n
cr
ea
s
i
n
g
d
em
a
n
d
to
s
ec
u
r
e
th
e
in
f
r
astr
u
ct
u
r
es
an
d
p
latf
o
r
m
s
t
h
at
ar
e
u
s
ed
to
ac
ce
s
s
th
e
s
e
o
n
lin
e
s
o
cial
n
et
w
o
r
k
s
.
Fo
r
ex
a
m
p
le,
th
er
e
ar
e
m
an
y
atte
m
p
ts
to
p
r
o
p
o
s
e
s
ec
u
r
e
clo
u
d
co
m
p
u
ti
n
g
p
latf
o
r
m
s
t
h
at
p
r
o
v
id
e
s
tr
o
n
g
u
s
er
s
au
th
e
n
ticat
io
n
an
d
au
th
o
r
izatio
n
[
2
4
]
.
A
n
d
s
in
c
e
th
e
clo
u
d
co
m
p
u
ti
n
g
en
v
ir
o
n
m
e
n
ts
i
m
p
le
m
e
n
tatio
n
is
c
o
s
tl
y
,
t
h
e
p
r
o
p
o
s
ed
s
ec
u
r
e
p
lat
f
o
r
m
s
ar
e
f
ir
s
t
te
s
ted
an
d
s
i
m
u
lated
u
s
i
n
g
b
est
clo
u
d
s
i
m
u
lato
r
s
to
v
er
if
y
t
h
eir
s
ec
u
r
it
y
a
n
d
p
er
f
o
r
m
a
n
ce
le
v
els [
2
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
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
:
275
-
287
278
3.
CURR
E
NT
M
ACH
I
NE
L
E
A
RNIN
G
SO
L
U
T
I
O
N
S
F
O
R
I
N
T
RU
SI
O
N
AND
SPAM
DE
T
E
C
T
I
O
N
O
V
E
R
O
SNs
T
o
d
ay
,
Face
b
o
o
k
,
T
w
itter
,
I
n
s
tag
r
a
m
,
Go
o
g
le+
,
Sn
ap
c
h
at,
an
d
o
th
er
s
o
cial
m
ed
ia
n
et
w
o
r
k
s
s
h
ap
i
n
g
o
u
r
s
o
cial
li
v
es,
b
y
ef
f
o
r
tles
s
l
y
s
ta
y
i
n
g
co
n
n
ec
ted
w
it
h
f
r
ien
d
s
a
n
d
f
a
m
il
y
.
Ne
v
er
th
ele
s
s
,
OSN
u
s
er
s
n
ee
d
to
m
ak
e
a
co
n
s
c
io
u
s
d
ec
i
s
io
n
ab
o
u
t
e
v
e
r
y
p
iece
o
f
p
er
s
o
n
al
in
f
o
r
m
at
io
n
h
e/s
h
e
s
h
ar
es
,
b
ec
a
u
s
e
th
e
a
f
o
r
e
m
e
n
tio
n
ed
t
h
r
ea
ts
a
n
d
in
tr
u
s
io
n
s
.
I
n
ad
d
itio
n
,
ev
er
y
s
o
cial
n
et
w
o
r
k
h
as
its
p
r
iv
ac
y
an
d
s
ec
u
r
it
y
s
etti
n
g
s
th
at
g
o
v
er
n
t
h
e
o
n
li
n
e
ex
p
er
ien
ce
an
d
p
r
o
tect
u
s
er
’
s
in
f
o
r
m
at
io
n
[
2
6
]
.
T
h
e
p
r
iv
ac
y
a
n
d
s
ec
u
r
it
y
s
etti
n
g
s
ar
e
ad
j
u
s
ted
th
r
o
u
g
h
co
llab
o
r
atio
n
b
etw
ee
n
ac
ad
e
m
ic
r
esear
ch
er
s
,
s
ec
u
r
it
y
co
m
p
a
n
ies,
an
d
d
eleg
ate
s
f
o
r
ev
er
y
s
o
cial
m
ed
ia
n
et
w
o
r
k
to
co
p
e
w
it
h
cu
r
r
e
n
t
s
ec
u
r
it
y
an
d
p
r
iv
ac
y
t
h
r
ea
ts
.
T
h
er
ef
o
r
e,
th
e
s
ec
u
r
it
y
an
d
p
r
iv
ac
y
s
ett
in
g
s
m
u
s
t b
e
u
p
d
at
ed
an
d
en
h
a
n
ce
d
at
r
eg
u
lar
b
a
s
is
.
T
h
e
o
p
er
ato
r
s
o
f
s
o
cial
n
e
t
wo
r
k
s
i
m
p
r
o
v
ed
a
u
t
h
en
t
icatio
n
b
y
in
cl
u
d
i
n
g
n
e
w
o
p
tio
n
s
t
o
p
r
ev
en
t
p
o
s
s
ib
le
th
r
ea
ts
an
d
attac
k
s
.
Am
o
n
g
th
e
s
e
a
u
th
e
n
tica
tio
n
tec
h
n
iq
u
es
ar
e
t
h
e
t
w
o
o
r
th
r
ee
-
f
ac
to
r
au
th
e
n
tica
tio
n
,
s
u
ch
as
u
s
i
n
g
m
o
b
ile
p
h
o
n
e
n
u
m
b
er
s
to
v
er
i
f
y
t
h
eir
ac
co
u
n
t
s
.
I
n
ad
d
itio
n
,
to
k
en
s
o
r
o
n
e
-
ti
m
e
p
ad
s
ar
e
b
ein
g
s
en
t to
u
s
er
s
to
v
er
if
y
s
o
cial
n
et
w
o
r
k
s
ac
co
u
n
t
s
[2
7
]
.
On
t
h
e
o
th
er
s
id
e,
s
o
cial
n
et
wo
r
k
s
o
p
er
ato
r
s
allo
w
u
s
er
s
to
c
o
n
f
i
g
u
r
e
th
eir
o
w
n
p
r
iv
ac
y
s
et
tin
g
s
s
u
c
h
as
li
m
i
tin
g
w
h
o
ca
n
s
ee
th
eir
p
r
o
f
iles
,
w
h
o
ca
n
co
n
tac
t
th
e
m
,
an
d
th
e
o
p
tio
n
to
b
lo
ck
ce
r
tai
n
u
s
er
s
.
I
n
o
r
d
er
to
ac
h
iev
e
a
u
to
m
ated
f
u
t
u
r
e
p
r
o
tectio
n
d
ata
a
n
al
y
s
i
s
a
n
d
clas
s
i
f
icatio
n
tec
h
n
iq
u
es
ar
e
r
eq
u
ir
e
d
[
2
8
]
.
T
h
e
f
u
r
th
er
p
r
o
tectio
n
ca
n
in
cl
u
d
e
o
p
tio
n
s
lik
e
ab
u
s
e,
s
p
a
m
m
e
s
s
a
g
es
a
n
d
p
r
iv
ac
y
p
o
lic
y
v
io
latio
n
s
r
ep
o
r
tin
g
.
Mo
r
eo
v
er
,
ef
f
icien
t
i
m
p
le
m
e
n
tat
io
n
s
o
f
cr
y
p
to
g
r
ap
h
ic
al
g
o
r
it
h
m
s
ca
n
b
e
u
s
ed
to
p
r
o
v
id
e
co
n
f
id
en
tialit
y
f
o
r
u
s
er
s
d
ata
[
2
9
]
.
T
h
e
au
th
o
r
s
in
[
3
0
]
p
r
o
p
o
s
ed
an
ef
f
ic
ie
n
t
p
r
o
g
r
a
m
m
ab
le
ellip
tic
cu
r
v
e
cr
y
p
to
g
r
ap
h
y
i
m
p
le
m
en
ta
tio
n
,
w
h
ich
is
co
n
s
id
er
ed
to
b
e
v
er
y
s
ec
u
r
e
cr
y
p
to
s
y
s
te
m
.
I
n
s
i
m
ilar
co
n
te
x
t,
th
e
au
t
h
o
r
s
in
[
3
1
]
p
r
o
p
o
s
ed
a
s
ca
lab
le
cr
y
p
to
p
r
o
ce
s
s
o
r
th
at
ca
n
b
e
u
s
ed
to
p
r
o
v
id
e
co
n
f
id
en
tial
it
y
f
o
r
d
if
f
er
en
t
ap
p
licati
o
n
s
w
it
h
d
i
f
f
er
e
n
t o
p
er
an
d
s
izes.
On
th
e
o
t
h
er
s
id
e,
in
f
o
r
m
ati
o
n
s
ec
u
r
it
y
co
m
p
an
ies
h
a
v
e
a
s
ig
n
if
ica
n
t
r
o
le
in
p
r
o
v
id
in
g
b
ette
r
p
r
o
tectio
n
b
y
d
e
v
elo
p
in
g
s
e
cu
r
it
y
to
o
ls
s
u
ch
as
th
e
Z
o
n
e
A
lar
m
So
cial
Gu
ar
d
s
o
f
t
w
a
r
e
th
at
o
f
f
er
s
h
i
g
h
p
r
o
tectio
n
f
r
o
m
s
tr
a
n
g
er
s
a
n
d
d
an
g
er
o
u
s
l
in
k
s
o
n
Face
b
o
o
k
.
Se
v
er
al
r
esear
c
h
er
s
in
v
est
i
g
ated
n
e
w
s
o
lu
tio
n
s
f
o
r
in
tr
u
s
io
n
d
etec
t
io
n
a
n
d
th
r
ea
t
p
r
ev
en
tio
n
in
s
o
cial
n
et
w
o
r
k
s
.
Stri
n
g
h
i
n
i
et
a
l
.
[
3
2
]
d
ev
elo
p
ed
a
tech
n
iq
u
e
to
d
etec
t
s
p
a
m
m
er
s
i
n
s
o
cial
n
et
w
o
r
k
s
.
T
h
e
y
s
h
o
w
th
a
t
it
i
s
p
o
s
s
ib
le
to
a
u
to
m
atica
ll
y
d
e
f
i
n
e
w
h
ic
h
ac
co
u
n
t
s
s
p
a
m
m
er
s
ar
e
u
s
i
n
g
.
D
u
r
i
n
g
th
eir
s
t
u
d
y
,
t
h
e
r
esear
c
h
te
a
m
co
llab
o
r
ated
w
it
h
T
w
itte
r
an
d
u
s
i
n
g
t
h
eir
tech
n
iq
u
e,
th
e
y
d
etec
ted
an
d
d
elete
d
a
r
o
u
n
d
1
6
0
0
0
s
p
am
m
er
p
r
o
f
iles
.
An
o
th
er
w
o
r
k
b
y
Ga
o
et
a
l
.
[
3
3
]
p
r
o
p
o
s
ed
an
o
n
lin
e
s
p
a
m
-
f
il
ter
in
g
s
y
s
te
m
t
h
at
in
s
p
ec
ted
m
e
s
s
a
g
es
s
e
n
t
f
r
o
m
u
s
er
s
i
n
r
ea
l
-
ti
m
e
b
e
f
o
r
e
r
ea
ch
in
g
t
h
e
r
ec
ip
ie
n
ts
.
T
h
e
au
t
h
o
r
s
s
u
g
g
e
s
ted
to
r
ec
o
n
s
tr
u
ct
s
p
a
m
m
e
s
s
a
g
es
an
d
class
i
f
y
t
h
e
m
i
n
to
ca
m
p
aig
n
s
,
a
n
d
s
o
,
th
e
m
e
s
s
a
g
es
w
il
l
b
e
ex
a
m
i
n
ed
in
ca
m
p
aig
n
s
r
ath
er
t
h
an
i
n
d
iv
id
u
all
y
.
On
th
e
o
th
er
h
an
d
,
f
ak
e
n
e
w
s
i
s
co
n
s
id
er
ed
as
s
p
am
d
ata
an
d
u
n
f
o
r
tu
n
atel
y
,
i
t
ca
n
b
e
s
p
r
ea
d
o
v
er
th
e
OSNs
v
er
y
f
as
t.
Ma
n
y
p
r
ev
io
u
s
r
elate
d
w
o
r
k
s
d
i
s
cu
s
s
ed
th
e
w
id
e
s
p
r
ea
d
o
f
f
a
k
e
n
e
w
s
o
v
er
s
o
cial
n
e
t
w
o
r
k
s
an
d
p
r
o
p
o
s
ed
s
o
m
e
s
o
lu
tio
n
s
f
o
r
f
ak
e
n
e
w
s
d
etec
ti
o
n
b
y
ap
p
ly
i
n
g
m
ac
h
i
n
e
lear
n
in
g
tec
h
n
iq
u
e
s
o
v
er
On
l
in
e
So
cial
Net
w
o
r
k
s
.
Th
e
au
th
o
r
s
i
n
[
3
4
]
i
d
en
ti
f
ied
t
w
o
o
p
p
o
s
ite
w
a
y
s
to
d
etec
t
th
e
f
ak
e
n
e
w
s
:
h
u
m
a
n
i
n
ter
v
e
n
tio
n
a
n
d
u
s
i
n
g
alg
o
r
it
h
m
s
.
T
h
e
f
ir
s
t
ap
p
r
o
ac
h
d
ep
en
d
s
o
n
th
e
u
s
er
s
t
o
f
lag
t
h
e
f
a
k
e
n
e
w
s
b
y
f
ac
t
c
h
ec
k
er
s
f
r
o
m
m
ed
ia
o
r
g
an
izatio
n
s
s
u
ch
as
t
h
e
W
ash
i
n
g
to
n
P
o
s
t,
Sn
o
p
es.c
o
m
,
an
d
th
e
Fr
en
ch
n
e
w
s
p
ap
er
L
e
Mo
n
d
e
t
h
at
h
a
s
a
s
p
ec
iali
ze
d
f
ac
t
-
c
h
ec
k
i
n
g
u
n
it
w
h
o
d
ev
elo
p
ed
a
w
eb
e
x
te
n
s
io
n
De
co
d
ex
.
T
h
e
s
ec
o
n
d
ap
p
r
o
ac
h
is
to
u
s
e
a
lg
o
r
it
h
m
s
to
v
alid
ate
t
h
e
in
f
o
r
m
at
io
n
s
o
u
r
ce
s
a
n
d
id
en
t
if
y
f
a
k
e
co
n
ten
ts
.
I
n
th
e
ir
o
p
in
io
n
,
th
is
ap
p
r
o
ac
h
ha
s
n
o
t
y
et
g
ai
n
ed
t
h
e
n
ec
ess
ar
y
r
o
b
u
s
tn
e
s
s
to
ac
cu
r
atel
y
v
e
r
i
f
y
w
h
ich
i
n
f
o
r
m
atio
n
is
f
a
ls
e
o
r
w
h
ic
h
is
n
o
t
.
Ma
ch
i
n
e
L
ea
r
n
i
n
g
h
as
b
ee
n
u
s
ed
to
d
etec
t
f
a
k
e
n
e
w
s
b
as
ed
o
n
n
e
w
s
co
n
ten
t
an
d
s
o
ci
al
co
n
tex
t
f
ea
t
u
r
es
[
3
5
]
.
T
h
e
ex
is
ti
n
g
B
o
o
lean
cr
o
w
d
s
o
u
r
ci
n
g
al
g
o
r
it
h
m
s
w
o
r
k
w
ell
w
h
e
n
u
s
ed
to
class
i
f
y
a
p
o
s
t
w
i
th
s
o
cial
i
n
ter
ac
tio
n
s
is
ab
o
v
e
a
ce
r
tain
t
h
r
es
h
o
ld
.
T
h
e
p
er
f
o
r
m
an
ce
m
ig
h
t
g
o
d
o
w
n
w
h
en
t
h
e
s
o
cial
i
n
ter
ac
tio
n
s
ar
e
b
elo
w
t
h
at
t
h
r
esh
o
ld
.
B
ase
d
o
n
th
at,
t
h
e
a
u
t
h
o
r
s
p
r
o
p
o
s
ed
co
n
ten
t
-
b
ased
m
eth
o
d
s
to
b
e
u
s
ed
as
w
ell.
T
h
e
p
ap
er
c
o
m
b
i
n
ed
co
n
ten
t
-
an
d
s
o
cial
-
b
ased
ap
p
r
o
ac
h
es
b
y
co
m
p
u
ti
n
g
a
s
co
r
e
an
d
class
if
ie
s
p
o
s
ts
ex
ce
ed
in
g
a
th
r
es
h
o
ld
λ
.
T
h
e
s
co
r
e
d
ep
en
d
s
o
n
l
y
o
n
s
o
cial
in
ter
ac
tio
n
s
i.e
.
n
u
m
b
er
o
f
li
k
es
a
n
d
s
h
ar
es
o
n
Face
b
o
o
k
,
r
et
w
ee
t
s
an
d
f
o
llo
w
s
o
n
a
T
w
e
eter
,
etc.
So
cial
s
p
a
m
m
er
s
c
h
an
g
e
th
e
ir
s
p
a
m
m
i
n
g
s
tr
ateg
ie
s
to
tr
ick
d
ep
lo
y
ed
a
n
ti
-
s
p
a
m
m
i
n
g
s
y
s
te
m
s
,
w
h
ic
h
cr
ea
tes
th
e
n
ee
d
f
o
r
m
o
r
e
ef
f
i
cien
t
an
ti
-
s
p
a
m
m
i
n
g
tech
n
iq
u
es
to
p
r
o
tect
s
o
cial
n
et
w
o
r
k
s
u
s
er
s
.
T
h
e
au
th
o
r
s
i
n
[
3
6
]
in
d
icate
d
th
at
s
o
cial
b
o
ts
ca
n
b
e
u
s
ed
p
o
p
u
late
s
o
cial
s
y
s
te
m
s
.
I
n
m
o
s
t
o
f
th
e
ca
s
es,
th
e
s
o
cial
b
o
ts
ar
e
u
s
ed
f
o
r
u
s
e
f
u
l
p
u
r
p
o
s
es
b
u
t
i
n
o
th
er
ca
s
es,
it
ca
n
b
e
v
er
y
h
ar
m
f
u
l
b
y
d
ec
eiv
i
n
g
t
h
e
O
n
li
n
e
So
cial
Net
w
o
r
k
s
u
s
er
s
.
Fo
r
ex
a
m
p
le,
t
h
e
y
ca
n
b
e
u
s
ed
to
in
f
l
u
e
n
ce
elec
tio
n
s
,
t
a
m
p
er
th
e
s
to
ck
m
ar
k
et,
an
d
s
p
r
ea
d
f
ak
e
n
e
w
s
to
s
er
v
e
ce
r
tain
ag
e
n
d
a.
T
h
ey
a
ls
o
m
en
tio
n
ed
th
at
t
h
er
e
ar
e
m
a
n
y
p
r
o
p
o
s
ed
s
y
s
te
m
s
to
d
etec
t
s
o
cial
b
o
ts
.
So
m
e
o
f
th
e
s
e
s
y
s
te
m
s
u
tili
ze
cr
o
w
d
s
o
u
r
cin
g
s
tr
ate
g
ies,
f
ea
tu
r
e
-
b
ased
s
u
p
er
v
i
s
ed
lear
n
in
g
,
an
d
h
y
b
r
i
d
s
y
s
te
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
ec
u
r
ity
tech
n
iq
u
es fo
r
in
tellig
en
t sp
a
m
s
en
s
in
g
a
n
d
a
n
o
ma
ly
d
ete
ctio
n
in
o
n
lin
e
...
(
Mo
n
th
er A
ld
w
a
ir
i)
279
W
e
ca
n
s
ay
t
h
at
s
y
s
te
m
s
t
h
at
d
ep
en
d
o
n
m
ac
h
i
n
e
lear
n
i
n
g
tech
n
iq
u
e
s
ar
e
th
e
b
est
ca
n
d
id
ates
f
o
r
in
s
u
r
i
n
g
s
p
a
m
-
f
r
ee
s
o
cial
n
et
w
o
r
k
s
[
3
7
]
.
Ma
ch
i
n
e
lear
n
i
n
g
tec
h
n
iq
u
e
s
lea
n
o
n
elec
ti
n
g
k
n
o
w
led
g
e
f
r
o
m
p
r
ev
io
u
s
l
y
s
e
n
t
s
p
a
m
i
te
m
s
a
n
d
th
e
n
u
s
e
t
h
e
ac
q
u
ir
ed
in
f
o
r
m
atio
n
to
p
r
ed
ict
th
e
b
eh
a
v
io
r
o
f
n
e
w
l
y
r
ec
ei
v
ed
s
p
a
m
a
n
d
class
if
y
t
h
e
m
.
T
h
e
au
th
o
r
s
in
[
3
8
]
p
r
o
p
o
s
ed
an
ef
f
icie
n
t
cla
s
s
i
f
ier
to
p
r
ed
ict
an
d
d
etec
t
s
p
a
m
m
er
s
’
ac
tio
n
s
u
s
i
n
g
f
ea
t
u
r
e
r
elev
a
n
c
e
an
al
y
s
is
o
n
s
o
cial
n
et
w
o
r
k
is
d
ev
elo
p
ed
Z
h
en
g
et
a
l
.
[
1
9
]
p
r
o
p
o
s
ed
a
n
e
f
f
ec
ti
v
e
s
p
a
m
m
er
d
etec
tio
n
s
y
s
te
m
b
ased
o
n
s
u
p
er
v
i
s
e
d
m
ac
h
in
e
lear
n
in
g
s
o
lu
tio
n
.
T
h
i
s
s
y
s
te
m
co
n
s
id
er
ed
u
s
er
’
s
co
n
ten
t
an
d
b
eh
a
v
io
r
f
ea
tu
r
e
s
,
a
n
d
t
h
en
ap
p
lied
t
h
e
m
i
n
to
th
e
SVM
f
o
r
s
p
a
m
m
er
s
cl
ass
i
f
icatio
n
.
A
cc
o
r
d
in
g
to
th
e
ex
p
er
i
m
e
n
ts
,
t
h
is
s
y
s
te
m
s
h
o
w
ed
ex
ce
l
len
t
p
er
f
o
r
m
a
n
ce
.
Su
g
a
n
y
a,
an
d
He
m
alat
h
a
[
3
9
]
co
m
b
i
n
ed
u
s
er
’
s
co
n
ten
t
a
n
d
b
e
h
a
v
io
r
f
ea
tu
r
es
w
it
h
m
ac
h
in
e
lear
n
in
g
to
i
m
p
le
m
e
n
t
s
p
a
m
cla
s
s
i
f
icat
io
n
m
et
h
o
d
an
d
th
eir
e
x
p
er
i
m
e
n
t
s
s
h
o
w
ed
in
ter
e
s
ti
n
g
r
es
u
lts
.
H
w
a
et
a
l
.
[
4
0
]
f
o
cu
s
ed
o
n
s
en
d
i
n
g
s
p
a
m
u
s
i
n
g
s
et
s
o
f
th
o
u
s
an
d
s
o
f
f
a
k
e
ac
co
u
n
t
s
.
Au
t
h
o
r
s
p
r
o
v
id
ed
a
m
ac
h
i
n
e
-
lear
n
in
g
p
ip
elin
e
t
h
at
class
i
f
ies
f
a
k
e
ac
co
u
n
ts
i
n
to
clu
s
ter
s
ac
co
r
d
in
g
to
th
eir
ac
t
o
r
s
.
Fah
i
m
,
Mu
tah
ir
a
a
n
d
Nasee
m
[
4
1
]
p
r
esen
ted
th
e
r
ea
s
o
n
b
eh
i
n
d
th
e
b
eh
a
v
io
r
o
f
Face
b
o
o
k
s
p
am
m
er
s
.
T
h
ey
also
p
r
o
p
o
s
ed
a
m
eth
o
d
o
lo
g
y
to
f
i
lter
Face
b
o
o
k
s
p
am
u
s
in
g
A
r
t
if
ic
ial
Ne
u
r
al
Net
w
o
r
k
to
d
etec
t
ea
c
h
u
n
u
s
u
al
ac
t
io
n
t
h
at
m
a
y
lead
to
s
p
a
m
s
h
ar
in
g
o
r
p
o
s
t
b
y
s
t
u
d
y
i
n
g
t
h
e
b
eh
a
v
io
r
o
f
all
f
r
ien
d
s
.
Ass
u
m
in
g
s
o
cia
l
n
et
w
o
r
k
s
m
a
k
e
o
u
r
s
o
cial
liv
e
s
s
i
m
p
ler
w
it
h
o
u
t
w
o
r
r
ies
ab
o
u
t
p
r
iv
ac
y
a
n
d
s
ec
u
r
it
y
co
n
ce
r
n
s
,
au
t
h
o
r
s
o
f
[
4
2
]
talk
ed
ab
o
u
t
th
e
b
i
g
r
o
le
Ma
ch
in
e
L
ea
r
n
i
n
g
tec
h
n
iq
u
e
s
p
la
y
in
OSN
p
r
iv
ac
y
.
T
h
e
y
f
o
cu
s
ed
esp
ec
iall
y
o
n
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
s
an
d
Gen
etic
Alg
o
r
it
h
m
as
t
h
e
y
b
o
th
s
h
o
w
e
x
tr
a
in
telli
g
en
ce
an
d
p
r
e
d
ictio
n
th
at
i
s
m
o
r
e
ac
c
u
r
ate.
4.
ARTI
F
I
CI
AL
N
E
URA
L
NE
T
WO
RK
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
is
a
b
r
an
ch
o
f
A
r
t
if
ic
ial
I
n
telli
g
en
ce
(
A
I
)
th
at
is
b
ased
o
n
th
e
n
e
u
r
al
s
tr
u
ct
u
r
e
o
f
t
h
e
h
u
m
a
n
’
s
b
r
ai
n
[
4
3
]
.
A
NN
ai
m
s
to
co
n
v
er
t a
s
p
ec
if
ic
i
n
p
u
t i
n
to
s
i
g
n
if
ica
n
t
o
u
tp
u
t
u
s
i
n
g
h
id
d
en
ar
tif
icial
n
eu
r
o
n
s
,
w
h
ich
ar
e
co
n
s
id
er
ed
th
e
m
ai
n
p
r
o
ce
s
s
i
n
g
ele
m
e
n
ts
i
n
A
NN
t
h
at
ca
n
b
e
u
s
ed
to
d
ev
elo
p
m
an
y
ap
p
licatio
n
s
[
4
4
]
.
E
ac
h
n
e
u
r
o
n
i
s
p
r
o
g
r
a
m
m
ed
to
ac
co
m
p
li
s
h
s
p
ec
i
f
ic
o
p
er
atio
n
a
cc
o
r
d
in
g
to
w
h
ic
h
d
ata
w
il
l
f
la
w
f
r
o
m
n
eu
r
o
n
to
an
o
th
er
.
T
h
ese
n
eu
r
o
n
s
ar
e
o
r
g
an
ized
i
n
s
p
ec
i
f
ic
la
y
er
s
th
r
o
u
g
h
w
h
ich
in
p
u
t
d
ata
m
o
v
e
u
n
ti
l
th
e
o
u
tp
u
t
i
s
p
r
o
d
u
ce
d
.
I
n
o
th
er
w
o
r
d
s
,
th
e
o
u
tp
u
t
is
a
n
e
m
er
g
e
n
t
r
esu
l
t
o
f
ea
ch
o
p
er
atio
n
p
er
f
o
r
m
ed
b
y
e
v
er
y
n
eu
r
o
n
d
a
ta
r
ea
ch
[
4
5
]
.
B
u
ild
in
g
A
r
ti
f
ic
ial
Neu
r
al
Mo
d
el
to
s
o
lv
e
s
p
e
cif
ic
p
r
o
b
le
m
n
ee
d
s
in
te
n
s
i
v
e
k
n
o
w
led
g
e
ab
o
u
t
t
h
e
p
r
o
b
lem
,
th
e
A
NN
i
ts
el
f
,
an
d
th
e
w
o
r
k
i
n
g
p
la
n
[
4
5
]
.
E
ac
h
A
r
tific
ial
Ne
u
r
al
Mo
d
el
h
as
in
p
u
t
(
d
ata
to
b
e
p
r
o
ce
s
s
ed
)
,
th
e
o
u
tp
u
t
(
r
esu
lted
in
f
o
r
m
at
io
n
)
,
n
eu
r
o
n
s
,
an
d
w
eig
h
ts
f
o
r
th
e
m
.
T
h
e
m
o
d
el
also
co
n
tain
s
th
e
o
p
era
tio
n
s
(
m
at
h
e
m
a
ti
ca
l
f
u
n
ctio
n
s
)
t
h
at
d
eter
m
in
e,
w
h
ic
h
n
e
u
r
o
n
d
ata
n
ee
d
to
b
e
ac
ti
v
ated
[
4
6
]
.
T
h
e
h
i
g
h
w
ei
g
h
t
o
f
a
n
e
u
r
o
n
in
d
ic
ates
s
tr
o
n
g
d
ata
to
b
e
o
p
e
r
ated
.
B
y
s
ett
in
g
th
e
weig
h
t
o
f
ev
er
y
n
eu
r
o
n
u
s
i
n
g
p
ar
ticu
lar
alg
o
r
ith
m
i
m
p
le
m
en
t
ed
s
p
ec
if
icall
y
f
o
r
th
is
r
ea
s
o
n
,
th
e
o
u
tp
u
t
w
ill
b
e
p
r
o
d
u
ce
d
f
o
r
s
p
ec
if
ic
in
p
u
t
[
4
6
]
.
A
l
m
o
s
t
all
ANNs
h
a
v
e
th
e
s
a
m
e
s
tr
u
ctu
r
e
.
Fig
u
r
e
1
an
d
Fig
u
r
e
2
p
r
esen
t
th
e
b
asic
s
tr
u
ct
u
r
e
o
f
an
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
an
d
an
A
r
ti
f
icial
Ne
u
r
o
n
,
r
esp
ec
tiv
el
y
.
Fig
u
r
e
1
.
B
asic
s
tr
u
ct
u
r
e
o
f
an
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
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
:
275
-
287
280
Fig
u
r
e
2
.
An
ar
tif
ic
ial
n
e
u
r
o
n
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
s
ar
e
m
o
r
e
th
a
n
ar
tif
ic
ial
n
e
u
r
o
n
s
g
r
o
u
p
ed
in
to
la
y
er
s
an
d
co
n
n
ec
te
d
th
r
o
u
g
h
co
m
m
u
n
icat
io
n
li
n
es.
A
cc
o
r
d
in
g
to
Fi
g
u
r
e
1
,
th
er
e
a
r
e
th
r
ee
k
i
n
d
s
o
f
n
eu
r
o
n
s
.
T
h
er
e
ar
e
n
eu
r
o
n
s
t
h
a
t
r
ec
eiv
e
t
h
e
i
n
p
u
t
f
r
o
m
th
e
r
ea
l
w
o
r
d
,
n
e
u
r
o
n
s
t
h
at
s
e
n
d
t
h
e
o
u
tp
u
t
to
a
s
ec
o
n
d
ar
y
p
r
o
ce
s
s
in
g
an
d
co
n
tr
o
llin
g
s
y
s
te
m
,
a
n
d
n
eu
r
o
n
s
th
at
ar
e
h
id
d
en
f
r
o
m
v
ie
w
.
T
h
e
n
e
u
r
o
n
s
ar
e
d
is
tr
ib
u
ted
i
n
to
s
e
v
er
al
la
y
er
s
.
E
ac
h
n
e
u
r
o
n
in
t
h
e
h
id
d
en
la
y
er
r
ec
ei
v
es
in
p
u
t
f
r
o
m
all
i
n
p
u
t
n
e
u
r
o
n
s
an
d
s
e
n
d
s
o
u
tp
u
t
to
all
o
u
tp
u
t
n
e
u
r
o
n
s
af
ter
p
er
f
o
r
m
in
g
its
co
r
r
e
lated
f
u
n
ctio
n
.
On
t
h
e
o
th
er
s
id
e,
th
e
r
e
ar
e
th
r
ee
ty
p
es
o
f
co
m
m
u
n
icatio
n
li
n
e
s
th
at
co
n
n
ec
t
n
eu
r
o
n
s
to
g
et
h
er
.
T
h
er
e
ar
e
co
n
n
ec
tio
n
s
th
at
le
t
n
ex
t
n
eu
r
o
n
s
’
s
u
m
m
i
n
g
m
e
ch
an
i
s
m
ad
d
,
an
d
o
th
er
co
n
n
ec
tio
n
s
le
t
th
e
m
s
u
b
tr
ac
t.
So
m
e
ANNs
h
av
e
a
n
o
th
er
t
y
p
e
o
f
co
n
n
e
ctio
n
s
,
ca
l
led
f
ee
d
b
ac
k
co
n
n
ec
tio
n
li
n
es.
T
h
ese
li
n
es
ar
e
u
s
ed
to
r
o
u
te
b
ac
k
th
e
o
u
tp
u
t f
r
o
m
th
e
o
u
tp
u
t la
y
er
to
th
e
h
id
d
en
la
y
er
as i
t c
an
b
e
s
ee
n
f
r
o
m
Fi
g
u
r
e
3
.
Af
ter
s
tr
u
ct
u
r
i
n
g
an
A
N
N
f
o
r
a
s
p
ec
i
f
ic
ap
p
licatio
n
,
t
h
e
n
et
w
o
r
k
b
eg
i
n
s
to
lear
n
.
T
r
a
in
i
n
g
t
h
e
n
et
w
o
r
k
h
ap
p
en
s
in
t
w
o
d
if
f
er
en
t
ap
p
r
o
ac
h
es.
T
h
e
f
ir
s
t
ap
p
r
o
ac
h
is
th
e
s
u
p
er
v
i
s
ed
tr
ain
i
n
g
i
n
w
h
ich
w
e
s
u
p
p
l
y
th
e
n
et
w
o
r
k
w
it
h
o
u
tp
u
t
eit
h
er
b
y
r
ati
n
g
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
n
et
w
o
r
k
o
r
b
y
p
r
o
v
id
in
g
t
h
e
o
u
tp
u
t
alo
n
g
w
it
h
it
s
i
n
p
u
t.
I
n
t
h
e
s
ec
o
n
d
ap
p
r
o
ac
h
,
n
o
o
u
t
s
id
e
h
elp
is
p
r
o
v
id
ed
to
t
h
e
n
et
w
o
r
k
,
a
n
d
it s
h
o
u
ld
p
o
r
ten
d
th
e
in
p
u
t a
cc
o
r
d
in
g
to
s
p
ec
i
f
ic
ch
ar
ac
ter
is
tics
.
Fig
u
r
e
3
.
Feed
b
ac
k
c
o
n
n
ec
tio
n
l
in
e
s
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
s
h
a
v
e
b
ee
n
s
u
cc
e
s
s
f
u
ll
y
ap
p
lied
to
s
ev
er
al
r
ea
l
-
w
o
r
ld
f
ield
s
.
Fo
r
ex
a
m
p
le
,
it
is
ap
p
lied
in
f
i
n
a
n
ce
(
e.
g
.
cr
ed
it
r
atin
g
)
,
m
ed
ici
n
e
(
e.
g
.
p
at
ien
t
d
ia
g
n
o
s
is
)
,
i
n
d
u
s
tr
y
(
e.
g
.
p
r
o
ce
s
s
an
d
q
u
al
it
y
co
n
tr
o
l)
,
an
d
s
cien
ce
(
e.
g
.
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
)
[
4
7
]
.
M
o
r
eo
v
er
,
th
e
A
N
N
ca
n
b
e
ap
p
lied
in
ed
u
ca
tio
n
(
e.
g
.
t
ea
ch
i
n
g
n
e
u
r
al
n
et
w
o
r
k
s
)
,
en
er
g
y
(
e.
g
.
elec
tr
ical
lo
ad
an
d
d
e
m
a
n
d
f
o
r
ec
asti
n
g
)
,
a
n
d
o
th
er
m
is
ce
llan
eo
u
s
f
ield
s
[
4
8
]
.
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
S
ec
u
r
ity
tech
n
iq
u
es fo
r
in
tellig
en
t sp
a
m
s
en
s
in
g
a
n
d
a
n
o
ma
ly
d
ete
ctio
n
in
o
n
lin
e
...
(
Mo
n
th
er A
ld
w
a
ir
i)
281
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
s
ar
e
r
ec
en
tl
y
u
s
ed
in
i
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
s
,
th
r
ea
t
p
r
ev
en
tio
n
s
y
s
te
m
s
,
an
d
s
p
a
m
p
r
ed
ictio
n
s
y
s
te
m
s
.
Ho
w
e
v
er
,
th
er
e
is
n
o
t
m
u
ch
w
o
r
k
d
o
n
e
o
n
u
s
i
n
g
A
r
t
if
ic
ial
Neu
r
al
Net
w
o
r
k
s
f
o
r
s
ec
u
r
it
y
co
n
ce
r
n
s
i
n
OSN
s
.
W
e
b
eliev
e
t
h
at
it
i
s
g
o
i
n
g
to
b
e
in
ter
es
tin
g
,
v
al
u
ab
le
an
d
co
n
tr
ib
u
to
r
y
to
s
t
u
d
y
t
h
e
av
ai
lab
ilit
y
o
f
ANN’
s
s
ec
u
r
it
y
ap
p
licatio
n
s
f
o
r
en
s
u
r
in
g
th
e
r
e
q
u
ir
ed
s
ec
u
r
it
y
a
n
d
p
r
iv
ac
y
i
n
OSN
s
.
B
asicall
y
,
in
th
e
f
ield
o
f
s
ec
u
r
it
y
a
n
d
p
r
iv
a
c
y
in
OSNs
,
ANNs
w
i
ll
b
e
u
ti
lized
in
t
w
o
w
a
y
s
,
d
is
tin
g
u
is
h
i
n
g
n
o
r
m
a
l
ac
co
u
n
ts
f
r
o
m
s
p
a
m
ac
co
u
n
t
s
a
n
d
d
esig
n
i
n
g
d
etec
tio
n
f
ea
t
u
r
es
[
4
9
]
.
I
n
b
o
th
ca
s
es,
A
N
N
s
ec
u
r
i
t
y
-
e
n
s
u
r
in
g
s
y
s
te
m
s
n
ee
d
to
b
e
u
p
d
ated
f
r
eq
u
en
tl
y
.
5.
ARTI
F
I
CI
AL
NUE
RAL
N
E
T
WO
RK
I
N
T
RU
SI
O
N
D
E
T
E
C
T
I
O
N
A
ND
SP
AM
F
I
L
T
E
R
I
N
G
O
VE
R
SO
CI
AL
N
E
T
WO
R
K
S
Dete
ctin
g
s
p
a
m
e
m
a
ils
a
n
d
s
o
cial
n
et
w
o
r
k
s
p
a
m
p
o
s
ts
ca
n
b
en
e
f
it
f
r
o
m
ap
p
l
y
i
n
g
th
e
s
a
m
e
tech
n
iq
u
es
,
b
ec
a
u
s
e
o
f
th
e
s
tr
ik
i
n
g
s
i
m
ilar
it
ies
ac
co
r
d
in
g
to
[
5
0
]
.
On
lin
e
So
cial
N
et
w
o
r
k
s
m
alicio
u
s
co
m
m
u
n
it
y
r
ep
r
esen
ted
b
y
s
p
am
m
er
s
i
s
g
etti
n
g
m
o
r
e
d
an
g
er
o
u
s
.
A
p
r
o
p
o
s
ed
b
u
t
n
o
t
p
er
f
ec
tl
y
ex
p
lo
r
ed
s
tr
ateg
y
i
s
to
s
tr
u
c
tu
r
e
a
n
A
r
t
i
f
icial
Neu
r
al
Net
w
o
r
k
f
o
r
S
p
am
d
etec
tio
n
o
v
er
s
o
cial
n
et
w
o
r
k
s
.
I
n
g
en
er
al,
to
ap
p
r
o
x
im
a
te
s
p
ec
if
ic
f
u
n
ct
io
n
s
b
y
ANN,
th
er
e
ar
e
d
if
f
icu
l
ties
in
s
etti
n
g
u
p
its
s
tr
u
ct
u
r
e,
d
ec
id
in
g
h
id
d
en
n
o
d
es
,
an
d
d
ea
lin
g
w
it
h
its
co
m
p
lex
p
ar
a
m
e
ter
s
li
k
e
w
eig
h
t
s
o
f
co
n
n
ec
tio
n
s
a
n
d
lear
n
i
n
g
r
ates.
T
o
o
v
er
co
m
e
s
u
ch
d
if
f
ic
u
ltie
s
,
A
NN
s
ar
e
ap
p
lied
alo
n
g
w
it
h
Gen
et
ic
A
l
g
o
r
ith
m
to
e
n
h
a
n
ce
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
s
p
a
m
d
etec
t
io
n
an
d
class
if
ica
tio
n
[
5
1
]
.
T
h
e
au
th
o
r
s
i
n
[5
1]
p
r
o
p
o
s
ed
a
c
o
m
b
i
n
atio
n
o
f
b
o
th
A
N
N
an
d
G
A
to
co
m
e
u
p
w
it
h
a
n
e
w
h
y
b
r
id
alg
o
r
ith
m
th
at
b
ea
ts
th
e
co
n
v
e
n
tio
n
a
l
ANN.
A
cc
o
r
d
in
g
to
th
e
i
m
p
r
o
v
e
m
en
t
o
n
s
p
a
m
d
etec
ti
o
n
ac
cu
r
ac
y
,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
alg
o
r
ith
m
ca
n
b
e
i
m
p
le
m
e
n
ted
to
d
etec
t
s
p
a
m
m
es
s
ag
e
s
o
n
O
SN
s
.
T
h
e
au
t
h
o
r
s
o
f
[
5
2
]
p
r
o
p
o
s
e
d
a
s
y
s
te
m
th
at
f
o
cu
s
e
d
o
n
t
h
e
m
ai
n
b
o
d
y
o
f
t
h
e
s
p
a
m
a
n
d
ch
ec
k
ed
i
t
w
o
r
d
b
y
w
o
r
d
u
s
i
n
g
A
NN.
E
ac
h
w
o
r
d
i
n
t
h
e
m
es
s
ag
e
is
g
i
v
e
n
a
s
p
ec
if
ic
w
ei
g
h
t
b
ased
o
n
it
s
p
r
o
b
a
b
ilit
y
to
b
e
a
s
p
a
m
w
o
r
d
.
A
cc
o
r
d
in
g
to
t
h
ese
w
ei
g
h
t
s
,
th
e
m
e
s
s
a
g
e
i
s
b
lack
l
is
ted
o
r
w
h
iteli
s
ted
.
I
f
a
m
es
s
ag
e
i
s
b
lack
l
is
ted
,
t
h
en
it
is
s
e
n
t
f
r
o
m
d
o
m
ai
n
s
th
at
ar
e
r
estricte
d
to
s
p
am
m
er
s
.
I
f
th
e
m
es
s
a
g
e
i
s
w
h
iteli
s
ted
,
th
e
n
it is
s
en
t f
r
o
m
tr
u
s
ted
d
o
m
a
in
s
.
I
n
ad
d
itio
n
to
d
is
tin
g
u
is
h
i
n
g
l
eg
iti
m
ate
f
r
o
m
h
a
m
m
e
s
s
a
g
es,
th
i
s
r
esear
c
h
d
ev
elo
p
s
a
tech
n
iq
u
e
u
s
i
n
g
Op
tical
C
h
ar
ac
ter
R
ec
o
g
n
itio
n
(
OC
R
)
to
o
ls
to
ex
tr
ac
t
s
p
am
m
es
s
ag
e
e
m
b
ed
d
ed
in
i
m
a
g
es.
A
cc
o
r
d
in
g
to
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
th
e
t
e
x
t
s
p
a
m
-
d
etec
tio
n
,
an
d
ex
tr
ac
ted
tex
t
f
r
o
m
i
m
a
g
e
s
p
a
m
-
d
etec
t
io
n
a
r
e
v
er
y
i
m
p
o
r
tan
t
to
b
e
u
tili
ze
d
in
So
cial
Net
w
o
r
k
,
b
ec
au
s
e
s
a
m
e
t
y
p
e
s
o
f
s
p
am
ar
e
b
ein
g
s
p
r
ea
d
v
ia
th
e
s
e
Net
w
o
r
k
s
.
A
p
p
l
y
i
n
g
s
u
c
h
s
y
s
te
m
to
OSN
s
p
a
m
d
etec
tio
n
s
u
its
w
i
ll
h
elp
i
n
r
ed
u
cin
g
w
a
s
ted
ti
m
e
a
n
d
m
e
m
o
r
y
a
n
d
w
ill
p
r
o
tect
p
er
s
o
n
al
da
ta
f
r
o
m
b
ein
g
h
ar
m
ed
b
ec
au
s
e
o
f
s
p
a
m
-
s
p
r
ea
d
in
g
.
T
h
e
w
o
r
k
i
n
[
5
3
]
to
o
k
in
to
co
n
s
id
er
atio
n
t
h
e
tas
k
o
f
T
ex
t
C
lass
i
f
icatio
n
(
TC
)
o
f
s
p
a
m
m
e
s
s
ag
e
s
.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
e
d
an
an
ti
-
s
p
a
m
f
il
ter
in
g
s
y
s
te
m
th
at
u
s
e
s
A
NN
f
o
r
m
u
lti
la
y
er
p
r
o
tectio
n
,
an
d
a
Gen
etic
A
l
g
o
r
ith
m
to
tr
ai
n
t
h
eir
p
r
o
tec
tio
n
s
y
s
te
m
.
A
p
p
l
y
i
n
g
t
h
i
s
s
y
s
te
m
s
h
o
w
ed
h
i
g
h
le
v
el
o
f
ac
c
u
r
ac
y
w
h
e
n
u
s
ed
to
d
is
tin
g
u
is
h
h
a
m
m
es
s
a
g
es
f
r
o
m
s
p
a
m
m
e
s
s
a
g
es.
Fro
m
th
is
r
esear
ch
,
w
e
d
er
i
v
e
t
h
at
s
u
b
j
e
ct
an
d
b
o
d
y
f
ield
s
al
w
a
y
s
co
n
tai
n
s
p
ec
if
ic
in
d
ica
tio
n
s
t
h
at
ea
s
e
t
h
e
p
r
o
ce
s
s
o
f
d
is
tin
g
u
is
h
i
n
g
h
a
m
f
r
o
m
s
p
am
m
es
s
ag
e
s
.
O
n
t
h
e
o
th
er
h
a
n
d
,
th
is
s
y
s
te
m
p
r
o
v
e
d
th
at
1
5
-
3
0
h
id
d
en
n
e
u
tr
o
n
s
ar
e
g
o
o
d
en
o
u
g
h
to
p
r
o
ce
s
s
ea
s
y
m
es
s
ag
e
s
an
d
class
i
f
y
th
e
m
.
I
n
So
cial
Me
d
ia,
th
is
s
y
s
te
m
ca
n
b
e
u
ti
lized
to
d
etec
t
s
p
am
m
e
s
s
a
g
es
i
f
au
th
o
r
s
s
o
lv
ed
t
h
e
p
r
o
b
lem
o
f
lo
n
g
d
etec
tio
n
ti
m
e.
An
o
th
er
h
y
b
r
id
A
NN
w
as
p
r
o
p
o
s
ed
by
[
5
4
]
.
I
n
t
h
is
r
ese
ar
ch
,
t
h
e
y
u
s
ed
R
ad
ial
B
as
is
Fu
n
ctio
n
Neu
r
al
Net
w
o
r
k
s
(
R
B
FNN)
alo
n
g
w
i
th
P
ar
ticle
S
w
ar
m
Op
ti
m
izatio
n
(
P
SO
)
to
r
ea
ch
b
etter
ac
cu
r
ac
y
an
d
ef
f
ec
tiv
e
n
e
s
s
.
T
h
is
m
et
h
o
d
is
v
er
y
ap
p
r
o
p
r
iate
to
b
e
u
tili
z
ed
in
OSN
s
b
ec
au
s
e
it
u
s
e
d
i
m
p
r
o
v
ed
n
et
w
o
r
k
ar
ch
itect
u
r
e
an
d
lear
n
in
g
al
g
o
r
ith
m
.
I
n
[
5
5
]
,
th
e
au
th
o
r
s
p
r
o
p
o
s
e
d
an
o
th
er
m
u
lti
la
y
er
A
N
N
m
et
h
o
d
,
an
d
th
e
y
ca
lled
it
"
an
tid
o
te.
"
T
h
is
m
et
h
o
d
is
v
er
y
s
p
ec
ial
b
ec
au
s
e
it
i
s
d
esig
n
ed
to
s
er
v
e
ea
c
h
u
s
er
b
y
u
s
i
n
g
h
i
s
c
h
o
s
en
p
ar
am
eter
s
to
s
et
an
ap
p
r
o
p
r
iate
m
u
ltil
a
y
er
A
NN
ac
co
r
d
in
g
to
w
h
ich
m
e
s
s
a
g
es
ar
e
g
o
i
n
g
t
o
b
e
class
if
ied
i
n
to
s
p
a
m
a
n
d
leg
i
ti
m
ate
m
es
s
ag
es.
T
h
is
s
y
s
te
m
ca
n
b
e
a
ppl
ied
t
o
So
cial
Me
d
ia
s
ec
u
r
i
t
y
s
u
i
tes
d
u
e
to
it
s
f
le
x
ib
ilit
y
an
d
s
h
o
r
t le
ar
n
i
n
g
ti
m
e
.
A
N
Ns
h
av
e
g
r
ea
t
p
o
te
n
tial
i
n
OS
Ns
i
n
tr
u
s
io
n
d
etec
tio
n
;
u
n
f
o
r
tu
n
atel
y
,
t
h
e
y
h
a
v
e
n
o
t
b
ee
n
f
u
ll
y
in
v
e
s
ti
g
ated
in
t
h
e
liter
atu
r
e
.
I
n
g
en
er
al,
I
DS
s
ca
n
ca
tch
m
i
s
u
s
es
an
d
s
to
p
th
e
m
f
r
o
m
ca
u
s
in
g
d
a
m
a
g
es.
Fo
r
th
e
s
a
m
e
r
ea
s
o
n
s
,
A
NN
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
m
et
h
o
d
s
c
an
b
e
ap
p
lied
,
w
it
h
s
o
m
e
m
o
d
if
icatio
n
s
,
to
So
cial
Ne
t
w
o
r
k
p
latf
o
r
m
s
.
Al
-
J
ar
r
ah
an
d
A
r
af
a
t
[
5
6
]
u
s
ed
T
i
m
e
Dela
y
D
y
n
a
m
ic
A
r
ti
f
ici
al
Neu
r
al
Net
w
o
r
k
(
T
DDNN
)
to
id
en
tify
ea
c
h
at
tack
b
eh
a
v
io
r
.
T
h
e
y
d
es
ig
n
ed
th
eir
s
y
s
te
m
to
g
e
n
er
ate
aler
ts
w
h
en
t
h
e
A
NN
class
i
f
ier
r
ec
o
g
n
izes
a
n
attac
k
.
P
r
o
d
u
cin
g
t
h
e
attac
k
f
ea
tu
r
es
tak
es
s
h
o
r
t
a
n
d
co
n
s
ta
n
t
ti
m
e
s
tar
t
in
g
f
r
o
m
r
ec
o
g
n
izi
n
g
t
h
e
attac
k
p
r
esen
ce
to
g
e
n
er
ati
n
g
t
h
e
attac
k
al
er
t.
B
ec
au
s
e
o
f
it
s
f
a
s
t
i
n
tr
u
s
i
o
n
r
ec
o
g
n
itio
n
,
th
is
s
y
s
te
m
i
s
v
er
y
co
m
p
at
ib
le
w
it
h
So
cial
Net
w
o
r
k
s
s
ec
u
r
i
t
y
an
d
p
r
iv
ac
y
n
e
ed
s
,
esp
ec
iall
y
b
ec
au
s
e
OSN
attac
k
er
s
ar
e
v
er
y
a
g
g
r
ess
iv
e
.
Qiu
a
n
d
S
h
a
n
[
5
7
]
u
s
ed
m
u
lti
p
ly
s
w
ar
m
o
p
ti
m
izatio
n
-
b
ac
k
p
r
o
p
ag
atio
n
MP
SO
-
B
P
n
e
u
r
al
n
et
w
o
r
k
f
o
r
th
eir
p
r
o
p
o
s
ed
m
o
d
el
o
f
in
tr
u
s
io
n
d
etec
tio
n
.
P
SO
alg
o
r
ith
m
i
s
u
s
ed
to
o
p
tim
ize
b
ac
k
p
r
o
p
ag
atio
n
A
N
N’
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
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
:
275
-
287
282
p
ar
am
eter
s
.
T
h
u
s
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
s
h
o
w
ed
a
n
i
m
p
r
o
v
ed
ef
f
ec
t
o
n
t
h
e
i
n
tr
u
s
io
n
d
etec
tio
n
r
ates
i
n
co
m
p
ar
is
o
n
w
it
h
P
SO
-
B
P
n
eu
r
al
n
et
w
o
r
k
an
d
B
P
n
eu
r
al
n
et
w
o
r
k
.
T
h
is
m
o
d
el
is
s
u
itab
le
f
o
r
So
cial
Netw
o
r
k
P
latf
o
r
m
s
,
b
ec
a
u
s
e
i
t
ca
n
h
a
n
d
le
s
ig
n
i
f
ica
n
t
a
m
o
u
n
t
s
o
f
d
ata
s
i
m
u
ltan
eo
u
s
l
y
;
i
n
ad
d
itio
n
to
its
in
d
ep
en
d
e
n
t
lear
n
in
g
a
n
d
r
eg
u
lar
d
atab
ase
u
p
d
ates.
In
[
5
8
]
,
th
e
au
t
h
o
r
s
p
r
o
p
o
s
ed
s
u
p
er
v
i
s
ed
b
ac
k
p
r
o
p
ag
atio
n
A
N
N
b
ased
An
o
m
al
y
Dete
ct
i
o
n
S
y
s
te
m
.
T
h
eir
s
y
s
te
m
ai
m
s
to
ca
tc
h
all
atte
m
p
ted
a
n
o
m
alies
an
d
k
ee
p
all
d
ata
co
m
p
lete
l
y
s
a
f
e
a
n
d
it
co
n
ce
n
tr
ate
s
o
n
th
e
h
ier
ar
ch
y
an
o
m
al
y
I
DS.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
s
h
o
w
e
d
h
ig
h
er
ac
cu
r
ac
y
,
ef
f
ic
ien
c
y
,
an
d
p
er
f
o
r
m
an
ce
b
ec
au
s
e
th
e
y
u
s
e
o
n
l
y
1
7
KDD
9
9
f
ea
tu
r
es.
T
h
e
y
f
o
llo
w
ed
f
ea
tu
r
e
s
r
ed
u
ctio
n
tec
h
n
iq
u
e
th
at
ar
e
ap
p
r
o
p
r
iate
f
o
r
So
cial
Net
w
o
r
k
P
latf
o
r
m
s
as
ac
cu
r
ac
y
r
ea
ch
es
9
8
%
an
d
tr
ain
in
g
an
d
test
i
n
g
ti
m
e
is
r
ed
u
ce
d
to
th
e
m
i
n
i
m
u
m
.
In
[
5
9
]
,
th
e
a
u
t
h
o
r
s
co
m
p
ar
e
d
th
e
ac
c
u
r
ac
y
ac
h
iev
ed
b
y
ap
p
ly
i
n
g
s
e
v
er
al
m
et
h
o
d
s
to
A
n
o
m
al
y
Dete
ctio
n
S
y
s
te
m
.
T
h
e
m
e
th
o
d
s
th
e
y
s
t
u
d
ied
in
th
eir
w
o
r
k
ar
e
Gen
etic
A
l
g
o
r
ith
m
w
i
th
A
r
tific
ial
Neu
r
a
l
Net
w
o
r
k
(
GA
-
A
N
N
)
C
las
s
if
i
er
th
at
u
s
ed
1
8
f
ea
tu
r
es.
Oth
er
m
et
h
o
d
s
th
e
y
u
s
ed
ar
e
th
e
Mo
d
if
ied
Mu
tu
al
I
n
f
o
r
m
a
tio
n
Feat
u
r
e
S
elec
tio
n
(
MM
lFS
)
wi
th
2
4
f
ea
tu
r
e
s
,
L
in
ea
r
C
o
r
r
elatio
n
Feat
u
r
e
Sele
ctio
n
(
L
C
FS
)
w
it
h
2
1
f
ea
tu
r
es,
a
n
d
Fo
r
w
ar
d
Fe
atu
r
e
Select
io
n
(
F
FS
)
w
it
h
3
1
f
ea
tu
r
e
s
.
A
cc
o
r
d
in
g
to
t
h
ei
r
s
tu
d
y
,
G
A
-
A
NN
c
lass
i
f
ier
r
aised
t
h
e
ac
c
u
r
ac
y
o
f
d
etec
tin
g
a
n
o
m
a
lies
to
th
e
m
a
x
i
m
u
m
o
f
9
9
%
m
a
k
in
g
it
a
n
e
x
ce
lle
n
t
ca
n
d
id
ate
f
o
r
So
cial
Net
w
o
r
k
P
latf
o
r
m
s
.
6.
DE
T
E
C
T
I
O
N
O
F
M
AL
I
C
I
O
US
AC
T
I
VI
T
I
E
S
AND
CO
M
M
UNIT
I
E
S’
B
E
H
A
VIOR
O
V
E
R
O
SNs
I
n
g
en
er
al,
t
h
e
OSN
m
ali
cio
u
s
co
m
m
u
n
ities
s
h
ar
e
m
an
y
o
f
t
h
e
f
o
llo
w
in
g
d
is
tin
g
u
i
s
h
in
g
o
b
s
er
v
atio
n
s
:
a.
So
cial
m
ed
ia
s
p
a
m
m
er
s
a
r
e
th
e
m
o
s
t p
er
s
p
icac
io
u
s
a
m
o
n
g
al
l k
in
d
s
o
f
s
p
a
m
m
er
s
.
b.
4
0
% o
f
all
s
o
cial
m
ed
ia
ac
co
u
n
ts
ar
e
m
ar
k
ed
as sp
a
m
ac
co
u
n
ts
.
c.
No
w
ad
a
y
s
,
m
o
s
t
o
f
m
alicio
u
s
co
n
ten
t
s
ar
e
b
ein
g
s
en
t
an
d
s
h
a
r
ed
b
y
au
to
m
ated
s
p
a
m
m
in
g
to
o
ls
.
Su
c
h
to
o
ls
s
e
n
d
s
p
a
m
e
f
f
ic
ien
t
l
y
esp
ec
iall
y
w
h
en
tar
g
eti
n
g
g
r
o
u
p
s
o
f
u
s
er
s
.
d.
Sp
a
m
ac
co
u
n
t
s
te
n
d
to
b
e
co
n
n
ec
ted
(
Frie
n
d
s
o
r
f
o
llo
w
i
n
g
ea
ch
o
t
h
er
)
,
b
ec
au
s
e
t
h
e
y
u
s
u
all
y
s
e
n
d
f
o
llo
w
in
g
a
n
d
f
r
ien
d
s
h
ip
r
eq
u
ests
w
it
h
n
o
s
p
ec
i
f
ic
co
n
s
id
er
atio
n
to
th
e
q
u
alit
y
o
f
th
e
ac
co
u
n
ts
t
h
e
y
co
n
tact.
e.
Sp
a
m
m
in
g
ac
co
u
n
ts
ten
d
to
a
cc
ep
t
all
f
r
ien
d
r
eq
u
e
s
ts
th
e
y
r
ec
eiv
e
a
n
d
f
o
llo
w
b
ac
k
a
ll
ac
c
o
u
n
t
s
t
h
e
y
f
o
llo
w
th
e
m
.
f.
W
h
en
t
h
er
e
is
a
s
p
ec
if
ic
i
n
n
e
r
r
elatio
n
s
h
ip
b
et
w
ee
n
s
p
a
m
m
in
g
ac
co
u
n
ts
o
v
er
s
o
cial
n
et
wo
r
k
s
,
th
e
y
ca
n
b
e
ex
p
o
s
ed
ea
s
il
y
.
g.
Sp
a
m
m
in
g
ac
co
u
n
ts
s
h
ar
e
to
p
i
cs t
h
at
at
tr
a
ct
t
h
e
tar
g
eted
v
ict
i
m
s
,
an
d
th
e
s
e
to
p
ics
ar
e
u
s
u
al
l
y
s
i
m
ilar
ac
r
o
s
s
m
o
s
t o
f
t
h
e
s
p
a
m
m
in
g
ac
co
u
n
t
s
.
On
e
i
n
ter
esti
n
g
to
p
ic
is
to
f
ak
e
ce
leb
r
itie
s
’
ac
co
u
n
ts
.
h.
Ma
licio
u
s
ac
co
u
n
ts
te
n
d
to
s
tay
ac
t
iv
e
f
o
r
p
r
o
tr
ac
ted
p
er
io
d
s
an
d
k
ee
p
d
am
ag
in
g
as
lo
n
g
as
th
e
y
ar
e
ac
tiv
e.
i.
Sp
a
m
m
er
s
s
ea
r
ch
all
p
o
p
u
lar
ac
co
u
n
t
s
to
r
ea
ch
th
e
p
r
iv
ate
in
f
o
r
m
atio
n
o
f
t
h
eir
f
o
llo
w
er
s
o
r
f
r
ien
d
s
an
d
u
s
e
t
h
e
m
in
t
h
eir
cr
i
m
e
s
.
6
.
1
.
Cliqu
e
-
ba
s
e
d
det
ec
t
io
n
m
et
ho
do
lo
g
y
An
O
SN
u
s
er
is
u
s
u
al
l
y
r
ep
r
es
en
ted
b
y
a
n
ac
co
u
n
t
o
r
a
p
r
o
f
il
e.
T
h
e
p
r
o
f
ile
d
escr
ib
es th
e
u
s
er
'
s
s
o
cial
r
elate
d
attr
ib
u
tes
th
at
i
n
cl
u
d
e
h
is
o
r
h
er
n
a
m
e,
th
e
li
s
t
o
f
c
o
n
tacts,
an
d
t
h
eir
h
o
b
b
ies
o
r
in
ter
est
s
.
T
h
e
r
e
ar
e
t
w
o
t
y
p
e
s
o
f
r
elatio
n
s
h
ip
s
b
et
w
ee
n
t
h
e
ac
co
u
n
ts
:
it
co
u
ld
b
e
eith
er
o
n
e
s
id
ed
as
in
T
w
it
ter
o
r
co
u
ld
b
e
t
w
o
-
s
id
ed
as
ca
n
b
e
s
ee
n
i
n
F
ac
eb
o
o
k
f
r
ien
d
s
h
ip
s
.
A
s
m
e
n
t
io
n
ed
ea
r
lier
,
th
e
o
n
li
n
e
s
o
cial
n
et
w
o
r
k
u
s
er
s
ca
n
s
h
ar
e
v
id
eo
s
,
p
h
o
to
s
,
lo
ca
tio
n
s
an
d
ev
en
m
o
r
e
p
er
s
o
n
al
i
n
f
o
r
m
at
io
n
s
u
ch
as
b
ir
th
d
a
y
s
a
n
d
p
h
o
n
e
n
u
m
b
er
s
.
I
t
is
w
o
r
th
p
o
in
ti
n
g
o
u
t
th
a
t
ev
en
Face
b
o
o
k
an
d
T
w
itt
er
ar
e
am
o
n
g
th
e
m
o
s
t
p
o
p
u
lar
OSNs
,
th
er
e
ar
e
o
th
er
o
n
lin
e
s
o
cial
p
lat
f
o
r
m
s
s
u
c
h
a
s
Go
o
g
le+
a
n
d
L
i
n
k
ed
I
n
.
S
u
c
h
n
et
w
o
r
k
s
h
elp
u
s
er
s
f
r
o
m
d
if
f
er
en
t
g
eo
g
r
ap
h
ical
ar
ea
s
to
s
tay
co
n
n
ec
ted
.
Mo
r
eo
v
er
,
th
ese
o
n
li
n
e
n
et
w
o
r
k
s
allo
w
t
h
eir
u
s
er
s
to
estab
lis
h
n
e
w
r
elat
io
n
s
w
i
th
d
if
f
er
e
n
t
p
eo
p
le
all
o
v
er
th
e
wo
r
ld
w
h
o
h
a
v
e
s
i
m
ilar
i
n
ter
est
s
in
cl
u
d
in
g
t
h
e
s
a
m
e
p
r
o
f
ess
io
n
o
r
h
o
b
b
ies.
O
n
li
n
e
s
o
cial
n
et
w
o
r
k
s
ca
n
b
e
r
ep
r
esen
ted
as
a
s
o
cial
g
r
ap
h
.
L
et’
s
ass
u
m
e
th
e
g
r
o
u
p
o
f
u
s
er
s
w
it
h
i
n
a
ce
r
tain
s
o
cial
n
e
t
w
o
r
k
co
n
s
i
s
ts
o
f
t
h
r
ee
u
s
er
s
w
h
o
ar
e
r
ep
r
esen
ted
a
s
n
o
d
es
{
A
,
B
,
C
}
o
n
t
h
at
n
et
w
o
r
k
.
T
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
th
e
s
e
u
s
er
s
ar
e
r
ep
r
esen
ted
b
y
ed
g
es.
T
h
is
s
o
cial
g
r
ap
h
ca
n
b
e
u
s
e
d
to
id
en
tify
“
tie
s
”
b
et
w
ee
n
t
h
e
u
s
er
s
(
n
o
d
es).
T
h
ese
ties
co
u
ld
g
i
v
e
co
m
m
o
n
d
etails
a
n
d
i
n
ter
est
s
o
f
th
e
g
r
o
u
p
m
e
m
b
er
s
s
u
c
h
as
th
eir
g
en
d
er
,
p
er
s
o
n
al
i
n
ter
est
s
,
s
p
o
r
ts
,
ed
u
ca
tio
n
le
v
el,
an
d
m
a
n
y
o
th
er
i
m
p
o
r
tan
t
d
etail
s
.
No
w
,
tec
h
n
icall
y
s
p
ea
k
i
n
g
th
e
s
e
g
r
o
u
p
s
o
v
er
o
n
li
n
e
s
o
cial
n
et
w
o
r
k
s
t
h
at
h
a
v
e
all
t
h
e
u
s
er
s
as
f
r
ie
n
d
s
ar
e
ca
lled
s
o
m
eti
m
e
s
cliq
u
es.
Fi
g
u
r
e
4
s
h
o
w
s
t
h
e
s
o
cial
g
r
ap
h
w
ith
e
v
er
y
u
s
er
be
f
r
ien
d
in
g
all
th
e
o
th
er
u
s
er
s
w
it
h
in
t
h
i
s
g
r
o
u
p
.
T
h
e
u
s
er
s
(
n
o
d
es)
{
A
,
B
,
C
,
D,
E
}
ar
e
all
f
r
ien
d
s
o
f
ea
c
h
o
t
h
e
r
an
d
s
o
t
h
e
y
ar
e
ca
lled
cliq
u
es.
T
o
clar
if
y
t
h
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
S
ec
u
r
ity
tech
n
iq
u
es fo
r
in
tellig
en
t sp
a
m
s
en
s
in
g
a
n
d
a
n
o
ma
ly
d
ete
ctio
n
in
o
n
lin
e
...
(
Mo
n
th
er A
ld
w
a
ir
i)
283
co
n
ce
p
t
o
f
cl
iq
u
es,
Fi
g
u
r
e
5
s
h
o
w
s
t
h
e
s
a
m
e
u
s
er
s
w
it
h
i
n
t
h
e
s
a
m
e
g
r
o
u
p
r
ep
r
ese
n
ted
as
n
o
d
es
o
n
t
h
e
s
o
cia
l
g
r
ap
h
,
b
u
t
t
h
e
y
ar
e
n
o
t
cliq
u
e
f
o
r
ea
ch
o
th
er
.
A
s
ca
n
b
e
s
e
en
f
r
o
m
th
e
f
i
g
u
r
e,
t
h
e
u
s
er
s
C
,
D,
an
d
E
ar
e
n
o
t
f
r
ien
d
s
f
o
r
ea
ch
o
th
er
.
F
ig
u
r
e
4
.
Fiv
e
C
liq
u
e
User
s
o
n
a
So
cial
Gr
ap
h
F
ig
u
r
e
5
.
Fiv
e
No
n
-
C
liq
u
e
U
s
er
s
o
n
a
So
cial
G
r
ap
h
As
it
is
k
n
o
w
n
,
t
h
e
u
s
er
s
o
f
o
n
li
n
e
s
o
cial
n
et
w
o
r
k
s
s
p
en
d
g
o
o
d
am
o
u
n
t
o
f
t
h
eir
ti
m
e
s
o
ci
al
izin
g
w
i
th
f
r
ien
d
s
a
n
d
p
eo
p
le
w
h
o
m
t
h
e
y
s
h
ar
e
th
e
s
a
m
e
in
ter
e
s
ts
w
it
h
.
T
h
er
e
is
a
h
i
g
h
p
o
s
s
ib
ili
t
y
t
h
at
s
o
m
e
m
alicio
u
s
b
eh
av
io
r
o
r
th
o
u
g
h
ts
an
d
p
o
s
ts
m
i
g
h
t
tak
e
p
lace
w
it
h
i
n
th
ese
s
o
cial
izatio
n
ac
ti
v
iti
es.
Her
e
co
m
es
th
e
i
m
p
o
r
tan
t
r
o
le
o
f
t
h
e
s
o
cial
g
r
ap
h
s
to
b
u
ild
a
tr
u
s
t
w
o
r
t
h
in
e
s
s
m
o
d
el
b
ased
o
n
d
if
f
er
en
t
s
o
cial
ac
tiv
itie
s
t
h
a
t
tak
e
p
lace
b
et
w
ee
n
u
s
er
s
w
i
th
in
t
h
e
s
a
m
e
g
r
o
u
p
[
6
0
].
I
t
is
b
eliev
ed
th
at
t
h
e
s
o
cial
g
r
ap
h
s
ca
n
b
e
co
n
s
tr
u
c
ted
s
p
ec
iall
y
b
et
w
ee
n
cliq
u
es
to
ca
p
tu
r
e
d
if
f
er
en
t
t
y
p
e
s
o
f
s
o
cial
ac
t
iv
ities
.
T
h
ese
ac
tiv
it
ies
r
an
g
e
f
r
o
m
j
u
s
t
r
et
w
ee
ti
n
g
to
p
o
s
ti
n
g
n
e
w
t
wee
ts
[
6
1
]
.
A
ls
o
,
ac
ti
v
it
ies
to
b
e
m
o
n
ito
r
ed
an
d
ca
p
t
u
r
ed
in
clu
d
e
s
h
ar
in
g
f
al
s
e
in
f
o
r
m
atio
n
,
v
ir
al
i
m
ag
e
s
an
d
v
id
eo
s
o
n
Face
b
o
o
k
an
d
o
th
er
s
o
cial
p
latf
o
r
m
s
.
U
s
in
g
s
o
cial
g
r
ap
h
s
,
w
e
ca
n
p
r
o
p
o
s
e
m
a
n
y
le
v
els
o
f
tr
u
s
t
w
o
r
th
in
e
s
s
.
Af
ter
th
a
t,
m
alic
io
u
s
ac
tiv
itie
s
ca
n
b
e
d
etec
ted
b
ased
o
n
th
eir
lev
el
o
f
tr
u
s
t
w
o
r
th
in
e
s
s
.
I
n
o
t
h
er
w
o
r
d
s
,
th
e
u
s
er
s
an
d
th
eir
s
o
cial
r
elatio
n
s
h
ip
s
an
d
ac
tiv
it
ies
o
v
er
t
h
e
o
n
li
n
e
s
o
cial
n
et
w
o
r
k
s
ar
e
g
r
o
u
p
ed
as
d
is
tin
g
u
is
h
ed
en
t
i
ties
.
An
d
s
o
,
by
m
ea
s
u
r
in
g
h
o
w
m
u
c
h
ea
ch
s
o
cial
ac
tiv
it
y
i
s
tr
u
s
t
f
u
l
,
w
e
ca
n
d
is
ti
n
g
u
is
h
t
h
e
le
g
iti
m
ate
a
cti
v
itie
s
f
r
o
m
t
h
e
m
alicio
u
s
ac
tiv
itie
s
w
it
h
in
t
h
e
cliq
u
e
n
et
w
o
r
k
.
Fi
g
u
r
e
6
s
h
o
w
s
t
h
e
d
if
f
er
en
t
m
et
h
o
d
s
u
s
ed
to
d
etec
t
m
alicio
u
s
ac
ti
v
itie
s
o
v
er
o
n
lin
e
s
o
cial
n
et
w
o
r
k
s
in
clu
d
in
g
t
h
e
s
o
cial
g
r
ap
h
.
Fig
u
r
e
6
.
Me
th
o
d
s
to
D
etec
t
Ma
licio
u
s
A
ct
iv
i
ties
o
v
er
OS
Ns
T
h
e
o
th
er
d
etec
tio
n
ap
p
r
o
ac
h
i
s
u
s
i
n
g
t
h
e
Ma
c
h
i
n
e
L
ea
r
n
in
g
tech
n
iq
u
es
,
w
h
ich
ca
n
b
e
cla
s
s
if
ied
i
n
to
s
u
p
er
v
i
s
ed
m
et
h
o
d
s
an
d
u
n
s
u
p
er
v
i
s
ed
m
et
h
o
d
s
.
T
h
e
d
i
f
f
er
en
ce
b
et
w
ee
n
t
h
e
t
w
o
ca
teg
o
r
ies
is
t
h
at
th
e
s
u
p
er
v
i
s
ed
m
et
h
o
d
s
u
s
e
p
r
ep
ar
ed
s
et
o
f
d
ata
f
o
r
tr
ain
i
n
g
a
n
d
p
r
ed
ictin
g
th
e
m
o
d
el,
w
h
i
le
in
th
e
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
s
th
er
e
w
il
l
b
e
n
o
d
ata
u
s
ed
f
o
r
tr
a
in
i
n
g
.
E
x
a
m
p
les
o
f
t
h
e
f
ir
s
t
ca
teg
o
r
y
i
n
cl
u
d
e:
r
eg
r
ess
io
n
m
o
d
els,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
,
an
d
d
ec
is
io
n
tr
ee
m
o
d
els.
E
x
a
m
p
le
s
o
f
th
e
u
n
s
u
p
er
v
is
e
d
lear
n
in
g
in
cl
u
d
e:
cl
u
s
ter
in
g
alg
o
r
ith
m
s
an
d
h
id
d
en
Ma
r
k
o
v
m
o
d
els.
T
h
er
e
is
a
n
o
th
er
m
ac
h
i
n
e
lear
n
in
g
ca
teg
o
r
y
t
h
at
u
s
e
s
co
m
b
i
n
atio
n
s
o
f
t
h
e
ab
o
v
e
t
w
o
ca
teg
o
r
ize
s
an
d
s
o
it is
ca
lled
s
e
m
i
-
s
u
p
er
v
is
ed
m
eth
o
d
.
T
h
e
th
ir
d
m
alicio
u
s
ac
ti
v
itie
s
d
etec
tio
n
tech
n
iq
u
e
is
t
h
r
o
u
g
h
u
s
i
n
g
m
a
n
u
al
v
er
if
ica
tio
n
.
T
h
e
co
n
ten
t
s
h
o
u
ld
b
e
a
n
al
y
s
ed
to
m
a
k
e
s
u
r
e
i
f
i
t
i
s
f
ak
e
o
r
le
g
iti
m
ate
,
t
h
er
ef
o
r
e
i
s
t
h
e
OSNs
u
s
er
s
’
ta
s
k
to
d
o
u
b
le
c
h
ec
k
th
e
co
n
ten
ts
b
e
f
o
r
e
s
p
r
ea
d
in
g
it
to
o
t
h
er
u
s
er
s
.
As
p
ar
t
o
f
t
h
e
m
a
n
u
al
v
er
i
f
icatio
n
p
r
o
ce
s
s
,
s
o
m
e
s
o
cial
o
n
li
n
e
p
latf
o
r
m
s
allo
w
t
h
eir
u
s
e
r
s
to
r
ep
o
r
t
co
n
ten
t
th
a
t
v
io
lates
t
h
eir
p
r
iv
ac
y
r
u
le
s
.
S
u
ch
v
io
la
tin
g
co
n
te
n
t
m
i
g
h
t
in
cl
u
d
e
m
al
w
ar
e
li
n
k
s
,
s
p
a
m
,
an
d
a
g
g
r
ess
i
v
e
o
r
ab
u
s
i
v
e
c
o
n
ten
t.
Mo
r
eo
v
er
,
m
a
n
y
s
o
cial
n
et
w
o
r
k
s
as
k
t
h
e
f
ee
d
b
ac
k
f
r
o
m
th
e
u
s
er
s
to
en
h
an
ce
t
h
eir
p
r
iv
ac
y
p
o
licie
s
.
•
De
ve
l
o
p
i
n
g
tr
u
s
tw
o
rt
h
i
n
e
s
s
mo
d
e
l
b
e
tw
e
e
n
c
l
i
q
u
e
s
G
ra
p
h
-
b
ase
d
•
S
u
p
e
rvi
s
e
d
Me
th
o
d
s
•
Un
s
u
p
e
rvi
s
e
d
Me
th
o
d
s
Ma
ch
in
e
Learn
in
g
•
R
e
p
o
rt
i
n
g
an
y s
u
s
p
i
c
i
o
u
s
ac
ti
vit
i
e
s
•
Us
e
rs
fee
d
b
ac
k
to
th
e
O
S
N
ad
min
s
tr
ato
rs
Ma
n
u
al
Ve
rif
icatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
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
:
275
-
287
284
6
.
2
.
Resul
t
s
a
n
d d
is
c
us
s
io
ns
Fo
r
e
ac
h
en
ti
t
y
i
n
t
h
e
s
o
cial
g
r
ap
h
th
e
t
r
u
s
t
w
o
r
t
h
in
e
s
s
s
co
r
e
w
i
ll
b
e
ca
lcu
la
ted
.
No
w
,
i
f
t
h
at
s
co
r
e
is
b
elo
w
a
ce
r
tain
th
r
es
h
o
ld
,
th
e
n
w
e
ca
n
p
r
ed
ict
w
it
h
h
i
g
h
co
n
f
id
e
n
ce
th
at
t
h
e
ac
tiv
ities
a
s
s
o
ciate
d
w
ith
t
h
i
s
en
tit
y
w
ill
b
e
m
alic
io
u
s
a
n
d
ca
n
’
t
b
e
tr
u
s
ted
.
On
e
m
a
in
s
o
cial
g
r
ap
h
p
r
o
p
er
ty
is
th
e
Dia
m
eter
,
w
h
ich
i
s
d
ef
in
ed
to
b
e
th
e
g
r
ea
t
est
d
is
ta
n
ce
b
et
w
ee
n
an
y
t
w
o
n
o
d
es
o
n
th
e
g
r
ap
h
.
I
n
o
r
d
er
to
f
in
d
th
e
d
iam
eter
,
f
ir
s
t
w
e
n
ee
d
to
f
in
d
t
h
e
s
h
o
r
tes
t
p
ath
b
et
w
ee
n
a
ny
p
air
o
f
n
o
d
es
in
th
e
s
o
cial
g
r
ap
h
f
o
r
all
n
o
d
es.
T
h
en
w
e
tak
e
th
e
m
a
x
i
m
u
m
len
g
t
h
o
f
all
th
e
s
e
s
h
o
r
test
p
at
h
s
.
As a
n
e
x
a
m
p
le,
let
th
e
le
n
g
t
h
b
et
w
ee
n
a
n
y
t
w
o
n
o
d
es (
x
,
y
)
o
n
th
e
g
r
ap
h
to
b
e
l
en
.
T
h
en
th
e
d
ia
m
eter
,
d
ia
m
,
is
:
d
ia
m
=
m
a
x
l
en
(
x
,
y
)
f
o
r
all
p
o
s
s
ib
le
n
o
d
es o
n
t
h
e
s
o
cial
g
r
ap
h
T
h
e
u
s
a
g
e
o
f
c
l
iq
u
es
is
p
o
p
u
l
ar
in
g
r
ap
h
-
b
a
s
ed
an
al
y
s
i
s
ar
e
as
in
c
lu
d
i
n
g
th
e
s
o
cial
n
et
w
o
r
k
s
i
n
o
r
d
er
to
u
n
d
er
s
ta
n
d
co
n
n
ec
tio
n
s
a
n
d
tr
u
s
t
r
elatio
n
s
b
et
w
ee
n
g
r
ap
h
n
o
d
e
s.
A
s
a
n
al
g
o
r
ith
m
,
cliq
u
e
ca
lcu
la
tes
th
e
m
a
x
i
m
u
m
n
u
m
b
er
o
f
n
o
d
es
i
n
t
h
e
g
r
ap
h
i
n
w
h
ic
h
e
v
er
y
n
o
d
e
in
th
e
c
liq
u
e
is
a
f
r
ien
d
t
o
all
o
th
er
n
o
d
es
i
n
th
e
c
liq
u
e
.
Fi
g
u
r
e
7
s
h
o
w
s
t
h
e
to
tal
an
d
w
ei
g
h
ted
cliq
u
e
s
tr
e
n
g
th
.
Fig
u
r
e
7
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
t
o
tal
an
d
n
o
r
m
alize
d
/
w
ei
g
h
t
ed
c
liq
u
e
s
tr
en
g
th
s
I
t
is
clea
r
th
at
e
x
tr
ac
ti
n
g
cliq
u
e
r
elatio
n
s
i
n
OS
Ns
ca
p
t
u
r
es
g
r
o
u
p
s
p
r
o
p
er
ties
an
d
h
o
w
t
h
e
y
i
n
ter
ac
t
w
it
h
ea
ch
o
t
h
er
.
L
ar
g
er
cliq
u
e
s
m
a
y
co
n
tai
n
s
m
a
ll
er
cliq
u
es
an
d
th
e
r
esear
ch
er
’
s
f
o
cu
s
s
h
o
u
ld
b
e
o
n
f
in
d
in
g
th
e
m
a
x
i
m
u
m
cliq
u
e
s
ize
.
Ou
r
m
ai
n
co
n
tr
ib
u
tio
n
w
as
n
o
r
m
alizin
g
cliq
u
e
s
tr
e
n
g
th
s
to
g
iv
e
b
etter
ass
ess
m
en
t
o
f
u
s
er
’
s
tr
u
s
t
w
o
r
t
h
i
n
ess
a
n
d
u
s
er
s
ac
tiv
ities
a
n
d
in
ter
ac
tio
n
w
it
h
i
n
a
cliq
u
e
.
7.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
ad
d
r
ess
ed
th
e
i
m
p
o
r
tan
t
i
s
s
u
e
o
f
s
ec
u
r
it
y
an
d
p
r
iv
ac
y
i
n
O
n
li
n
e
So
cial
Net
w
o
r
k
s
.
W
h
at
m
a
k
es
s
ec
u
r
in
g
i
n
f
o
r
m
atio
n
i
n
OSN
m
o
r
e
co
m
p
lica
ted
is
th
e
h
eter
o
g
e
n
eo
u
s
w
e
b
ap
p
licatio
n
s
an
d
p
r
o
to
co
ls
u
s
ed
,
an
d
v
ar
iety
o
f
m
o
b
ile
ap
p
s
p
latf
o
r
m
s
s
u
c
h
as
A
n
d
r
o
id
o
r
iOS
u
s
ed
to
ac
ce
s
s
OSN
s
.
W
e
in
v
e
s
ti
g
ated
th
e
n
ee
d
to
ap
p
ly
C
o
m
p
u
tatio
n
al
I
n
te
lli
g
en
ce
tech
n
iq
u
es
i
n
O
SNs
s
ec
u
r
it
y
b
ec
au
s
e
tr
ad
itio
n
al
s
ec
u
r
it
y
tec
h
n
iq
u
es
ar
e
n
o
t
ef
f
icien
t
e
n
o
u
g
h
to
p
r
o
v
id
e
co
m
p
lete
-
p
r
o
tectio
n
ag
ai
n
s
t
r
ec
en
t
c
y
b
er
-
attac
k
s
[
6
3
]
.
Th
is
r
esear
ch
to
o
k
A
r
t
if
ic
ial
Neu
r
al
Net
w
o
r
k
s
a
n
d
Ma
c
h
in
e
L
ea
r
n
in
g
in
to
co
n
s
id
er
atio
n
an
d
p
r
o
v
id
e
d
a
co
m
p
r
e
h
en
s
iv
e
r
elate
d
w
o
r
k
s
tu
d
y
a
n
d
a
n
al
y
s
is
o
f
t
h
e
e
x
i
s
t
in
g
m
eth
o
d
s
f
o
r
s
p
a
m
an
d
f
a
k
e
n
e
w
s
d
etec
tio
n
.
Mo
r
eo
v
er
,
w
e
in
v
es
tig
a
ted
th
e
ap
p
licatio
n
o
f
A
NN
s
f
o
r
i
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
s
an
d
s
p
a
m
f
ilter
i
n
g
f
o
r
OSNs
p
lat
f
o
r
m
s
.
Fin
all
y
,
w
e
ad
d
r
ess
ed
h
o
w
o
n
l
in
e
s
o
cial
n
et
w
o
r
k
s
ca
n
b
e
s
tr
u
ctu
r
ed
in
to
s
o
cial
g
r
ap
h
s
w
it
h
t
h
e
u
s
er
s
r
ep
r
esen
ted
b
y
n
o
d
es
o
n
t
h
e
g
r
ap
h
.
Mo
r
e
o
v
er
,
an
d
b
ased
o
n
th
e
o
b
s
er
v
atio
n
t
h
at
ce
r
tain
c
o
m
m
u
n
it
y
o
r
g
r
o
u
p
ov
er
an
O
SN
ca
n
fo
r
m
a
n
e
n
tit
y
w
it
h
t
h
eir
s
o
cial
ac
ti
v
iti
es,
w
e
p
r
o
p
o
s
ed
th
e
tr
u
s
t
w
o
r
th
i
n
es
s
p
r
in
cip
le
to
id
en
ti
f
y
t
h
e
co
m
m
u
n
itie
s
/en
tit
ies
w
it
h
m
alicio
u
s
ac
ti
v
ates
.
A
d
d
itio
n
al
l
y
,
w
e
p
r
o
p
o
s
ed
n
e
w
ap
p
r
o
ac
h
th
a
t
u
s
es
th
e
co
n
ce
p
t
o
f
w
e
ig
h
ted
cliq
u
es
in
th
e
d
etec
tio
n
o
f
s
u
b
-
co
m
m
u
n
itie
s
’
m
alic
io
u
s
b
eh
a
v
i
o
r
s
o
v
er
OSNs
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
is
b
a
s
ed
o
n
co
m
p
u
ti
n
g
t
h
e
o
v
er
all
w
e
ig
h
t
o
f
th
e
c
li
q
u
e
b
ased
o
n
in
d
iv
id
u
al
ed
g
es,
a
n
d
it
ca
n
b
e
u
s
ed
to
id
en
ti
f
y
s
u
s
p
icio
u
s
b
e
h
av
io
r
o
f
ce
r
tai
n
o
n
l
i
n
e
g
r
o
u
p
s
a
n
d
to
p
r
ev
e
n
t
f
u
r
t
h
er
p
lan
n
ed
ac
tio
n
s
s
u
c
h
as c
y
b
er
/ter
r
o
r
is
t a
ttac
k
s
b
ef
o
r
e
th
e
y
h
ap
p
en
.
Evaluation Warning : The document was created with Spire.PDF for Python.