Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
1
,
No
.
1
,
Ma
y
2
0
2
0
,
p
p
.
1
~
1
2
I
SS
N:
2722
-
3
2
2
1
,
DOI
: 1
0
.
1
1
5
9
1
/
csit
.
v
1
i1
.
p
1
-
12
1
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
Em
a
il phishing
:
T
ex
t
clas
sifica
tio
n using
natura
l la
ng
ua
g
e
pro
cess
ing
P
riy
a
nk
a
Ver
m
a
,
Anj
a
li G
o
y
a
l a
nd
Yo
g
it
a
G
ig
ra
s
Th
e
No
rt
h
c
a
p
U
n
i
v
e
rsity
,
G
u
rg
a
o
n
,
Ha
ry
a
n
a
,
I
n
d
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
1
4
,
2
0
19
R
ev
is
ed
No
v
1
2
,
2
0
19
Acc
ep
ted
J
an
7
,
2
0
2
0
P
h
ish
i
n
g
is
n
e
tw
o
rk
e
d
t
h
e
ft
i
n
w
h
ich
th
e
m
a
in
m
o
ti
v
e
o
f
p
h
is
h
e
rs
is
to
ste
a
l
a
n
y
p
e
rso
n
’s
p
ri
v
a
te
in
f
o
rm
a
ti
o
n
,
it
s
f
in
a
n
c
ial
d
e
tails
li
k
e
a
c
c
o
u
n
t
n
u
m
b
e
r,
c
re
d
it
c
a
rd
d
e
tails,
lo
g
i
n
i
n
fo
rm
a
t
io
n
,
p
a
y
m
e
n
t
m
o
d
e
in
f
o
r
m
a
ti
o
n
b
y
c
re
a
ti
n
g
a
n
d
d
e
v
e
lo
p
in
g
a
fa
k
e
p
a
g
e
o
r
a
fa
k
e
we
b
site,
wh
ich
lo
o
k
c
o
m
p
lete
ly
a
u
th
e
n
ti
c
a
n
d
g
e
n
u
in
e
.
No
wa
d
a
y
s
e
m
a
il
p
h
ish
in
g
h
a
s
b
e
c
o
m
e
a
b
i
g
t
h
re
a
t
t
o
a
ll
,
a
n
d
is
i
n
c
re
a
sin
g
d
a
y
b
y
d
a
y
.
M
o
re
o
v
e
r,
d
e
tec
ti
o
n
o
f
p
h
is
h
in
g
e
m
a
il
s
h
a
s
b
e
e
n
c
o
n
sid
e
re
d
a
n
imp
o
rtan
t
re
se
a
rc
h
issu
e
a
s
p
h
ish
in
g
e
m
a
il
s
h
a
v
e
b
e
e
n
in
c
re
a
sin
g
d
a
y
b
y
d
a
y
.
Va
rio
u
s
te
c
h
n
iq
u
e
s
h
a
v
e
b
e
e
n
in
tr
o
d
u
c
e
d
a
n
d
a
p
p
li
e
d
to
d
e
a
l
wit
h
su
c
h
a
b
ig
issu
e
.
T
h
e
m
a
jo
r
o
b
jec
ti
v
e
o
f
t
h
is
re
se
a
rc
h
p
a
p
e
r
is
g
iv
i
n
g
a
d
e
tailed
d
e
sc
rip
ti
o
n
o
n
th
e
c
las
sifica
ti
o
n
o
f
p
h
ish
i
n
g
e
m
a
il
s
u
sin
g
th
e
n
a
tu
ra
l
la
n
g
u
a
g
e
p
ro
c
e
ss
in
g
c
o
n
c
e
p
ts.
NLP
(
n
a
tu
ra
l
la
n
g
u
a
g
e
p
ro
c
e
ss
in
g
)
c
o
n
c
e
p
ts
h
a
v
e
b
e
e
n
a
p
p
li
e
d
f
o
r
t
h
e
c
las
sifica
ti
o
n
o
f
e
m
a
il
s,
a
lo
n
g
with
t
h
a
t
a
c
c
u
ra
c
y
ra
te
o
f
v
a
rio
u
s
c
las
sifiers
h
a
v
e
b
e
e
n
c
a
lcu
late
d
.
Th
e
p
a
p
e
r
is
p
re
se
n
ted
in
fo
u
r
se
c
ti
o
n
s.
A
n
in
tro
d
u
c
ti
o
n
a
b
o
u
t
p
h
ish
in
g
it
s
ty
p
e
s,
it
s
h
isto
r
y
,
sta
ti
stics
,
li
fe
c
y
c
le,
m
o
t
iv
a
ti
o
n
fo
r
p
h
is
h
e
rs
a
n
d
wo
rk
in
g
o
f
e
m
a
il
p
h
ish
in
g
h
a
v
e
b
e
e
n
d
isc
u
ss
e
d
in
th
e
first
se
c
ti
o
n
.
Th
e
se
c
o
n
d
se
c
ti
o
n
c
o
v
e
rs
v
a
rio
u
s
tec
h
n
o
l
o
g
ies
o
f
p
h
is
h
i
n
g
-
e
m
a
il
p
h
is
h
in
g
a
n
d
a
lso
d
e
s
c
rip
ti
o
n
o
f
e
v
a
lu
a
ti
o
n
m
e
tri
c
s.
An
o
v
e
rv
iew
o
f
t
h
e
v
a
ri
o
u
s
p
ro
p
o
se
d
so
l
u
ti
o
n
s
a
n
d
wo
rk
d
o
n
e
b
y
re
se
a
rc
h
e
rs
in
th
is
f
ield
i
n
f
o
rm
o
f
li
tera
tu
re
re
v
iew
h
a
s
b
e
e
n
p
re
se
n
ted
i
n
th
e
th
ird
se
c
ti
o
n
.
T
h
e
so
lu
ti
o
n
a
p
p
r
o
a
c
h
a
n
d
th
e
o
b
tai
n
e
d
re
su
lt
s
h
a
v
e
b
e
e
n
d
e
fin
e
d
in
th
e
f
o
u
r
th
se
c
ti
o
n
g
i
v
i
n
g
a
d
e
tailed
d
e
sc
rip
ti
o
n
a
b
o
u
t
NLP
c
o
n
c
e
p
ts a
n
d
w
o
rk
i
n
g
p
r
o
c
e
d
u
re
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
r
ep
o
r
t
C
o
n
f
u
s
io
n
m
etr
ics
E
m
ail
p
h
is
h
in
g
Ma
ch
in
e
lear
n
in
g
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
So
cial
en
g
in
ee
r
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Priy
an
k
a
Ver
m
a
,
T
h
e
No
r
th
ca
p
Un
iv
er
s
ity
,
I
n
d
ia
.
E
m
ail:
p
r
iy
an
k
a
1
7
csp
0
0
8
@
n
c
u
in
d
ia.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
Ph
is
h
in
g
is
b
asically
a
n
etwo
r
k
ed
th
ef
t
in
wh
ich
th
e
m
ai
n
m
o
tiv
e
o
f
p
h
is
h
er
s
is
to
s
teal
an
y
p
er
s
o
n
’
s
p
r
iv
ate
in
f
o
r
m
atio
n
,
its
f
in
an
c
ial
d
etails
lik
e
ac
co
u
n
t
n
u
m
b
e
r
,
cr
ed
it
ca
r
d
d
etails,
lo
g
in
in
f
o
r
m
atio
n
,
p
ay
m
en
t
m
o
d
e
in
f
o
an
d
m
an
y
m
o
r
e.
Ph
is
h
in
g
is
a
tec
h
n
iq
u
e
in
wh
ich
an
attac
k
er
cr
ea
tes
an
d
d
ev
elo
p
a
f
ak
e
p
ag
e
o
r
a
f
ak
e
web
s
ite,
wh
ich
lo
o
k
c
o
m
p
letely
au
th
en
tic
a
n
d
g
e
n
u
in
e,
b
u
t
it
is
n
o
t.
T
h
e
attac
k
er
d
ep
lo
y
s
th
e
s
am
e
an
d
m
ak
e
p
e
o
p
le
to
e
n
ter
th
ei
r
cr
ed
en
tials
.
No
wad
ay
s
th
is
is
d
o
n
e
m
ain
l
y
th
r
o
u
g
h
e
-
m
ai
ls
.
Ma
n
y
f
ak
e
s
ites
ar
e
av
ailab
le
an
d
ar
e
u
s
ed
b
y
p
h
is
h
er
s
to
f
r
au
d
p
eo
p
le
b
y
s
en
d
in
g
f
ak
e
m
ails
an
d
s
teal
th
eir
p
r
iv
ate
in
f
o
o
r
m
ak
e
th
em
a
v
ictim
o
f
em
ail
p
h
is
h
in
g
b
y
s
en
d
in
g
an
y
k
i
n
d
o
f
m
a
licio
u
s
lin
k
o
r
p
o
p
-
u
p
in
m
ail
s
th
at
th
e
u
s
er
will
u
n
k
n
o
win
g
ly
o
p
en
an
d
th
u
s
g
o
t
s
tu
ck
in
th
eir
tr
ap
.
I
t
is
a
f
o
r
m
o
f
f
r
au
d
in
wh
ich
th
e
attac
k
er
r
ep
r
esen
ts
h
im
s
elf
to
b
e
g
en
u
in
e
en
tity
a
n
d
attac
k
v
ia
co
m
m
u
n
icatio
n
ch
an
n
els.
Ph
is
h
in
g
is
b
r
o
a
d
ly
class
if
ied
in
th
r
ee
ca
teg
o
r
ies.
Sp
ea
r
p
h
is
h
in
g
:
T
ar
g
etin
g
a
s
in
g
le
o
r
a
n
in
d
iv
id
u
al
o
r
th
e
cr
o
wd
o
f
p
e
o
p
le
h
av
in
g
c
o
m
m
o
n
in
ter
est,
ter
m
ed
as
s
p
ea
r
p
h
is
h
in
g
.
I
n
th
is
ty
p
e
o
f
p
h
is
h
in
g
th
e
m
ajo
r
tar
g
et
o
f
th
e
p
h
is
h
er
is
s
tealin
g
an
d
u
s
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
V
o
l.
5
,
No
.
1
,
Ma
y
20
20
:
1
-
1
2
2
th
e
p
r
iv
ate
d
etails
ab
o
u
t
th
e
ta
r
g
et
to
ass
u
r
e
th
eir
c
h
an
ce
s
o
f
s
u
cc
ess
.
C
lo
n
e
p
h
is
h
in
g
:
in
t
h
is
ty
p
e
o
f
p
h
is
h
in
g
attac
k
,
th
e
attac
k
er
cr
ea
tes
a
clo
n
e
o
f
ex
is
tin
g
em
ail
an
d
a
ttach
m
alicio
u
s
co
n
ten
t
o
r
lin
k
with
th
e
m
ail
in
o
r
d
er
t
o
s
teal
p
er
s
o
n
’
s
in
f
o
o
r
an
y
f
r
a
u
d
.
T
h
e
em
ail
with
m
a
licio
u
s
co
n
ten
t
is
th
en
s
en
t
f
r
o
m
a
s
p
o
o
f
e
d
em
ail
ad
d
r
ess
th
at
ap
p
ea
r
s
to
b
e
an
o
r
ig
in
al
em
ail
a
d
d
r
ess
.
I
t
m
ay
claim
to
b
e
a
r
esen
d
o
f
th
e
o
r
i
g
in
al
o
r
an
u
p
d
ate
d
v
er
s
io
n
to
th
e
o
r
ig
in
al.
I
t
is
n
o
t
tar
g
et
s
p
ec
if
ic.
An
y
k
in
d
o
f
p
er
s
o
n
ca
n
c
o
m
e
an
d
en
ter
th
e
ir
cr
ed
en
tials
.
T
h
ey
ju
s
t
n
ee
d
to
co
llect
th
e
cr
ed
en
tials
o
f
th
e
cr
o
wd
f
o
r
th
eir
o
wn
p
u
r
p
o
s
e.
W
h
alin
g
:
T
h
is
ty
p
e
o
f
p
h
is
h
in
g
attac
k
h
as
b
ee
n
in
v
e
n
ted
f
r
o
m
s
p
ea
r
p
h
is
h
in
g
attac
k
s
wh
ich
a
r
e
d
ir
ec
ted
m
ain
ly
at
s
en
io
r
ex
ec
u
ti
v
es
o
r
o
th
e
r
h
ig
h
-
lev
el
tar
g
ets.
I
n
th
is
attac
k
,
th
e
m
alicio
u
s
co
n
ten
t
to
tar
g
et
a
n
u
p
p
e
r
lev
el
p
e
r
s
o
n
lik
e
th
e
C
E
O
o
r
th
e
p
er
s
o
n
'
s
r
o
le
in
th
e
c
o
m
p
an
y
is
cr
ea
ted
.
2.
B
ACK
G
RO
UND
T
h
is
s
ec
tio
n
g
iv
es
a
d
escr
ip
tio
n
o
n
th
e
h
is
to
r
y
a
n
d
s
tatis
tics
,
life
cy
cle,
m
o
tiv
atio
n
f
o
r
p
h
is
h
er
s
,
em
ail
p
h
is
h
in
g
an
d
its
wo
r
k
in
g
.
2
.
1
.
H
is
t
o
r
y
T
h
e
ter
m
“p
h
is
h
in
g
”
was in
v
e
n
ted
in
ea
r
ly
1
9
9
0
s
,
wh
en
a
h
u
g
e
n
u
m
b
er
o
f
u
s
er
s
with
f
ak
e
cr
ed
it c
ar
d
d
etails,
g
en
er
ated
an
alg
o
r
ith
m
f
o
r
s
tealin
g
u
s
er
’
s
in
f
o
r
m
at
io
n
.
T
h
ese
p
eo
p
le
r
e
g
is
ter
ed
th
em
s
elv
es
o
n
AOL
(
Am
er
ica
o
n
lin
e)
web
s
ite
with
o
u
t
an
y
co
n
f
ir
m
atio
n
an
d
s
tar
ted
u
s
in
g
AOL
’
s
s
y
s
tem
r
e
s
o
u
r
ce
s
.
B
y
1
9
9
5
,
AOL
was
ab
le
to
s
to
p
th
e
r
an
d
o
m
cr
ed
it
ca
r
d
g
en
e
r
ato
r
s
,
b
u
t
th
e
war
ez
g
r
o
u
p
m
o
v
ed
o
n
to
o
th
er
m
eth
o
d
s
,
s
p
ec
if
ically
p
r
eten
d
in
g
to
b
e
AOL
em
p
lo
y
ee
s
a
n
d
m
e
s
s
ag
in
g
p
eo
p
le
v
ia
AOL
Me
s
s
en
g
er
f
o
r
t
h
eir
in
f
o
r
m
atio
n
[
1
]
.
T
h
is
q
u
ick
ly
b
ec
am
e
s
u
ch
a
p
r
o
b
lem
t
h
at
o
n
J
an
u
ar
y
2
,
1
9
9
6
,
th
e
wo
r
d
“
p
h
is
h
in
g
”
was
f
ir
s
t
p
o
s
ted
in
a
Usen
et
g
r
o
u
p
d
e
d
icate
d
to
Am
er
ican
On
lin
e
[
1
]
.
Ph
is
h
in
g
ce
leb
r
ated
its
2
1
th
b
ir
th
d
ay
last
y
ea
r
.
T
h
is
p
r
ac
tice
g
o
t
its
s
tar
t
o
n
AOL
wh
en
a
g
r
o
u
p
o
f
h
ac
k
e
r
s
cr
ea
ted
a
to
o
l,
wh
ic
h
g
e
n
er
ate
r
an
d
o
m
cr
ed
it
ca
r
d
n
u
m
b
er
s
th
at
wer
e
u
s
ed
to
cr
e
ate
AOL
ac
co
u
n
ts
.
T
h
ey
tr
ick
ed
u
s
er
s
f
o
r
s
tealin
g
th
eir
p
r
iv
ate
in
f
o
r
m
atio
n
lik
e
SS
n
u
m
b
er
s
,
c
r
ed
it/d
eb
it
ca
r
d
n
u
m
b
er
s
,
DOB,
cr
ed
e
n
tials
etc.
T
h
ey
wo
u
ld
th
en
d
e
p
lo
y
o
th
er
AOL
a
cc
o
u
n
ts
wh
o
m
th
ey
ca
n
u
s
e
f
u
r
t
h
er
to
d
o
p
h
is
h
in
g
attac
k
s
.
Sin
ce
p
e
o
p
le
b
ec
o
m
e
awa
r
e
a
b
o
u
t
t
h
is
s
ca
m
s
o
,
p
h
is
h
er
s
th
en
f
o
u
n
d
o
u
t
n
ew
way
o
f
p
h
is
h
in
g
an
d
ch
o
o
s
es
em
ail
co
m
m
u
n
icatio
n
s
th
at
wer
e
v
er
y
ch
ea
p
,
ea
s
y
an
d
v
er
y
h
ar
d
to
g
et
ca
u
g
h
t
.
A
co
m
p
a
r
ativ
e
an
aly
s
is
o
f
p
h
i
s
h
in
g
attac
k
s
in
y
ea
r
2
0
1
6
-
2
0
1
8
th
e
r
e
is
a
h
u
g
e
am
o
u
n
t
o
f
i
n
cr
ea
s
e
in
attac
k
s
,
an
d
ch
an
g
es
o
f
th
ese
attac
k
s
to
g
r
o
w
m
o
r
e
i
n
co
m
i
n
g
y
ea
r
s
b
ec
a
u
s
e
if
lack
o
f
a
war
en
ess
s
h
o
wn
in
Fig
u
r
e
1
.
As
p
er
Sy
m
a
n
tec’
s
2
0
1
8
I
n
ter
n
et
Secu
r
ity
T
h
r
ea
t
R
ep
o
r
t
(
I
STR)
[
3
]
,
a
wh
o
p
p
in
g
5
4
.
6
%
o
f
all
em
ail
is
s
p
am
.
T
h
eir
d
ata
s
h
o
ws
th
at
an
av
er
ag
e
u
s
er
r
ec
ei
v
es
ab
o
u
t
1
6
m
alicio
u
s
m
ails
p
er
m
o
n
t
h
th
at
is
a
v
er
y
h
u
g
e
am
o
u
n
t.
9
2
.
4
%
m
al
war
e
is
d
eliv
er
e
d
v
ia
m
ail.
So
,
it
is
a
b
ig
th
r
ea
t
an
d
em
p
l
o
y
ee
h
as
to
b
e
tr
ain
ed
to
k
ee
p
awa
r
e.
I
t is n
o
t e
v
e
n
p
o
s
s
ib
le
f
o
r
ev
er
y
em
p
lo
y
ee
to
id
en
tify
ev
e
r
y
m
alicio
u
s
em
ail
.
So
,
it is
n
ec
ess
ar
y
to
h
av
e
r
i
g
h
t secu
r
ity
s
o
lu
tio
n
s
.
Fig
u
r
e
1
.
Ph
is
h
in
g
attac
k
s
ex
p
er
ien
ce
d
in
last
th
r
ee
y
ea
r
s
[
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
E
ma
il p
h
is
h
in
g
:
T
ex
t c
la
s
s
ifica
tio
n
u
s
in
g
n
a
tu
r
a
l la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
P
r
iya
n
ka
V
erma
)
3
2
.
2
.
L
if
e
cy
cle
Fig
u
r
e
2
s
h
o
w
s
th
e
life
cy
cle
o
f
p
h
is
h
in
g
.
Fr
o
m
b
e
g
in
n
in
g
to
en
d
,
th
e
p
h
is
h
in
g
p
r
o
ce
s
s
in
v
o
lv
es
f
o
llo
win
g
s
tep
s
:
Stag
e
1
:
Plan
an
d
s
etu
p
cr
ea
tin
g
:
I
t
is
th
e
v
er
y
f
ir
s
t
s
tep
o
f
p
h
is
h
in
g
,
in
wh
ich
th
e
att
ac
k
er
s
id
en
tify
th
e
tar
g
eted
o
r
g
an
izatio
n
o
r
in
d
iv
id
u
al.
T
h
eir
aim
is
to
g
ath
er
in
f
o
r
m
atio
n
ab
o
u
t
th
e
tar
g
eted
o
r
g
an
izatio
n
an
d
its
n
etwo
r
k
.
T
h
is
ca
n
b
e
d
o
n
e
b
y
v
is
itin
g
th
at
p
lace
o
r
b
y
m
o
n
ito
r
in
g
th
e
tr
af
fic
g
o
in
g
in
a
n
d
o
u
t
o
f
th
at
o
r
g
a
n
izatio
n
’
s
n
etwo
r
k
.
T
h
e
n
e
x
t
s
tep
is
to
cr
ea
te
s
etu
p
f
o
r
th
e
attac
k
s
b
y
p
o
s
s
ib
le
m
ea
n
s
lik
e
cr
ea
tin
g
f
ak
e
web
s
ites
an
d
s
en
d
in
g
e
m
ails
with
m
alicio
u
s
lin
k
s
an
d
co
n
ten
t,
wh
ich
will th
en
r
ed
ir
ec
t t
h
e
u
s
er
s
to
war
d
s
s
o
m
e
f
r
au
d
web
p
ag
e.
Stag
e
2
:
Sen
d
in
g
m
alicio
u
s
co
n
ten
t:
T
h
e
n
ex
t
s
tep
in
p
h
i
s
h
in
g
cy
cle
is
to
s
en
d
th
e
s
p
o
o
f
ed
e
m
ails
,
e.
g
.
,
im
p
er
s
o
n
ated
as
s
o
m
e
g
e
n
u
in
e
o
r
g
a
n
izatio
n
’
s
em
ail
to
th
e
v
ictim
u
s
in
g
th
e
c
o
llected
em
ail
ad
d
r
ess
es,
an
d
ask
in
g
th
e
u
s
er
to
u
p
d
ate
th
eir
s
en
s
itiv
e
o
r
p
er
s
o
n
al
in
f
o
r
m
atio
n
u
r
g
en
tly
b
y
click
in
g
o
n
s
o
m
e
m
alicio
u
s
lin
k
.
Stag
e
3
:
I
n
v
ad
i
n
g
/b
r
ea
k
in
g
-
i
n
:
On
ce
th
e
v
ictim
click
s
th
e
f
r
au
d
lin
k
,
ei
th
er
a
m
alwa
r
e
is
in
s
talled
o
n
th
e
s
y
s
tem
o
r
t
h
e
u
s
er
m
a
y
b
e
r
e
d
ir
ec
ted
to
s
o
m
e
f
ak
e
m
alicio
u
s
p
ag
e
wh
ich
m
ak
es
th
e
attac
k
er
to
g
ai
n
ac
ce
s
s
to
th
e
s
y
s
tem
o
r
ch
an
g
e
th
e
s
y
s
tem
co
n
f
ig
u
r
atio
n
t
o
m
ain
tain
th
at
ac
ce
s
s
.
Stag
e
4
:
E
x
tr
ac
tin
g
u
s
ef
u
l
d
at
a:
Af
ter
g
ai
n
in
g
c
o
n
tr
o
l
to
t
h
e
v
ictim
’
s
s
y
s
tem
,
th
e
r
eq
u
ir
ed
d
ata
ar
e
ex
tr
ac
ted
,
an
d
if
a
n
y
h
o
w
t
h
e
u
s
er
u
n
k
n
o
win
g
ly
g
iv
es
h
is
/h
er
ac
c
o
u
n
t
d
etails
to
th
e
attac
k
e
r
,
th
at
m
ay
r
esu
lt
in
h
u
g
e
fin
a
n
cial
lo
s
s
es
to
th
e
u
s
er
.
I
n
ca
s
e
o
f
e
x
p
lo
itatio
n
attac
k
s
,
th
e
attac
k
er
ca
n
also
p
er
f
o
r
m
DDOs
[
4
]
attac
k
to
d
am
ag
e
th
e
u
s
er
’
s
s
y
s
tem
o
r
ca
n
g
et
th
e
s
y
s
tem
’
s
r
em
o
te
ac
ce
s
s
an
d
th
e
d
ata
h
e
wan
ts
.
Stag
e
5
:
E
s
ca
p
in
g
/B
r
ea
k
in
g
-
o
u
t:
T
h
is
is
th
e
m
ain
s
tep
f
o
r
p
h
is
h
er
s
,
as
it
in
v
o
lv
es
cle
ar
in
g
o
f
tr
ac
k
s
an
d
ev
id
en
ce
s
.
Af
ter
ex
tr
ac
tin
g
al
l
th
e
ju
icy
in
f
o
r
m
atio
n
,
th
e
a
ttack
er
elim
in
ate
th
e
ev
id
e
n
c
es
lik
e
th
e
f
ak
e
web
s
ites
an
d
ac
co
u
n
ts
.
T
h
e
attac
k
er
s
ca
n
also
k
ee
p
a
tr
ac
k
o
f
th
e
v
ictim
f
o
r
f
u
t
u
r
e
att
ac
k
s
.
Fig
u
r
e
2
.
L
if
e
cy
cle
o
f
p
h
is
h
in
g
[
5
]
2
.
3
.
M
o
t
iv
a
t
io
n f
o
r
ph
is
hers
Ph
is
h
er
s
tak
e
ad
v
an
tag
e
o
f
t
h
e
lack
o
f
awa
r
en
ess
an
d
ig
n
o
r
an
ce
o
f
th
e
u
s
er
s
an
d
f
o
r
s
te
alin
g
th
eir
in
f
o
r
m
atio
n
.
No
wad
a
y
s
p
h
is
h
er
s
ar
e
v
er
y
m
u
ch
ca
p
ab
le
i
n
f
in
d
i
n
g
o
u
t
lo
o
p
h
o
les
in
th
e
n
ewly
g
e
n
er
ate
d
tech
n
iq
u
e
t
o
co
m
m
it
s
u
cc
ess
f
u
l
attac
k
s
.
T
h
er
e
ar
e
v
a
r
io
u
s
f
ac
to
r
s
o
th
er
t
h
an
f
i
n
an
cial
g
ai
n
s
th
at
en
co
u
r
ag
es
attac
k
er
s
to
co
m
m
it th
e
c
r
im
e.
So
m
e
o
f
th
e
f
ac
to
r
s
ar
e
as f
o
llo
ws:
−
Stealin
g
lo
g
in
in
f
o
r
m
atio
n
/cr
e
d
en
tials
:
Ph
is
h
er
s
m
an
ag
e
d
to
s
teal
th
e
l
o
g
in
cr
ed
e
n
tials
o
f
v
ar
io
u
s
o
n
lin
e
s
er
v
ices
lik
e
b
an
k
in
g
ap
p
licat
io
n
s
,
am
az
o
n
,
G
-
m
ail,
Face
b
o
o
k
,
eBay
etc.
f
r
o
m
th
e
u
s
er
b
y
m
ea
n
s
o
f
f
ak
e
em
ails
o
r
war
n
in
g
m
ess
ag
es f
o
r
u
p
d
atin
g
p
ass
wo
r
d
s
an
d
in
f
o
r
m
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
V
o
l.
5
,
No
.
1
,
Ma
y
20
20
:
1
-
1
2
4
−
Stealin
g
b
an
k
i
n
g
d
etails/
cr
ed
en
tials
:
Var
io
u
s
p
er
s
o
n
al
in
f
o
r
m
atio
n
lik
e
A/c
n
u
m
b
er
,
c
r
ed
it/d
eb
it
ca
r
d
d
etails,
C
C
V
n
u
m
b
er
,
a
n
d
lo
g
in
cr
ed
e
n
tials
o
f
b
an
k
in
g
ap
p
licatio
n
s
etc.
s
er
v
es
as
a
g
o
o
d
b
ait
f
o
r
th
e
p
h
is
h
er
s
.
−
C
ap
tu
r
in
g
p
r
iv
ate
in
f
o
r
m
atio
n
:
Priv
ate
d
ata,
s
u
ch
as
Aad
h
ar
n
u
m
b
er
,
r
esid
en
tial
ad
d
r
ess
,
co
n
tact
d
etails,
telep
h
o
n
e
n
u
m
b
e
r
,
ca
n
ac
t
as a
h
u
g
e
d
em
an
d
f
o
r
m
an
y
o
r
g
an
izatio
n
s
an
d
m
ar
k
etin
g
co
m
p
a
n
ies.
−
Stealin
g
o
f
c
o
n
f
id
e
n
tial
d
o
c
u
m
en
ts
an
d
t
r
ad
in
g
s
ec
r
ets:
As
p
er
n
atu
r
e
o
f
s
p
ea
r
p
h
is
h
in
g
in
tar
g
etin
g
b
ig
o
r
g
an
izatio
n
s
,
o
r
g
an
izatio
n
s
e
cr
ets
an
d
d
o
cu
m
e
n
ts
ca
n
p
ay
a
v
er
y
g
o
o
d
p
r
ice
to
p
h
is
h
er
s
f
r
o
m
o
p
p
o
s
itio
n
an
d
att
en
tiv
e
p
a
r
ties
.
−
R
ec
o
g
n
itio
n
an
d
o
p
p
r
o
b
r
iu
m
:
A
co
g
n
itiv
e
asp
ec
t
ab
o
u
t
p
h
is
h
in
g
th
at
’
s
v
er
y
in
te
r
e
s
tin
g
,
in
wh
ich
in
f
o
r
m
atio
n
is
s
to
len
n
o
t
f
o
r
s
tealin
g
p
u
r
p
o
s
e
b
u
t
m
ain
ly
f
o
r
g
ain
in
g
r
ec
o
g
n
itio
n
an
d
b
a
d
f
am
e
am
o
n
g
th
eir
f
r
ien
d
s
/p
ee
r
s
.
−
E
x
p
lo
itatio
n
o
f
s
ec
u
r
ity
lo
o
p
h
o
les:
I
n
q
u
is
itiv
e
n
atu
r
e
o
f
p
eo
p
le
esp
ec
ially
h
ac
k
er
s
,
h
av
e
a
f
ad
in
th
eir
n
atu
r
e
f
o
r
f
in
d
in
g
o
u
t
r
o
b
u
s
tn
ess
o
f
s
y
s
tem
th
at
th
ey
ev
e
n
wr
ite
co
d
e
f
o
r
e
x
p
lo
itin
g
th
e
s
y
s
tem
an
d
t
r
y
it
o
u
t o
n
s
o
m
eo
n
e
else’
s
s
y
s
tem
to
lau
n
ch
p
h
is
h
in
g
attac
k
o
r
e
v
en
s
ell
th
e
s
y
s
tem
to
o
th
er
p
h
is
h
er
s
.
2
.
4
.
E
ma
il phi
s
hi
ng
E
m
ail
p
h
is
h
in
g
is
th
e
ac
t
o
f
tr
i
ck
in
g
th
e
m
ail
r
ec
ip
ien
t
b
u
s
in
ess
o
r
an
y
o
th
er
e
n
tity
in
o
r
d
e
r
to
o
b
tain
s
en
s
itiv
e
p
er
s
o
n
al
in
f
o
r
m
atio
n
b
y
s
en
d
in
g
f
ak
e
m
ails
an
d
m
ak
in
g
th
e
r
ec
eiv
er
b
eliev
e
t
h
at
it
ca
m
e
f
r
o
m
a
g
en
u
in
e
s
o
u
r
ce
.
Data
ex
tr
ac
ted
af
ter
p
h
is
h
in
g
is
o
f
ten
u
s
ed
to
d
o
id
en
tity
th
ef
t
o
r
to
s
teal
l
o
g
in
d
etails
to
h
av
e
ac
ce
s
s
to
o
n
lin
e
ac
co
u
n
ts
.
Sp
o
o
f
in
g
is
a
way
s
im
ilar
to
em
ai
l
p
h
is
h
in
g
th
at
it
u
s
es
tech
n
iq
u
es
to
m
ak
e
p
eo
p
le
en
s
u
r
e
th
at
th
e
m
ails
h
av
e
co
m
e
f
r
o
m
a
leg
itima
te
s
o
u
r
ce
t
h
at
th
ey
ca
n
tr
u
s
t
an
d
th
u
s
b
ec
o
m
e
v
ictim
o
f
f
r
a
u
d
.
I
t u
s
es th
e
em
ail
h
ea
d
er
to
m
ak
e
it lo
o
k
s
lik
e
an
o
r
ig
in
al
s
o
u
r
ce
.
Similar
ly
,
s
p
o
o
f
ed
I
P’s u
s
e
f
o
r
g
ed
I
P a
d
d
r
ess
to
f
o
o
l
t
h
e
u
s
er
’
s
co
m
p
u
ter
a
n
d
m
ak
in
g
th
em
b
elie
v
e
th
at
it
ca
m
e
f
r
o
m
a
tr
u
s
ted
s
o
u
r
ce
.
V
ar
io
u
s
s
ites
ca
n
b
e
u
s
ed
to
cr
ea
te
an
d
s
en
d
f
ak
e
m
ails
:
h
ttp
s
://em
k
ei.
cz
/
,
h
ttp
s
://g
etg
o
p
h
is
h
.
co
m
/
,
w
ww.
tem
p
-
m
ail.
o
r
g
.
Fig
u
r
e
3
s
h
o
win
g
f
ak
e
e
m
ail
m
ess
ag
e
in
n
am
e
o
f
am
az
o
n
en
ter
p
r
is
e
.
Fig
u
r
e
3
.
Sh
o
win
g
f
a
k
e
em
ail
m
ess
ag
e
in
n
am
e
o
f
am
az
o
n
e
n
ter
p
r
is
e.
[
6
]
2
.
5
.
Wo
r
k
ing
o
f
ema
il phi
s
h
ing
T
h
e
wo
r
k
in
g
o
f
em
ail
p
h
is
h
in
g
as sh
o
wn
in
Fig
u
r
e
4
m
ai
n
ly
in
cu
d
es sev
en
s
tep
s
:
1.
C
o
m
p
r
o
m
is
e
web
s
er
v
e
r
:
th
e
v
er
y
f
i
r
s
t
s
tep
o
f
attac
k
er
is
to
b
r
ea
k
i
n
to
th
e
we
b
s
er
v
er
.
T
h
is
ca
n
b
e
d
o
n
e
u
s
in
g
v
ar
io
u
s
attac
k
s
an
d
to
o
ls
lik
e
DDOS
attac
k
an
d
av
ailab
le
p
h
is
h
in
g
to
o
ls
.
2.
Sen
d
in
g
p
h
is
h
in
g
e
-
m
ails
:
th
e
attac
k
er
th
en
s
en
d
s
th
e
m
ail
co
n
tain
in
g
m
alicio
u
s
lin
k
o
r
c
o
n
ten
t
o
r
ev
en
f
ak
e
m
ails
ask
in
g
f
o
r
p
r
iv
ate
i
n
f
o
r
m
atio
n
to
th
e
v
ictim
/r
ec
ei
v
er
.
3.
R
ec
eiv
ed
m
ail:
th
e
u
s
er
/v
ictim
wh
o
is
u
n
awa
r
e
o
f
th
e
f
ac
t
th
at
th
e
m
ail
is
n
o
t
a
g
en
u
i
n
e
o
n
e,
click
s
o
n
th
e
lin
k
p
r
o
v
id
e
d
in
th
e
m
ail.
4.
Acc
ess
web
s
ite
: a
f
ter
click
in
g
o
n
th
e
lin
k
th
e
u
s
er
is
d
ir
ec
te
d
to
war
d
s
th
e
co
m
p
r
o
m
is
ed
we
b
s
ite.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
E
ma
il p
h
is
h
in
g
:
T
ex
t c
la
s
s
ifica
tio
n
u
s
in
g
n
a
tu
r
a
l la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
P
r
iya
n
ka
V
erma
)
5
5.
Ph
is
h
in
g
web
s
ite
ap
p
ea
r
s
:
th
e
attac
k
er
th
en
s
en
d
s
th
e
f
a
k
e
a
n
d
m
alicio
u
s
s
ite
to
th
e
u
s
er
e
n
d
ask
in
g
f
o
r
in
f
o
r
m
atio
n
.
6.
Su
b
m
it
in
f
o
r
m
atio
n
:
th
e
u
s
er
b
ein
g
u
n
awa
r
e
ab
o
u
t
th
e
f
a
ct
th
at
th
e
s
ite
is
n
o
t
a
g
en
u
in
e
o
n
e
en
ter
s
h
is
/h
er
ask
ed
in
f
o
r
m
atio
n
a
n
d
b
ec
o
m
e
a
v
ictim
o
f
m
ail
p
h
is
h
in
g
.
7.
Ma
k
e
u
s
e
o
f
in
f
o
r
m
atio
n
:
a
f
ter
g
ettin
g
ju
icy
in
f
o
r
m
atio
n
f
r
o
m
th
e
u
s
er
,
th
e
attac
k
er
th
en
tak
es
ad
v
an
tag
e
o
f
th
at
in
f
o
r
m
ati
o
n
o
r
m
ay
m
is
u
s
e
th
at
o
r
ev
e
n
b
la
ck
m
ail
u
s
er
.
Fig
u
r
e
4
.
Pro
ce
d
u
r
e
o
f
em
ail
p
h
is
h
in
g
3.
E
VA
L
UA
T
I
O
N
M
E
T
RIC
E
S
Ma
n
y
r
esear
ch
er
s
u
s
e
ev
alu
at
io
n
m
etr
ics
f
o
r
th
e
ev
alu
atio
n
an
d
ex
p
e
r
im
en
tatio
n
o
f
th
e
ir
r
esear
ch
tech
n
iq
u
es
[
7
]
.
T
h
e
m
ain
o
b
jectiv
e
o
f
ev
alu
atio
n
m
etr
ics
is
to
s
tate
p
h
is
h
in
g
m
ails
f
r
o
m
a
s
et
o
f
g
iv
en
m
alicio
u
s
an
d
g
e
n
u
in
e
m
ails
.
Giv
en
b
elo
w
th
e
v
ar
io
u
s
e
v
alu
atio
n
m
etr
ics:
T
r
u
e
p
o
s
itiv
e
r
ate
(
T
PR
)
:
I
t
s
tates
th
e
r
atio
o
f
p
h
is
h
in
g
m
ails
d
etec
ted
with
r
esp
ec
t
t
o
all
m
alicio
u
s
an
d
g
en
u
in
e
m
ails
.
=
ℎ
ℎ
→
ℎ
ℎ
ℎ
ℎ
→
ℎ
ℎ
+
ℎ
ℎ
→
ℎ
=
+
Fals
e
p
o
s
itiv
e
r
ate
(
FP
R
)
: I
t st
ates th
e
r
atio
o
f
g
e
n
u
in
e
m
ails
th
at
wer
e
im
p
r
o
p
er
ly
d
etec
ted
as p
h
is
h
in
g
m
ails
.
=
ℎ
→
ℎ
ℎ
ℎ
→
ℎ
+
ℎ
→
ℎ
ℎ
=
+
Acc
u
r
ac
y
(
A)
:
I
t
m
ea
s
u
r
es
th
e
r
ate
o
f
m
ails
d
etec
ted
co
r
r
ec
tly
as
p
h
is
h
in
g
with
r
esp
ec
t
to
all
d
etec
ted
p
h
is
h
in
g
m
ails
.
=
TP
+
TN
TP
+
FP
+
FN
+
4.
T
AXO
NO
M
Y
O
F
P
H
I
SH
I
N
G
AT
T
ACK
S
Ph
is
h
in
g
attac
k
s
ca
n
b
e
d
eter
m
in
ed
as
p
er
m
u
ltip
le
tech
n
iq
u
es
u
s
ed
b
y
th
e
p
h
is
h
er
s
to
s
t
ea
l
p
er
s
o
n
al
in
f
o
r
m
atio
n
o
f
v
ictim
.
Ph
is
h
er
c
an
f
r
au
d
a
v
ictim
eith
er
b
y
s
en
d
in
g
m
alicio
u
s
lin
k
v
ia
em
ail
o
r
b
y
cr
ea
tin
g
f
ak
e
web
s
ite
to
tr
a
p
th
e
u
s
er
s
an
d
s
tealin
g
th
eir
p
er
s
o
n
al
in
f
o
r
m
atio
n
.
E
m
ail
th
r
ea
ts
h
a
v
e
b
ec
o
m
e
a
p
er
s
is
ten
t
s
o
u
r
ce
o
f
c
y
b
er
s
ec
u
r
ity
p
r
ac
titi
o
n
er
an
g
u
is
h
.
H
o
wev
er
,
la
ck
o
f
k
n
o
wl
ed
g
e
an
d
u
n
d
e
r
s
tan
d
in
g
am
o
n
g
th
e
u
s
er
s
ac
ts
as
a
b
en
e
f
it
f
o
r
th
e
p
h
is
h
er
s
f
o
r
p
er
f
o
r
m
in
g
p
h
is
h
in
g
attac
k
f
o
r
s
tealin
g
th
eir
cr
ed
e
n
tials
.
An
attac
k
er
ca
n
f
r
au
d
an
y
in
n
o
ce
n
t
u
s
er
eith
er
b
y
s
en
d
i
n
g
s
p
o
o
f
e
d
em
ails
o
r
b
y
u
s
in
g
f
ak
e
web
s
ites
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
V
o
l.
5
,
No
.
1
,
Ma
y
20
20
:
1
-
1
2
6
Var
io
u
s
tech
n
iq
u
e
s
lik
e
s
o
ci
al
en
g
in
ee
r
i
n
g
,
s
u
b
ter
f
u
g
e,
wir
eless
m
ed
iu
m
,
m
alicio
u
s
co
d
e,
k
ey
lo
g
g
er
s
,
an
d
s
cr
ee
n
ca
p
tu
r
e
ca
n
also
u
s
e
to
s
teal
p
er
s
o
n
al
in
f
o
r
m
atio
n
.
T
h
e
ca
teg
o
r
izatio
n
o
f
Ph
is
h
in
g
attac
k
s
is
s
h
o
wn
in
Fig
u
r
e
5
.
T
e
c
hni
que
s
of
phi
s
hi
ng a
t
t
a
c
ks
P
hi
s
hi
ng t
hr
ough
t
e
c
hni
c
a
l
s
ubt
e
r
f
uge
P
hi
s
hi
ng t
hr
ough
onl
i
ne
s
oc
i
a
l
ne
t
wor
k
P
hi
s
hi
ng t
hr
ough
wir
e
l
e
s
s
m
e
di
um
P
hi
s
hi
ng t
hr
ough
s
oc
i
a
l
e
ngi
ne
e
r
i
ng
B
l
ue
t
oot
h
DN
S
poi
s
oni
ng
C
l
i
c
ki
ng on
m
a
l
i
c
i
ous
l
i
nk
T
hr
ough s
m
s
S
e
s
s
i
on hi
j
a
c
ki
ng
I
ns
t
a
l
l
m
a
l
i
c
i
ous
a
pp
W
i
-
F
i
T
hr
ough
we
bs
i
t
e
M
a
n I
n t
he
m
i
ddl
e
a
t
t
a
c
k
V
i
s
i
t
i
ng s
poof
e
d
we
bs
i
t
e
s
T
hr
ough
e
m
a
i
l
s
C
r
os
s
s
i
t
e
s
c
r
i
pt
i
ng
R
e
s
pondi
ng wit
h
s
e
ns
i
t
i
ve
i
nf
or
m
a
t
i
on
S
pe
a
r
C
l
one
W
ha
l
i
ng
Fig
u
r
e
5
.
T
a
x
o
n
o
m
y
o
f
em
ail
p
h
is
h
in
g
4
.
1
.
P
his
hin
g
t
hro
ug
h so
cia
l e
ng
ineering
So
cio
lo
g
y
is
ter
m
ed
as
s
tu
d
y
o
f
n
atu
r
e
o
f
h
u
m
a
n
b
ein
g
s
.
Sin
ce
a
wid
er
p
o
r
tio
n
o
f
m
alicio
u
s
ac
tiv
ities
wer
e
co
n
s
u
m
m
ated
b
ec
au
s
e
o
f
h
u
m
a
n
er
r
o
r
s
an
d
n
eg
lectio
n
.
I
t
r
eq
u
ir
es
co
g
n
itiv
e
m
an
ip
u
latio
n
in
tr
ick
in
g
u
s
er
s
to
g
et
s
tu
ck
in
t
h
e
tr
ap
an
d
m
ak
e
s
ec
u
r
ity
m
is
tak
es
o
r
g
iv
in
g
awa
y
s
en
s
itiv
e
in
f
o
r
m
atio
n
[
8
]
.
I
t
m
ain
ly
d
ep
en
d
s
o
n
h
u
m
an
er
r
o
r
an
d
lack
o
f
k
n
o
wled
g
e,
r
at
h
er
th
an
wea
k
n
ess
in
s
o
f
twar
e
an
d
v
u
ln
er
a
b
ilit
ies
in
OS.
Mu
ch
less
p
r
e
d
ictab
le
m
is
tak
es
o
f
ten
ca
m
e
f
r
o
m
g
en
u
in
e
u
s
er
s
th
at
a
r
e
ev
e
n
h
ar
d
t
o
id
en
tify
.
So
m
e
o
f
s
o
cial
en
g
in
ee
r
in
g
m
eth
o
d
s
ar
e
d
is
cu
s
s
ed
b
elo
w:
4
.
1
.
1
.
P
his
hin
g
t
hro
ug
h S
M
S
T
h
e
p
r
o
ce
s
s
o
f
s
tealin
g
p
er
s
o
n
al
an
d
f
in
a
n
cial
in
f
o
r
m
ati
o
n
o
f
p
er
s
o
n
v
ia
s
m
s
is
ca
lled
S
m
is
h
in
g
[
9
]
.
T
h
is
m
eth
o
d
is
v
er
y
co
m
m
o
n
f
o
r
d
o
i
n
g
p
h
is
h
in
g
th
r
o
u
g
h
m
o
b
ile
p
h
o
n
es.
Ph
is
h
in
g
is
d
o
n
e
b
y
s
en
d
i
n
g
s
m
s
th
at
co
n
tain
m
alicio
u
s
lin
k
o
r
attac
h
m
en
t
th
at
r
ed
ir
ec
ts
th
e
u
s
er
s
to
war
d
s
a
f
ak
e
p
ag
e
to
s
teal
p
er
s
o
n
al
an
d
f
in
an
cial
in
f
o
r
m
atio
n
.
4
.
1
.
2
.
P
his
hin
g
t
hro
ug
h we
bs
it
es
T
h
is
m
eth
o
d
in
clu
d
es
cr
ea
tin
g
o
f
m
alicio
u
s
web
s
ite
th
at
lo
o
k
s
ex
ac
tly
s
am
e
as
th
e
o
r
ig
in
al
web
s
ite,
f
o
r
m
is
g
u
id
in
g
th
e
u
s
er
s
an
d
s
tealin
g
th
eir
p
er
s
o
n
al
in
f
o
r
m
at
io
n
.
T
h
e
p
h
is
h
in
g
web
s
ites
ca
n
b
e
a
cr
ea
te
d
o
n
e
o
r
a
leg
itima
te
o
n
e
co
n
tain
i
n
g
m
alicio
u
s
lin
k
s
.
4
.
1
.
3
.
P
his
hin
g
t
hro
ug
h e
m
a
ils
T
h
is
is
th
e
m
o
s
t
co
m
m
o
n
m
e
th
o
d
o
f
p
h
is
h
in
g
th
ese
d
ay
s
s
in
ce
em
ail
co
m
m
u
n
icatio
n
is
th
e
wid
ely
u
s
ed
m
ea
n
s
o
f
c
o
m
m
u
n
icatio
n
m
ain
ly
in
o
f
f
icial
p
u
r
p
o
s
es.
T
h
e
p
h
is
h
er
s
en
d
s
f
a
k
e
m
ails
o
r
m
ails
co
n
tain
in
g
m
alicio
u
s
lin
k
to
t
h
e
u
s
er
s
in
o
r
d
er
t
o
tr
ick
th
em
a
n
d
s
teal
t
h
eir
p
er
s
o
n
al,
f
in
a
n
cial,
lo
g
i
n
in
f
o
r
m
atio
n
.
E
m
ail
p
h
is
h
in
g
is
b
r
o
ad
ly
ca
teg
o
r
ize
d
in
to
th
r
ee
ty
p
es:
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
E
ma
il p
h
is
h
in
g
:
T
ex
t c
la
s
s
ifica
tio
n
u
s
in
g
n
a
tu
r
a
l la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
P
r
iya
n
ka
V
erma
)
7
−
Sp
ea
r
p
h
is
h
in
g
:
I
n
th
is
ty
p
e
o
f
p
h
is
h
in
g
,
attac
k
er
s
o
f
te
n
g
ath
er
u
s
er
’
s
p
er
s
o
n
al
in
f
o
r
m
atio
n
an
d
u
s
e
th
e
m
to
ass
u
r
e
th
eir
s
u
cc
ess
.
−
C
lo
n
e
p
h
is
h
in
g
:
I
n
th
is
ty
p
e
o
f
p
h
is
h
in
g
attac
k
,
th
e
attac
k
er
cr
ea
tes
a
clo
n
e
o
f
ex
is
tin
g
em
ail
an
d
attac
h
m
alicio
u
s
co
n
ten
t
o
r
l
in
k
with
th
e
m
ail
in
o
r
d
er
to
s
teal
p
er
s
o
n
’
s
in
f
o
o
r
an
y
f
r
au
d
.
T
h
e
em
ail
with
m
alicio
u
s
co
n
ten
t is th
en
s
en
t
to
th
e
v
ictim
th
at
lo
o
k
s
lik
e
it
ca
m
e
f
r
o
m
th
e
o
r
i
g
in
al
s
en
d
er
.
−
W
h
alin
g
:
I
n
th
is
ty
p
e,
th
e
p
h
is
h
er
’
s
attac
k
s
ar
e
d
ir
ec
ted
s
p
ec
if
ically
at
p
er
s
o
n
a
t
h
ig
h
er
lev
el
lik
e
th
e
C
E
O
o
f
th
e
co
m
p
a
n
y
a
n
d
o
t
h
e
r
h
ig
h
-
p
r
o
f
ile
tar
g
ets.
4
.
2
.
P
his
hin
g
t
hro
ug
h o
nli
n
e
s
o
cia
l net
wo
rk
So
cial
n
etwo
r
k
in
g
s
ites
ar
e
a
cr
az
e
th
ese
d
ay
s
.
W
ith
th
ese
s
i
t
es th
e
u
s
er
s
ca
n
in
ter
ac
t,
s
h
ar
e
id
ea
s
an
d
s
tu
f
f
with
ea
ch
o
th
er
.
Millio
n
s
o
f
p
eo
p
le
s
p
en
d
a
l
o
t
o
f
tim
e
u
s
in
g
th
ese.
T
h
e
p
h
is
h
er
s
to
o
k
a
g
o
o
d
ad
v
a
n
tag
e
o
f
th
ese
s
o
cial
s
ites
f
o
r
th
eir
o
wn
ad
v
an
tag
e.
Attack
er
s
ar
e
u
s
in
g
th
ese
s
i
tes
to
in
itiate
th
ei
r
attac
k
s
o
n
a
wid
e
n
u
m
b
er
o
f
p
eo
p
le
v
ia
th
ese
s
o
cial
s
ites
.
Var
io
u
s
in
cid
en
t
s
o
f
f
r
au
d
v
ia
s
o
cial
s
ites
h
av
e
b
ee
n
r
ec
o
r
d
e
d
.
Var
io
u
s
m
eth
o
d
s
u
s
ed
b
y
attac
k
er
s
to
f
r
au
d
u
s
er
s
ar
e
lis
ted
b
elo
w:
4
.
2
.
1
.
Click
ing
o
n
m
a
licio
us
lin
k
T
h
is
is
th
e
m
o
s
t
co
m
m
o
n
wa
y
th
r
o
u
g
h
wh
ic
h
th
e
u
s
er
s
g
et
tr
ap
p
e
d
o
n
th
e
p
h
is
h
in
g
attac
k
.
Ph
is
h
er
s
g
en
er
ate
m
ali
cio
u
s
lin
k
s
an
d
s
p
r
ea
d
th
em
v
ia
th
ese
s
o
cial
s
ites
to
tr
ap
u
s
er
s
.
Su
ch
lin
k
s
h
elp
th
e
p
h
is
h
er
s
in
co
m
p
letin
g
th
eir
task
b
y
s
teali
n
g
u
s
er
’
s
in
f
o
r
m
atio
n
.
4
.
2
.
2
.
I
ns
t
a
llin
g
m
a
licio
us
a
pp
lica
t
io
ns
Ph
is
h
er
s
b
u
ilt an
d
u
p
lo
a
d
m
ali
cio
u
s
ap
p
licatio
n
s
in
f
o
r
m
o
f
g
a
m
es a
n
d
v
alu
e
-
a
d
d
ed
s
er
v
ices o
n
s
o
m
e
s
ites
an
d
s
to
r
es
in
o
r
d
er
to
s
teal
an
d
s
ca
n
th
e
u
s
er
’
s
d
ata
an
d
in
f
o
r
m
atio
n
.
T
h
ese
ap
p
lica
tio
n
s
ca
n
b
e
in
th
e
f
o
r
m
o
f
co
p
y
o
f
o
r
i
g
in
al
ap
p
s
cr
ea
ted
b
y
attac
k
er
s
.
4
.
2
.
3
.
Sp
o
o
f
ed
websi
t
es:
T
h
is
attac
k
is
s
im
ilar
to
th
at
o
f
m
alicio
u
s
ap
p
attac
k
,
s
o
m
e
o
f
th
e
m
o
s
t
co
m
m
o
n
ly
s
u
cc
ess
f
u
l
s
ca
m
s
ar
e
An
Ap
p
le
iT
u
n
es “
em
er
g
e
n
cy
p
ass
wo
r
d
r
eset”
o
r
a
co
m
p
r
o
m
is
ed
Netf
lix
ac
co
u
n
t p
ass
wo
r
d
r
eset [
1
0
]
.
4
.
2
.
4
.
Rev
eling
s
ens
it
iv
e
info
rm
a
t
io
n
So
m
etim
es
th
e
m
o
s
t
c
o
m
m
o
n
an
d
d
i
r
ec
t
ap
p
r
o
ac
h
u
s
ed
b
y
p
h
is
h
er
s
is
en
o
u
g
h
to
g
ai
n
s
en
s
itiv
e
in
f
o
r
m
atio
n
.
A
m
o
s
t
c
o
m
m
o
n
r
ev
iew
r
ev
ea
ls
th
at
ab
o
u
t
3
0
%
s
tu
d
en
ts
r
ev
ea
l
th
eir
p
ass
wo
r
d
s
in
a
u
n
iv
er
s
ity
ju
s
t o
n
r
ec
eiv
in
g
a
s
im
p
le
tex
t
m
ess
ag
e.
4
.
3
.
P
his
hin
g
t
hro
ug
h t
ec
hn
ica
l su
bte
rf
ug
e
Ph
is
h
er
s
u
s
es
th
i
s
tech
n
iq
u
e
to
g
ain
o
r
s
teal
in
f
o
r
m
atio
n
f
r
o
m
u
s
er
s
f
o
r
th
eir
p
er
s
o
n
al
b
e
n
ef
its
.
So
m
e
m
eth
o
d
s
u
s
ed
f
o
r
tech
n
ical
s
u
b
ter
f
u
g
e
ar
e
d
is
cu
s
s
ed
b
elo
w:
4
.
3
.
1
.
DNS
po
is
o
nin
g
:
I
n
th
is
ty
p
e
o
f
attac
k
th
e
u
s
er
s
ar
e
r
ed
ir
ec
te
d
to
war
d
s
th
e
m
a
licio
u
s
web
s
ite
b
y
t
h
e
attac
k
er
s
,
an
d
th
is
is
d
o
n
e
b
y
c
r
ea
tin
g
a
f
ak
e
DN
S
s
er
v
er
o
r
alter
in
g
th
e
e
x
is
tin
g
o
n
e
.
I
n
th
is
attac
k
th
e
attac
k
er
tak
es
ad
v
an
tag
e
o
f
v
u
l
n
er
ab
ilit
y
o
f
d
o
m
ain
n
a
m
e
s
er
v
er
.
4
.
3
.
2
.
Ses
s
io
n hija
ck
ing
I
n
th
is
ty
p
e
o
f
attac
k
th
e
m
ain
m
o
to
o
f
p
h
is
h
er
is
to
s
teal
th
e
s
ec
u
r
ity
id
e
n
tifie
r
s
(
SID
)
o
f
th
e
u
s
er
i
n
o
r
d
er
to
s
teal
its
cr
ed
en
tials
.
SID
is
th
e
s
es
s
io
n
id
th
at
is
p
r
o
v
id
e
d
b
y
th
e
ap
p
licatio
n
t
o
au
th
en
ticate
th
e
co
n
n
ec
tio
n
o
f
th
e
u
s
er
.
On
ce
th
e
SID
is
s
to
len
,
th
e
attac
k
er
ca
n
n
o
w
lo
g
in
in
t
o
u
s
er
s
ac
co
u
n
t
a
n
d
s
teal
in
f
o
r
m
atio
n
.
4
.
3
.
3
.
M
a
n in m
idd
le
a
t
t
a
ck
(
M
I
T
M
)
I
t
ca
n
b
e
d
ef
in
ed
v
ia
an
as
s
u
m
p
tio
n
o
f
a
m
ailm
an
wr
it
in
g
d
o
wn
y
o
u
r
b
a
n
k
d
etails
an
d
th
en
d
eliv
er
in
g
th
e
e
n
v
elo
p
e
to
y
o
u
.
I
n
th
is
attac
k
th
e
p
h
is
h
er
p
la
ce
s
h
im
s
elf
b
etwe
en
t
h
e
co
n
v
er
s
atio
n
o
f
u
s
er
a
n
d
ap
p
licatio
n
f
o
r
s
tealin
g
u
s
er
’
s
p
er
s
o
n
al
an
d
f
in
an
cial
in
f
o
r
m
a
tio
n
.
4
.
4
.
P
his
hin
g
t
hro
ug
h wir
eless
m
edium
4
.
4
.
1
.
B
luet
o
o
t
h
B
ec
au
s
e
o
f
th
e
f
law
in
d
ev
ice
s
h
av
in
g
B
lu
eto
o
th
,
th
at
a
n
y
o
th
er
d
ev
ice
ca
n
c
o
n
n
ec
t
to
th
e
m
with
o
u
t
th
eir
p
er
m
is
s
io
n
.
T
h
is
f
law
ca
n
ac
t
as
a
b
ig
ad
v
a
n
tag
e
f
o
r
t
h
e
p
h
is
h
er
s
.
T
h
e
attac
k
er
ca
n
s
en
d
an
y
m
alicio
u
s
lin
k
o
r
f
ile
o
n
d
ev
ices w
ith
ac
tiv
e
B
lu
eto
o
th
co
n
n
ec
tio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
V
o
l.
5
,
No
.
1
,
Ma
y
20
20
:
1
-
1
2
8
4
.
4
.
2
.
Wi
-
Fi
Sin
ce
W
i
-
Fi
i
s
a
h
u
g
e
s
o
u
r
ce
o
f
n
etwo
r
k
t
h
ese
d
ay
s
.
Ma
n
y
p
eo
p
le
d
i
d
n
’
t
ev
e
n
au
th
en
ti
ca
te
to
th
e
ac
ce
s
s
p
o
in
t
r
esu
ltin
g
in
in
s
ec
u
r
e
co
n
n
ec
tio
n
th
at
ac
t
as
an
o
p
p
o
r
tu
n
ity
f
o
r
th
e
attac
k
er
to
i
n
ter
r
u
p
t
th
e
co
m
m
u
n
icatio
n
an
d
ca
n
ev
e
n
h
ijack
th
e
co
n
n
ec
tio
n
.
5.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Ma
n
y
r
esear
ch
er
s
h
a
v
e
p
r
o
p
o
s
ed
v
ar
io
u
s
wo
r
k
s
o
n
em
ail
p
h
i
s
h
in
g
.
So
m
e
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
ar
e:
1.
Geo
r
g
e
et
al.
[
1
1
]
in
th
eir
wo
r
k
“E
m
ail
Ph
is
h
in
g
Dete
ctio
n
Sy
s
tem
Usi
n
g
Neu
r
al
Netwo
r
k
”
h
as
p
r
o
p
o
s
ed
a
m
eth
o
d
o
f
tr
ai
n
in
g
b
ased
o
n
n
eu
r
al
n
etwo
r
k
.
T
h
ey
h
av
e
u
s
ed
two
d
atasets
p
h
is
h
an
d
h
am
d
ata
s
et,
ea
ch
co
n
s
is
tin
g
o
f
4
5
0
0
em
ails
.
T
h
ey
h
av
e
u
s
ed
v
ar
i
o
u
s
alg
o
r
it
h
m
lik
e
FNN
with
b
ac
k
p
r
o
p
a
g
atio
n
alg
o
r
ith
m
f
o
r
tr
ain
in
g
an
d
id
en
tify
in
g
h
am
an
d
p
h
is
h
em
ails
,
f
is
t
o
r
d
er
s
tatis
tical
m
ea
s
u
r
es
f
o
r
f
in
d
in
g
o
u
t
th
e
b
est
f
ea
tu
r
es
f
r
o
m
th
e
e
x
tr
ac
ted
o
n
es.
T
h
is
h
as
ac
h
iev
ed
a
v
er
y
lo
w
f
alse
n
eg
ativ
e
an
d
f
als
e
p
o
s
itiv
e
r
ate.
9
9
.
9
5
% wa
s
th
e
b
est cla
s
s
if
ied
r
esu
lt a
ch
iev
ed
u
s
in
g
1
2
b
est
f
ea
tu
r
es.
2.
T
h
e
au
th
o
r
s
in
th
eir
wo
r
k
“I
d
en
tific
atio
n
an
d
Dete
ctio
n
o
f
Ph
is
h
in
g
E
m
ails
Usi
n
g
Natu
r
al
L
an
g
u
ag
e
Pro
ce
s
s
in
g
T
ec
h
n
iq
u
es”
[
1
2
]
h
as
f
o
cu
s
ed
o
n
d
etec
tin
g
p
h
is
h
in
g
e
m
ails
th
at
d
o
n
o
t
co
n
tai
n
an
y
lin
k
s
an
d
u
r
ls
.
T
h
e
y
h
av
e
o
n
f
o
cu
s
ed
o
n
e
m
ail
co
m
m
u
n
icatio
n
.
T
h
ey
m
ak
e
u
s
e
o
f
NL
P
an
d
W
o
r
d
Net
in
th
eir
p
r
o
p
o
s
ed
wo
r
k
.
T
h
e
y
h
a
v
e
ex
am
in
ed
o
v
er
6
0
0
p
h
is
h
in
g
em
ails
an
d
4
0
0
g
en
u
in
e
em
ails
a
n
d
co
llected
a
lis
t
o
f
f
ea
tu
r
es
lik
e
ab
s
e
n
ce
o
f
r
ec
ip
ien
t’
s
n
am
e,
ask
in
g
f
o
r
m
o
n
ey
o
r
m
en
tio
n
o
f
m
o
n
ey
,
a
s
en
s
e
o
f
u
r
g
en
c
y
,
in
d
u
cin
g
s
en
ten
ce
s
th
at
lu
r
e
t
h
e
v
ictim
to
r
ep
ly
th
em
.
T
h
e
y
h
av
e
u
s
ed
Stan
f
o
r
d
C
o
r
e
NL
P’s
(
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
)
ap
p
licatio
n
p
r
o
g
r
a
m
in
ter
f
ac
e
f
o
r
f
o
r
m
in
g
a
b
ase
f
o
r
all
th
e
wo
r
d
s
p
r
esen
t in
p
h
is
h
in
g
em
ail.
T
N
(
tr
u
e
n
eg
a
tiv
e)
,
FN (
f
alse n
eg
ativ
e)
,
FP
(
f
alse p
o
s
itiv
e)
,
T
P (
tr
u
e
p
o
s
iti
v
e)
ar
e
u
s
ed
f
o
r
d
etec
tin
g
th
e
q
u
ality
o
f
th
eir
p
r
o
p
o
s
ed
wo
r
k
.
T
h
eir
o
b
tain
ed
r
esu
lts
ar
e
T
N=
3
9
8
,
FN
=
4
,
F
P=
2
,
T
P=
5
9
6
.
T
h
eir
f
u
tu
r
e
wo
r
k
is
to
im
p
r
o
v
e
th
e
ac
c
u
r
ac
y
.
T
h
ey
will
b
e
u
s
in
g
R
iTa
(
R
ea
l
I
n
t
ellig
en
ce
T
h
r
ea
t
An
aly
tics
)
[
1
3
]
W
o
r
d
Net
API
f
o
r
p
r
o
g
r
a
m
m
atica
lly
ac
ce
s
s
in
g
o
f
d
ata
b
ases
an
d
Op
t
ical
C
h
ar
ac
ter
R
ec
o
g
n
itio
n
tech
n
i
q
u
es
f
o
r
p
er
f
o
r
m
in
g
th
e
p
h
is
h
in
g
d
etec
t
io
n
o
n
th
e
tex
t
co
n
ten
ts
o
b
tai
n
ed
f
r
o
m
im
a
g
e
f
o
r
m
attac
h
m
e
n
ts
s
en
t in
m
ails
.
3.
Yasin
an
d
Ab
u
h
asan
[
1
4
]
i
n
t
h
eir
wo
r
k
“An
in
tellig
e
n
t
class
if
icatio
n
m
o
d
el
f
o
r
p
h
is
h
in
g
em
ail
d
etec
tio
n
”
h
as
p
r
o
p
o
s
ed
a
class
if
icatio
n
m
o
d
el
u
s
in
g
in
tellig
en
t
p
r
e
p
r
o
ce
s
s
in
g
p
h
ase
f
o
r
t
h
e
ex
tr
a
ctio
n
o
f
v
ar
io
u
s
f
ea
tu
r
es
o
f
e
m
ail
lik
e
em
ail
h
e
ad
er
,
b
o
d
y
,
ter
m
s
an
d
f
r
e
q
u
en
cy
,
b
y
ap
p
l
y
in
g
th
e
tech
n
iq
u
es
o
f
d
ata
m
in
in
g
an
d
k
n
o
wled
g
e
d
is
co
v
er
y
f
o
r
p
h
is
h
in
g
e
m
ails
o
r
s
p
o
o
f
e
d
e
m
ails
.
W
o
r
d
Net
o
n
to
l
o
g
y
was
u
s
ed
t
o
en
r
ich
th
e
f
ea
tu
r
es
a
n
d
f
o
r
en
h
a
n
cin
g
th
e
s
im
ilar
ity
b
e
twee
n
em
ai
ls
m
ess
ag
es,
tex
t
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
e
o
f
s
tem
m
in
g
is
u
s
ed
.
Fo
r
tr
ain
in
g
an
d
test
in
g
o
f
m
o
d
el
two
a
cc
r
ed
ited
d
ata
s
ets
(
p
h
is
h
in
g
an
d
h
am
em
ails
)
an
d
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
tech
n
iq
u
es
wer
e
u
s
ed
in
test
in
g
an
d
tr
ain
i
n
g
p
r
o
ce
s
s
.
Ver
y
p
o
p
u
lar
d
a
ta
m
in
in
g
alg
o
r
ith
m
s
lik
e
r
an
d
o
m
f
o
r
est,
J
4
8
,
B
ay
es
n
et
SVM
an
d
ML
P
wer
e
u
s
ed
to
e
x
p
er
i
m
en
t
th
e
m
o
d
el.
Hig
h
ly
en
c
o
u
r
ag
i
n
g
class
if
icatio
n
r
esu
lts
with
h
ig
h
ac
cu
r
ac
y
r
ates
wer
e
o
b
tain
e
d
as
co
m
p
a
r
ed
to
p
r
ev
i
o
u
s
m
o
d
els.
4.
Qb
eitah
an
d
Ald
wair
i”
[
1
5
]
in
th
eir
wo
r
k
“Dy
n
am
ic
Ma
lwar
e
An
aly
s
is
o
f
Ph
is
h
in
g
E
m
ails
”
h
as
p
r
o
p
o
s
ed
a
m
eth
o
d
o
lo
g
y
f
o
r
d
y
n
am
ic
an
aly
s
is
an
d
f
o
r
ca
p
tu
r
in
g
n
e
w
m
alwa
r
e
s
am
p
les
an
d
u
n
d
er
s
tan
d
in
g
th
eir
b
eh
av
e
w.
r
.
t
f
iles
,
r
eg
is
tr
y
,
O
S
an
d
n
etwo
r
k
.
T
h
ey
h
av
e
d
esig
n
ed
a
lab
u
s
in
g
th
r
ee
Dio
n
a
ea
h
o
n
ey
p
o
t
s
f
o
r
ca
p
tu
r
in
g
th
e
m
alwa
r
e
s
am
p
le
s
an
d
f
o
r
an
aly
zin
g
th
o
s
e
ca
p
t
u
r
ed
s
am
p
les
a
lab
u
s
in
g
R
E
MN
UX
s
an
d
b
o
x
was
s
etu
p
.
T
h
ey
ex
am
in
e
d
“
.
ex
e”
an
d
“e
x
ce
l
f
ile”
(
f
r
o
m
UAE
b
ased
o
r
g
a
n
izatio
n
)
f
r
o
m
th
e
n
ewly
ca
p
tu
r
ed
m
alwa
r
e
s
am
p
les
a
n
d
p
r
esen
ted
a
d
etailed
an
al
y
s
is
o
n
th
em
u
s
in
g
R
E
MN
UX.
T
h
eir
wo
r
k
co
n
tr
ib
u
ted
a
lo
t in
r
esp
o
n
s
e
p
r
o
ce
d
u
r
es b
y
m
alwa
r
e
a
n
aly
s
ts
.
5.
“De
tectio
n
o
f
p
h
is
h
in
g
attac
k
s
”
b
y
B
ay
k
ar
a
an
d
Gü
r
el
[
1
6
]
,
in
th
eir
wo
r
k
th
ey
h
av
e
d
ev
elo
p
ed
a
n
ap
p
licatio
n
“An
ti
Ph
is
h
in
g
Si
m
u
lato
r
”
to
id
en
tif
y
an
d
d
ete
ct
th
e
p
h
is
h
in
g
elem
e
n
t
in
te
x
t
an
d
m
ess
ag
e
u
s
in
g
th
e
B
ay
esian
class
if
icatio
n
alg
o
r
ith
m
with
m
an
y
d
ata
b
ases
.
New
p
h
is
h
in
g
/s
p
am
w
o
r
d
an
d
u
r
ls
c
an
also
b
e
ad
d
ed
to
th
e
d
atab
ase
u
s
in
g
“a
d
d
s
p
am
”
f
ea
tu
r
e.
T
h
e
g
en
er
ated
ap
p
licatio
n
f
o
cu
s
e
s
o
n
p
r
ev
en
tin
g
v
io
latio
n
b
y
c
o
n
tr
o
llin
g
s
ec
u
r
ity
an
d
ch
ec
k
in
g
th
e
in
c
o
m
in
g
m
ail
to
en
s
u
r
e
wh
eth
e
r
it
co
n
tain
s
an
y
m
alicio
u
s
co
n
ten
t.
Sp
am
b
o
x
is
u
s
ed
f
o
r
s
to
r
in
g
s
p
am
m
ails
an
d
is
also
u
s
er
f
r
ien
d
ly
.
6.
T
h
e
au
th
o
r
s
in
th
eir
wo
r
k
“
An
ap
p
r
o
ac
h
f
o
r
Ma
licio
u
s
S
p
am
Dete
ctio
n
in
E
m
ail
with
co
m
p
ar
is
o
n
o
f
d
if
f
er
en
t
class
if
ier
s
”
[
1
7
]
p
r
o
p
o
s
ed
a
m
o
d
el
f
o
r
p
er
f
o
r
m
in
g
f
ea
tu
r
e
s
elec
tio
n
o
f
p
h
is
h
in
g
em
ails
b
y
em
p
lo
y
in
g
a
n
o
v
el
d
ataset
u
s
in
g
two
m
o
d
els
NB
,
SVM
cl
ass
if
ier
.
A
tr
ain
in
g
d
ataset
an
d
a
test
d
ataset
co
n
tain
in
g
7
0
2
s
p
am
/
h
am
m
ails
an
d
2
6
0
m
ails
(
1
3
0
s
p
am
a
n
d
1
3
0
n
o
n
-
s
p
am
e
m
ails
)
.
T
h
e
au
th
o
r
h
as u
s
ed
s
cik
it
-
lear
n
Ma
ch
in
e
L
ea
r
n
in
g
lib
r
ar
y
(
a
n
o
p
en
s
o
u
r
ce
p
y
t
h
o
n
m
ac
h
i
n
e
lear
n
in
g
lib
r
ar
y
)
f
o
r
class
if
ier
’
s
tr
ain
in
g
.
T
h
e
o
b
tain
e
d
r
esu
lt
s
h
o
ws
th
at
b
o
th
th
e
m
o
d
els
h
av
e
b
alan
ce
d
f
alse
p
o
s
itiv
e
in
SVM
(
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e)
an
d
a
s
im
ilar
p
er
f
o
r
m
an
ce
r
ate
o
n
test
-
s
et.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
E
ma
il p
h
is
h
in
g
:
T
ex
t c
la
s
s
ifica
tio
n
u
s
in
g
n
a
tu
r
a
l la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
P
r
iya
n
ka
V
erma
)
9
7.
Dam
o
d
ar
am
[
1
8
]
,
in
h
er
wo
r
k
“
s
tu
d
y
o
n
p
h
is
h
in
g
attac
k
s
an
d
a
n
tip
h
is
h
in
g
to
o
ls
”
d
ete
r
m
in
es
v
ar
io
u
s
co
n
ce
p
ts
o
f
p
h
is
h
in
g
,
ty
p
es
o
f
p
h
is
h
in
g
attac
k
s
,
its
life
c
y
cle,
an
d
h
as
g
iv
e
n
a
b
r
ief
d
is
c
u
s
s
io
n
o
f
v
ar
io
u
s
an
ti
-
p
h
is
h
in
g
t
o
o
ls
:
−
“M
ail
-
SeC
u
r
e”
(
it is
a
m
o
d
u
le
th
at
co
m
b
in
es v
ar
io
u
s
tech
n
o
l
o
g
ies lik
e
an
ti
-
p
h
is
h
in
g
d
atab
a
s
e,
SUR
B
L
(
Sp
am
Un
if
o
r
m
R
eso
u
r
ce
I
d
e
n
tifie
r
R
ea
l
-
tim
e
B
lo
ck
L
is
t)
[
1
9
]
,
C
o
m
m
to
u
ch
R
PD,
Heu
r
is
tic
Fra
u
d
d
etec
tio
n
s
ets o
f
r
u
les,
in
ter
n
et
p
r
o
to
c
o
l (
I
P)
r
e
p
u
tatio
n
,
r
ate
l
im
it.
−
Netc
r
af
t “
A
Secu
r
ity
T
o
o
l Bar
”
−
“
Set Sec
u
r
ity
”
−
“Bro
wser
I
n
teg
r
ated
T
o
o
ls
”
−
“Usin
g
An
ti
-
p
h
is
h
an
d
Do
m
A
n
ti
-
p
h
is
h
T
ec
h
n
iq
u
es”.
T
h
e
au
th
o
r
’
s
s
tu
d
y
h
as g
iv
en
a
n
awa
r
en
ess
ab
o
u
t th
e
p
h
is
h
in
g
p
r
o
b
lem
s
an
d
s
o
lu
tio
n
s
.
6.
SO
L
U
T
I
O
N
AP
P
RO
ACH
/
M
E
T
H
O
DO
L
O
G
Y
US
E
D
A
lo
t
o
f
wo
r
k
s
h
a
v
e
b
ee
n
d
o
n
e
b
y
th
e
r
esear
ch
er
s
i
n
em
ail
class
if
icatio
n
s
,
d
etec
tio
n
an
d
p
r
ev
en
tio
n
s
u
s
in
g
m
an
y
tech
n
i
q
u
es.
Ou
r
f
o
cu
s
is
o
n
class
if
icat
io
n
s
o
f
p
h
is
h
in
g
em
ails
u
s
in
g
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es.
T
h
e
d
ata
s
et
“T
h
e
Sh
o
r
t
m
ess
ag
e
s
er
v
ice
Sp
am
C
o
llectio
n
v
.
1
”
co
n
s
is
tin
g
o
f
5
,
5
7
4
tag
g
ed
(
h
am
/s
p
am
)
,
r
ea
l
an
d
n
o
n
-
en
co
d
ed
E
n
g
lis
h
m
ess
ag
es
[
2
0
]
h
as
b
ee
n
u
s
ed
f
o
r
class
if
icatio
n
.
Natu
r
al
L
an
g
u
a
g
e
Pro
ce
s
s
in
g
,
an
d
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
w
er
e
u
s
ed
f
o
r
class
if
icati
o
n
.
T
e
x
t
class
if
icatio
n
an
d
an
aly
s
is
o
f
p
h
is
h
in
g
d
atasets
h
as
b
ee
n
d
o
n
e
u
s
in
g
NL
P
co
n
ce
p
ts
,
s
cik
it
-
lear
n
an
d
NL
T
K.
Var
io
u
s
class
if
ier
s
lik
e
SV
C
,
Dec
is
io
n
T
r
ee
,
an
d
R
an
d
o
m
Fo
r
est KNe
ig
h
b
o
r
s
C
lass
if
ier
s
ar
e
u
s
ed
.
NL
P:
NL
P
s
tan
d
s
f
o
r
Natu
r
al
lan
g
u
ag
e
Pro
ce
s
s
in
g
.
I
t
is
d
ef
i
n
ed
as
a
f
ield
o
f
AI
t
h
at
h
elp
s
co
m
p
u
ter
to
co
m
m
u
n
icate
with
h
u
m
an
s
.
B
ec
au
s
e
o
f
NL
P,
it
b
ec
o
m
es
p
o
s
s
ib
le
f
o
r
th
e
c
o
m
p
u
ter
s
to
r
ea
d
,
h
ea
r
,
ed
it
a
n
d
in
ter
p
r
et
tex
t,
s
p
ee
ch
an
d
d
e
ter
m
in
e
wh
ich
p
ar
ts
a
r
e
im
p
o
r
tan
t.
B
asic
NL
P
ta
s
k
s
in
cl
u
d
e:
r
em
o
v
i
n
g
s
to
p
wo
r
d
s
,
p
u
n
ct
u
atio
n
s
,
s
p
ec
ial
ch
ar
ac
ter
s
,
to
k
en
izatio
n
,
s
tem
m
in
g
,
tag
g
in
g
,
lan
g
u
a
g
e
d
etec
tio
n
an
d
id
en
tific
atio
n
o
f
s
em
an
tic
r
ela
tio
n
s
h
ip
s
.
I
t
is
also
ex
p
lain
ed
as
th
e
m
ea
n
s
o
f
h
a
n
d
lin
g
th
e
n
atu
r
al
lan
g
u
a
g
e
b
y
au
to
m
atic
m
ea
n
s
u
s
in
g
a
s
o
f
t
war
e.
B
asic
NL
P
task
s
in
clu
d
e:
r
em
o
v
in
g
s
to
p
wo
r
d
s
,
to
k
en
izatio
n
,
p
ar
t
-
of
-
s
p
ee
ch
tag
g
in
g
,
s
tem
m
in
g
,
p
u
n
ctu
atio
n
s
,
s
p
ec
ial
ch
ar
ac
ter
s
,
lan
g
u
ag
e
d
etec
tio
n
an
d
id
en
tif
icatio
n
o
f
s
em
an
tic
r
elatio
n
s
h
ip
s
.
Scik
it
-
lear
n
is
a
m
ac
h
in
e
lear
n
in
g
lib
r
a
r
y
f
o
r
th
e
Py
th
o
n
p
r
o
g
r
am
m
in
g
lan
g
u
ag
e.
Var
io
u
s
class
if
icatio
n
,
r
eg
r
ess
io
n
an
d
clu
s
ter
in
g
alg
o
r
ith
m
s
ar
e
also
d
ef
in
e
d
in
th
is
lib
r
ar
y
.
I
t
is
a
lib
r
ar
y
in
Py
t
h
o
n
th
at
p
r
o
v
id
es
m
an
y
u
n
s
u
p
er
v
is
ed
an
d
s
u
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
[
2
1
]
.
I
t’
s
b
u
ilt
u
p
o
n
s
o
m
e
o
f
th
e
tech
n
o
lo
g
y
y
o
u
m
ig
h
t
alr
ea
d
y
b
e
f
am
iliar
with
,
lik
e
Nu
m
P
y
,
p
a
n
d
as,
a
n
d
Ma
tp
lo
tlib
.
NL
T
K
is
ter
m
ed
as
a
“wo
n
d
er
f
u
l
to
o
l
f
o
r
teac
h
in
g
,
an
d
wo
r
k
in
g
in
,
co
m
p
u
tatio
n
al
lin
g
u
is
tics
u
s
in
g
Py
th
o
n
,
”
an
d
“a
n
am
az
in
g
lib
r
ar
y
to
p
lay
with
n
atu
r
al
lan
g
u
ag
e”
.
T
h
is
p
latf
o
r
m
allo
ws
to
wo
r
k
with
d
ata
th
at
is
in
f
o
r
m
o
f
h
u
m
a
n
lan
g
u
ag
e
b
y
b
u
ild
in
g
p
y
th
o
n
p
r
o
g
r
am
s
.
NL
T
K
is
em
b
ed
d
e
d
with
v
ar
io
u
s
tex
t p
r
o
ce
s
s
in
g
li
b
r
ar
ies
an
d
ea
s
y
-
to
u
s
e
in
ter
f
ac
es to
o
v
e
r
5
0
co
r
p
o
r
a
an
d
lex
ical
r
eso
u
r
ce
s
[
2
2
]
.
T
h
is
an
aly
s
is
is
d
o
n
e
u
s
in
g
an
ac
o
n
d
a
j
u
p
y
ter
la
b
.
T
h
e
c
o
d
in
g
is
d
o
n
e
u
s
in
g
p
y
th
o
n
.
T
h
e
wo
r
k
in
g
p
r
o
ce
d
u
r
e
is
as p
er
f
o
llo
win
g
s
tep
s
:
−
Do
wn
lo
ad
in
g
s
p
a
m
an
d
p
h
is
h
i
n
g
d
atasets
.
−
Op
en
in
g
th
e
ju
p
y
ter
lab
o
n
th
e
s
am
e
f
o
ld
er
wh
e
r
e
th
e
d
atasets
ar
e
lo
ca
ted
,
u
s
in
g
a
n
ac
o
n
d
a
p
r
o
m
p
t.
−
No
w
s
tar
t w
ith
co
d
e
wr
itin
g
th
at
in
v
o
lv
es v
ar
i
o
u
s
s
tep
s
:
−
I
m
p
o
r
tin
g
lib
r
ar
ies
−
L
o
ad
th
e
d
ataset
an
d
r
ea
d
i
n
g
t
h
e
co
n
ten
t
(
tex
t f
iles
)
.
−
Pre
p
r
o
ce
s
s
in
g
o
f
d
ataset:
th
e
v
er
y
f
ir
s
t
s
tep
in
NL
P
th
at
in
v
o
lv
es
to
k
e
n
izatio
n
,
s
to
p
wo
r
d
s
,
s
tem
m
in
g
,
r
em
o
v
in
g
n
u
m
b
er
s
an
d
p
u
n
ctu
atio
n
s
.
−
Gen
er
atin
g
f
ea
tu
r
es a
n
d
cr
ea
ti
n
g
a
f
ea
tu
r
e
s
et.
−
Div
id
in
g
th
e
f
ea
t
u
r
e
s
et
in
to
tr
ain
in
g
an
d
test
in
g
d
atasets
.
−
I
m
p
o
r
tin
g
c
h
o
s
en
class
if
ier
s
f
r
o
m
s
k
lear
n
a
n
d
ap
p
l
y
in
g
th
e
m
o
n
th
e
test
in
g
d
ataset
f
o
r
c
o
m
p
u
tin
g
th
e
ac
cu
r
ac
y
s
co
r
e.
−
L
astl
y
r
ep
r
esen
tin
g
r
esu
lts
u
s
in
g
co
n
f
u
s
io
n
m
at
r
ix
an
d
class
if
icatio
n
r
ep
o
r
t.
T
h
e
C
lass
if
icatio
n
o
f
d
ataset
is
d
o
n
e
b
y
b
u
ild
in
g
p
y
th
o
n
co
d
e
u
s
in
g
th
e
an
ac
o
n
d
a
ju
p
y
ter
lab
.
Fo
llo
win
g
ar
e
th
e
s
tep
s
in
v
o
lv
ed
in
cla
s
s
if
icatio
n
p
r
o
ce
d
u
r
e
,
as sh
o
wn
in
Fig
u
r
e
6
.
1.
I
m
po
rt
Nec
ess
a
ry
lib
ra
ries
:
T
h
e
v
er
y
f
ir
s
t
s
tep
is
im
p
o
r
tin
g
th
e
n
ec
ess
ar
y
lib
r
ar
ies.
T
h
e
im
p
o
r
ted
lib
r
ar
ies
ar
e
o
s
,
g
l
o
b
,
p
y
t
h
o
n
,
p
a
n
d
as,
n
u
m
p
y
,
n
ltk
,
s
ci
-
k
it,
s
en
t_
to
k
en
ize,
wo
r
d
_
to
k
en
ize
,
Po
r
ter
Stem
m
er
,
C
o
u
n
ter
,
m
o
d
el_
s
e
lectio
n
,
Sk
lear
n
C
lass
if
ier
,
S
VC
(
s
u
p
p
o
r
t
v
ec
to
r
class
if
ier
)
,
KNe
ig
h
b
o
r
s
C
las
s
if
ier
[
2
3
]
,
Dec
is
io
n
T
r
ee
C
lass
if
ier
,
R
an
d
o
m
Fo
r
est
C
las
s
if
ier
,
class
if
ic
atio
n
_
r
ep
o
r
t
,
ac
cu
r
ac
y
_
s
co
r
e
,
co
n
f
u
s
io
n
_
m
atr
ix
,
L
o
g
is
tic
R
eg
r
ess
io
n
.
Fu
r
th
er
ca
n
b
e
ad
d
e
d
wh
en
r
eq
u
ir
ed
.
2.
L
o
a
d
t
he
Da
t
a
s
et
:
Py
th
o
n
p
an
d
as
h
av
e
b
ee
n
u
s
ed
f
o
r
r
ea
d
in
g
th
e
d
ataset.
T
o
u
s
e
p
a
r
ticu
lar
d
ataset,
o
p
en
th
e
ju
p
y
ter
lab
in
th
at
d
at
ab
ase’
s
lo
ca
tio
n
u
s
in
g
th
e
an
a
co
n
d
a
p
r
o
m
p
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
V
o
l.
5
,
No
.
1
,
Ma
y
20
20
:
1
-
1
2
10
3.
P
re
pro
ce
s
s
ing
o
f
Da
t
a
:
T
h
e
v
er
y
f
i
r
s
t
s
tep
in
cl
ass
if
icatio
n
p
r
o
ce
s
s
is
th
e
p
r
e
p
r
o
ce
s
s
in
g
o
f
d
ataset.
T
h
is
in
clu
d
es
co
n
v
er
tin
g
wh
o
le
te
x
t
in
lo
wer
ca
s
e,
r
em
o
v
in
g
n
u
m
b
er
s
,
web
ad
d
r
ess
,
an
d
p
u
n
ctu
atio
n
s
,
r
em
o
v
in
g
s
to
p
wo
r
d
s
,
to
k
en
iz
atio
n
,
s
tem
m
in
g
.
4.
F
ea
t
ures
G
ener
a
t
io
n
:
th
is
is
an
im
p
o
r
ta
n
t
s
tep
in
class
if
icat
io
n
.
Featu
r
e
en
g
in
ee
r
in
g
is
u
s
ed
to
g
en
e
r
ate
f
ea
tu
r
es
f
r
o
m
th
e
d
ataset
u
s
in
g
d
o
m
ain
k
n
o
wled
g
e
an
d
th
o
s
e
f
ea
tu
r
es
will
b
e
u
s
ed
b
y
m
a
ch
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
.
T
h
e
f
ea
tu
r
es
ar
e
i
n
f
o
r
m
s
o
f
to
k
e
n
s
th
at
ar
e
g
e
n
er
ated
in
th
e
p
r
ev
io
u
s
s
tep
.
A
f
ea
tu
r
e
s
et
is
cr
ea
ted
f
r
o
m
t
h
ese
f
ea
tu
r
es
th
at
co
n
s
is
ts
o
f
th
e
m
o
s
t
co
m
m
o
n
f
ea
tu
r
es.
T
h
e
f
ea
tu
r
e
s
et
ca
n
also
co
n
tain
f
ea
tu
r
es
th
at
ar
e
n
o
t
m
ea
n
in
g
f
u
l
o
r
o
f
v
e
r
y
s
h
o
r
t
len
g
th
,
s
u
ch
f
ea
tu
r
es
n
ee
d
to
b
e
r
em
o
v
ed
f
o
r
b
etter
r
esu
lts
.
5.
G
ener
a
t
io
n
o
f
Da
t
a
s
et
s
f
o
r
T
esting
a
nd
T
r
a
ini
ng
t
he
M
o
del
:
T
h
e
f
ea
tu
r
e
s
et
is
d
iv
i
d
ed
in
e
q
u
al
o
r
an
y
r
atio
as
p
e
r
o
u
r
co
n
ce
r
n
to
m
a
k
e
tr
ai
n
in
g
an
d
test
in
g
d
atasets
.
T
h
e
tr
ain
in
g
d
ata
s
et
is
u
s
ed
f
o
r
tr
ain
in
g
t
h
e
class
if
ier
s
o
r
b
u
il
d
in
g
a
m
o
d
el.
W
h
ile
a
test
in
g
d
ataset
is
u
s
ed
f
o
r
v
alid
atin
g
t
h
e
b
u
ilt
m
o
d
el
an
d
ca
lcu
latin
g
t
h
e
r
esu
lts
.
6.
Appl
y
ing
Cla
s
s
if
iers
:
C
las
s
if
ier
s
,
alg
o
r
ith
m
s
th
at
h
av
e
to
b
e
u
s
ed
f
o
r
class
if
icatio
n
n
ee
d
to
b
e
im
p
o
r
ted
.
Va
r
io
u
s
s
k
lear
n
clas
s
if
ier
s
h
av
e
b
ee
n
u
s
ed
.
7.
Resul
t
s
:
C
alcu
latin
g
th
e
ac
cu
r
ac
y
r
ate
o
f
all
th
e
class
if
ier
s
an
d
cr
ea
tin
g
th
e
class
if
icatio
n
r
e
p
o
r
t
an
d
co
n
f
u
s
io
n
m
atr
ix
.
T
h
e
ac
cu
r
ac
y
r
ate
ca
lcu
lated
b
y
th
e
K
Nea
r
est
Neig
h
b
o
r
s
class
if
ier
is
9
4
.
7
5
,
Dec
is
io
n
T
r
ee
class
if
ier
is
9
7
.
5
5
,
R
an
d
o
m
Fo
r
est
class
if
ier
is
9
8
.
4
2
,
L
o
g
is
tic
R
eg
r
ess
io
n
clas
s
if
ier
is
9
8
.
5
6
,
SGD
C
las
s
i
f
ier
is
9
8
.
3
4
,
Naiv
e
B
a
y
es
class
if
ier
i
s
9
8
.
7
0
,
an
d
S
VM
L
in
ea
r
class
if
ier
i
s
9
8
.
7
7
,
as
s
h
o
wn
in
Fig
u
r
e
7
.
Fig
u
r
e
6
.
W
o
r
k
i
n
g
p
r
o
ce
d
u
r
e
IM
P
ORT
ING
L
IBRA
RIES
L
OA
DIN
G
T
HE
DA
T
A
S
ET
P
REP
ROCES
S
ING
OF
DA
T
A
F
E
A
T
UR
E
S
G
E
NE
RA
T
IONS
DIV
IS
ION
INT
O
T
RA
INING
A
ND
T
E
S
T
ING
DA
T
A
S
E
T
S
A
P
P
L
YIN
G
CL
A
S
S
IF
IERS
RE
S
UL
T
S
(c
o
n
f
u
sio
n
m
a
tri
x
,
c
las
sif
ica
ti
o
n
tab
le)
Evaluation Warning : The document was created with Spire.PDF for Python.