I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
2
,
A
p
r
il 2
0
2
5
,
p
p
.
1
2
8
1
~
1
2
8
9
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
2
.
p
p
1
2
8
1
-
1
2
8
9
1281
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Enha
ncing
f
ina
nc
ia
l cybers
ecuri
ty
v
ia
adv
a
nced ma
chine
lea
rning
:
a
na
ly
sis
,
co
mpa
riso
n
G
ra
ce
O
det
t
e
B
o
us
s
i
1
,
H
im
a
ns
hu
G
u
pta
2
,
Sy
ed
Ak
hte
r
H
o
s
s
a
in
3
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
A
mi
t
y
U
n
i
v
e
r
si
t
y
,
N
o
i
d
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
C
y
b
e
r
S
e
c
u
r
i
t
y
,
A
mi
t
y
U
n
i
v
e
r
si
t
y
,
N
o
i
d
a
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
Li
b
e
r
a
l
A
r
t
s,
D
h
a
k
a
,
B
a
n
g
l
a
d
e
sh
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
2
2
,
2
0
2
4
R
ev
is
ed
No
v
1
4
,
2
0
2
4
Acc
ep
ted
No
v
2
4
,
2
0
2
4
Th
e
fin
a
n
c
ial
se
c
to
r
is
a
p
rime
t
a
rg
e
t
fo
r
c
y
b
e
r
-
a
tt
a
c
k
s
d
u
e
to
t
h
e
se
n
siti
v
e
n
a
tu
re
o
f
t
h
e
d
a
ta
it
h
a
n
d
les
.
As
th
e
fre
q
u
e
n
c
y
a
n
d
so
p
h
isti
c
a
ti
o
n
o
f
c
y
b
e
r
th
re
a
ts
c
o
n
ti
n
u
e
t
o
rise
,
imp
lem
e
n
ti
n
g
e
ffe
c
ti
v
e
se
c
u
rit
y
m
e
a
su
re
s
b
e
c
o
m
e
s
p
a
ra
m
o
u
n
t.
In
t
h
is
p
a
p
e
r
we
p
r
o
v
i
d
e
a
c
o
m
p
re
h
e
n
siv
e
c
o
m
p
a
ri
so
n
o
f
si
x
p
ro
m
in
e
n
t
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
u
ti
li
z
e
d
i
n
th
e
fi
n
a
n
c
ial
in
d
u
stry
f
o
r
c
y
b
e
r
-
a
tt
a
c
k
p
re
v
e
n
ti
o
n
.
T
h
e
st
u
d
y
a
ims
to
i
d
e
n
ti
f
y
th
e
b
e
st
-
p
e
rfo
rm
in
g
m
o
d
e
l
a
n
d
su
b
se
q
u
e
n
tl
y
c
o
m
p
a
r
e
s
it
s
p
e
rfo
rm
a
n
c
e
with
a
p
ro
p
o
se
d
m
o
d
e
l
tailo
re
d
t
o
th
e
s
p
e
c
ifi
c
c
h
a
ll
e
n
g
e
s
fa
c
e
d
b
y
fi
n
a
n
c
ial
i
n
stit
u
ti
o
n
s.
T
h
is
p
a
p
e
r
lo
o
k
s
a
t
u
sin
g
a
d
v
a
n
c
e
d
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
s
t
o
m
a
k
e
c
y
b
e
rse
c
u
rit
y
stro
n
g
e
r
fo
r
fi
n
a
n
c
ial
in
stit
u
ti
o
n
s.
Th
e
wo
r
k
e
x
p
l
o
re
s
t
h
e
d
e
p
l
o
y
m
e
n
t
o
f
c
u
tt
in
g
-
e
d
g
e
m
a
c
h
in
e
lea
rn
i
n
g
a
lg
o
rit
h
m
s
-
l
o
g
ist
ic
re
g
re
ss
io
n
,
ra
n
d
o
m
fo
re
st,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
(
S
VM),
K
-
n
e
a
re
st
n
e
ig
h
b
o
u
r
(KN
N),
n
a
ï
v
e
Ba
y
e
s,
e
x
trem
e
g
ra
d
ien
t
b
o
o
sti
n
g
(
XG
Bo
o
st
)
,
a
n
d
d
e
e
p
lea
rn
i
n
g
tec
h
n
i
q
u
e
(De
n
se
Lay
e
r)
-
to
fo
rti
fy
t
h
e
c
y
b
e
rse
c
u
rit
y
fra
m
e
wo
rk
wit
h
in
fin
a
n
c
ia
l
in
stit
u
ti
o
n
s.
Th
r
o
u
g
h
a
m
e
ti
c
u
l
o
u
s
a
n
a
ly
sis
a
n
d
c
o
m
p
a
ra
ti
v
e
stu
d
y
,
w
e
e
x
p
lo
re
t
h
e
e
ffica
c
y
,
sc
a
lab
il
it
y
,
a
n
d
p
ra
c
ti
c
a
l
imp
lem
e
n
tatio
n
a
sp
e
c
ts
o
f
v
a
rio
u
s
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
tailo
re
d
to
a
d
d
re
ss
c
y
b
e
rse
c
u
rit
y
c
o
n
c
e
rn
s.
Ad
d
it
i
o
n
a
ll
y
,
we
p
r
o
p
o
se
a
fra
m
e
wo
rk
fo
r
in
te
g
ra
ti
n
g
th
e
m
o
st
e
ffe
c
ti
v
e
m
a
c
h
in
e
lea
rn
i
n
g
m
o
d
e
l
s
in
t
o
e
x
isti
n
g
c
y
b
e
rse
c
u
rit
y
i
n
fra
stru
c
tu
re
,
o
ffe
rin
g
in
si
g
h
ts
i
n
t
o
b
o
lsterin
g
r
e
sili
e
n
c
e
a
g
a
in
st
e
v
o
l
v
in
g
c
y
b
e
r
t
h
re
a
ts.
In
o
u
r
c
o
m
p
a
riso
n
,
XG
Bo
o
st
e
x
h
ib
it
e
d
o
u
tstan
d
in
g
p
e
rfo
rm
a
n
c
e
with
a
n
a
c
c
u
ra
c
y
o
f
9
5
%
.
K
ey
w
o
r
d
s
:
C
y
b
er
s
ec
u
r
ity
Dee
p
l
ea
r
n
in
g
Ex
tr
em
e
g
r
a
d
ien
t b
o
o
s
tin
g
Ma
ch
in
e
l
ea
r
n
in
g
Ma
lwar
e
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
:
Gr
ac
e
Od
ette
B
o
u
s
s
i
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
Am
ity
Un
i
v
er
s
ity
No
id
a
s
ec
to
r
1
4
3
,
2
0
1
3
0
1
,
Utt
ar
Pra
d
esh
,
I
n
d
ia
E
m
ail: g
r
ac
eb
o
u
s
s
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
ig
ital
lan
d
s
ca
p
e
h
as
m
ad
e
s
ig
n
if
ican
t
ad
v
an
ce
m
en
ts
,
esp
ec
ially
o
n
lin
e,
wh
er
e
a
m
ajo
r
ity
o
f
o
u
r
ac
tiv
ities
tak
e
p
lace
,
d
u
e
to
t
h
e
cr
ea
tiv
e
m
et
h
o
d
s
em
p
lo
y
e
d
b
y
attac
k
er
s
,
th
e
r
is
k
o
f
cy
b
er
attac
k
s
is
r
ap
id
ly
in
cr
ea
s
in
g
[
1
]
.
R
ap
id
tech
n
o
l
o
g
ical
ev
o
lu
tio
n
a
n
d
in
cr
ea
s
in
g
in
ter
n
et
u
s
er
s
,
r
ea
ch
in
g
4
.
4
b
illi
o
n
in
2
0
1
9
,
ar
e
ex
p
ec
ted
to
r
is
e
p
o
s
t
-
C
OVI
D
-
1
9
.
W
ith
o
n
lin
e
s
er
v
ices
h
o
ld
in
g
s
en
s
itiv
e
d
ata,
attac
k
er
s
in
cr
ea
s
in
g
ly
tar
g
et
h
ac
k
in
g
s
u
ch
p
latf
o
r
m
s
[
2
]
.
I
n
to
d
ay
'
s
d
ig
ital
er
a,
th
e
f
in
a
n
cial
s
ec
to
r
o
p
er
ates
with
in
a
n
in
tr
icate
web
o
f
in
ter
co
n
n
ec
ted
s
y
s
tem
s
an
d
p
r
o
ce
s
s
es,
m
ak
in
g
it
a
p
r
im
e
tar
g
et
f
o
r
cy
b
er
th
r
ea
t
s
o
f
u
n
p
r
ec
e
d
en
te
d
s
o
p
h
is
ticatio
n
an
d
s
ca
le
[
3
]
.
As
d
ig
ital
tr
an
s
ac
tio
n
s
,
s
en
s
iti
v
e
f
in
an
cial
d
ata,
an
d
co
m
p
lex
n
etwo
r
k
s
b
ec
o
m
e
in
cr
ea
s
in
g
ly
co
m
m
o
n
,
tr
ad
iti
o
n
al
cy
b
er
s
ec
u
r
ity
m
ea
s
u
r
es
o
f
ten
p
r
o
v
e
in
s
u
f
f
icien
t
in
p
r
o
tectin
g
ag
ain
s
t
ev
o
lv
in
g
t
h
r
ea
ts
.
C
o
n
s
eq
u
en
tl
y
,
f
in
an
cial
in
s
titu
tio
n
s
ar
e
u
n
d
er
g
r
o
win
g
p
r
ess
u
r
e
to
s
tr
en
g
th
en
th
eir
d
ef
en
s
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
8
1
-
1
2
8
9
1282
an
d
m
itig
ate
th
e
r
is
k
s
p
o
s
ed
b
y
cy
b
er
-
attac
k
s
.
I
n
r
esp
o
n
s
e
to
th
is
u
r
g
en
t
n
ee
d
,
t
h
er
e
is
a
r
is
in
g
in
ter
est
in
h
ar
n
ess
in
g
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
to
en
h
an
c
e
cy
b
er
s
ec
u
r
ity
with
in
th
e
f
in
a
n
cial
s
ec
to
r
.
T
h
ese
tech
n
o
lo
g
ies p
lay
a
c
r
u
cial
r
o
l
e
in
t
h
e
im
p
lem
en
tatio
n
o
f
cy
b
er
d
ef
en
s
e
s
tr
ateg
ies
s
u
ch
as m
o
n
ito
r
in
g
,
c
o
n
tr
o
l,
th
r
ea
t
d
etec
tio
n
,
an
d
alar
m
s
y
s
tem
s
[
4
]
.
T
h
e
ad
o
p
tio
n
o
f
m
ac
h
in
e
lear
n
in
g
in
c
y
b
er
s
ec
u
r
ity
h
as
witn
ess
ed
s
ig
n
if
ican
t
g
r
o
wth
in
p
o
p
u
la
r
ity
[
5
]
.
T
h
e
cu
r
r
e
n
t
s
tate
o
f
f
in
a
n
cial
cy
b
er
s
ec
u
r
ity
u
n
d
er
s
co
r
e
s
th
e
ess
en
tial
r
o
le
o
f
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es
in
im
p
r
o
v
in
g
d
ef
e
n
s
e
m
ec
h
an
is
m
s
ag
ai
n
s
t
cy
b
er
th
r
ea
ts
.
R
esear
ch
er
s
ar
e
d
ir
ec
tin
g
th
eir
ef
f
o
r
ts
to
war
d
s
co
n
d
u
ctin
g
c
o
m
p
r
eh
e
n
s
iv
e
an
aly
s
es,
co
m
p
ar
ativ
e
s
tu
d
ies,
an
d
d
ev
elo
p
in
g
in
teg
r
atio
n
f
r
a
m
e
wo
r
k
s
to
eq
u
i
p
f
in
an
cial
in
s
ti
tu
tio
n
s
with
r
esil
ien
t
an
d
ad
a
p
tab
le
to
o
ls
.
T
h
ese
ad
v
an
ce
m
e
n
ts
em
p
o
we
r
th
e
f
i
n
an
cial
s
ec
to
r
to
m
o
r
e
ef
f
ec
tiv
ely
m
an
a
g
e
c
y
b
er
r
is
k
s
,
th
e
r
eb
y
s
af
eg
u
a
r
d
in
g
th
e
s
ec
u
r
ity
an
d
in
te
g
r
ity
o
f
s
en
s
itiv
e
f
in
an
cial
d
ata
a
n
d
tr
a
n
s
ac
tio
n
s
.
T
ec
h
n
o
lo
g
y
h
as
r
e
v
o
lu
tio
n
ize
d
o
u
r
liv
es,
b
r
in
g
in
g
im
m
en
s
e
co
n
v
en
ien
ce
b
u
t
also
in
tr
o
d
u
cin
g
a
h
o
s
t
o
f
ch
allen
g
es
[
6
]
.
On
e
n
o
tab
le
is
s
u
e
is
th
e
esca
latio
n
o
f
cy
b
e
r
s
ec
u
r
ity
th
r
ea
ts
d
u
e
to
th
e
r
ap
id
ad
v
an
ce
m
e
n
t
o
f
tech
n
o
lo
g
y
.
An
o
t
h
er
co
n
ce
r
n
is
th
e
ex
p
o
n
e
n
tial
g
r
o
wth
o
f
d
ata
v
o
lu
m
es
,
m
a
k
in
g
it
in
c
r
e
asin
g
ly
ch
allen
g
in
g
to
en
s
u
r
e
s
ec
u
r
ity
.
Mo
r
eo
v
e
r
,
h
ig
h
ly
s
k
illed
h
ac
k
er
s
with
ex
ten
s
iv
e
k
n
o
wled
g
e
o
f
s
y
s
tem
s
an
d
p
r
o
g
r
am
m
in
g
h
av
e
th
e
ab
ilit
y
to
ex
p
lo
it we
ll
-
p
r
o
tecte
d
s
y
s
tem
s
,
co
m
p
o
u
n
d
in
g
s
ec
u
r
ity
co
n
ce
r
n
s
[
7
]
.
T
h
e
ter
m
"m
alwa
r
e"
is
a
f
u
s
io
n
o
f
"m
alicio
u
s
co
d
e"
an
d
"m
alicio
u
s
s
o
f
twar
e,
"
d
en
o
tin
g
s
o
f
twar
e
d
esig
n
ed
with
th
e
p
r
im
ar
y
aim
o
f
g
ain
in
g
u
n
a
u
th
o
r
ize
d
ac
ce
s
s
to
ex
ter
n
al
to
o
ls
.
Fu
r
th
er
m
o
r
e,
m
alwa
r
e
h
as
th
e
p
o
ten
tial
to
in
f
lict
en
d
u
r
in
g
d
am
ag
e
o
n
b
o
th
i
n
d
iv
id
u
als
an
d
o
r
g
an
izatio
n
s
[
8
]
.
T
h
e
in
c
r
ea
s
in
g
r
elea
s
e
o
f
m
alwa
r
e
is
wo
r
r
y
i
n
g
s
ec
u
r
ity
ex
p
er
ts
wo
r
ld
wid
e.
I
t'
s
im
p
o
r
tan
t
f
o
r
r
esear
ch
er
s
an
d
th
e
s
ec
u
r
ity
co
m
m
u
n
ity
to
s
tay
u
p
d
at
ed
o
n
n
ew
ty
p
es
o
f
m
alwa
r
e
an
d
h
o
w
to
d
etec
t
th
em
[
9
]
.
C
y
b
er
s
ec
u
r
ity
is
in
cr
ea
s
in
g
ly
em
p
h
asizin
g
th
e
id
en
tific
atio
n
an
d
s
u
p
p
r
ess
io
n
o
f
m
alwa
r
e
[
1
0
]
.
T
h
is
s
h
if
t
r
ef
lects
th
e
g
r
o
win
g
r
ec
o
g
n
itio
n
o
f
t
h
e
s
ig
n
if
ic
an
t
th
r
ea
t
p
o
s
ed
b
y
m
alicio
u
s
s
o
f
twar
e
to
co
m
p
u
t
er
s
y
s
tem
s
,
n
etwo
r
k
s
,
an
d
d
ata
.
As
cy
b
er
th
r
ea
ts
co
n
tin
u
e
t
o
ev
o
lv
e
an
d
b
ec
o
m
e
m
o
r
e
s
o
p
h
is
ticated
,
d
etec
tin
g
an
d
m
itig
atin
g
m
alwa
r
e
h
as
b
ec
o
m
e
a
t
o
p
p
r
io
r
ity
f
o
r
c
y
b
er
s
ec
u
r
it
y
p
r
o
f
ess
io
n
als
an
d
o
r
g
an
izati
o
n
s
[
1
1
]
.
B
y
im
p
lem
e
n
tin
g
r
o
b
u
s
t
d
etec
tio
n
an
d
m
itig
atio
n
s
tr
ateg
ies,
cy
b
er
s
ec
u
r
ity
e
x
p
er
ts
aim
to
s
af
eg
u
ar
d
d
ig
ital
ass
ets,
p
r
ev
e
n
t
u
n
au
t
h
o
r
ized
ac
ce
s
s
,
an
d
m
in
im
ize
th
e
im
p
ac
t
o
f
m
alwa
r
e
-
r
elate
d
in
ci
d
en
ts
o
n
in
d
iv
id
u
als,
b
u
s
in
ess
es,
an
d
cr
itical
in
f
r
astru
ctu
r
e.
R
esear
ch
er
s
ar
e
in
ter
ested
in
u
s
in
g
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
lear
n
in
g
b
ec
a
u
s
e
th
ey
ca
n
cr
ea
te
ad
v
a
n
ce
d
m
o
d
els
f
o
r
d
etec
tin
g
co
m
p
licated
m
alwa
r
e
[
1
2
]
.
T
h
is
r
esear
ch
en
d
ea
v
o
u
r
s
to
d
elv
e
in
to
th
e
r
ea
lm
o
f
s
o
p
h
i
s
ticated
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
o
lo
g
ies
an
d
th
eir
a
p
p
licatio
n
in
en
h
an
cin
g
cy
b
er
s
ec
u
r
ity
with
in
f
in
an
cial
in
s
titu
tio
n
s
.
T
h
r
o
u
g
h
a
co
m
p
r
eh
en
s
iv
e
an
aly
s
is
an
d
im
p
le
m
en
tatio
n
co
m
p
ar
is
o
n
,
th
is
s
tu
d
y
s
ee
k
s
t
o
elu
cid
ate
th
e
ef
f
icac
y
,
s
ca
lab
ilit
y
,
an
d
p
r
ac
tical
im
p
licatio
n
s
o
f
v
ar
io
u
s
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
tai
lo
r
ed
s
p
ec
if
ically
f
o
r
f
in
an
c
ial
cy
b
er
s
ec
u
r
ity
.
B
y
ex
am
in
in
g
th
e
s
tr
en
g
th
s
an
d
lim
itatio
n
s
o
f
d
if
f
er
en
t
a
p
p
r
o
ac
h
es,
we
aim
t
o
p
r
o
v
id
e
in
s
ig
h
ts
in
to
th
e
o
p
tim
al
u
tili
za
tio
n
o
f
m
ac
h
i
n
e
lear
n
i
n
g
tech
n
iq
u
es
to
ad
d
r
ess
th
e
u
n
iq
u
e
ch
allen
g
es
f
ac
ed
b
y
f
in
an
cial
in
s
titu
tio
n
s
in
s
af
eg
u
ar
d
in
g
th
eir
d
ig
ital a
s
s
ets an
d
in
f
r
astru
c
tu
r
e.
T
h
e
o
v
er
ar
c
h
in
g
o
b
jectiv
e
o
f
th
is
r
esear
ch
is
two
f
o
ld
.
F
ir
s
tly
,
to
as
s
es
s
th
e
p
er
f
o
r
m
an
ce
an
d
s
u
itab
ilit
y
o
f
ad
v
a
n
ce
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
in
d
e
tectin
g
an
d
m
itig
atin
g
cy
b
er
th
r
ea
ts
with
in
th
e
f
in
an
cial
s
ec
to
r
.
S
ec
o
n
d
ly
,
t
o
p
r
o
p
o
s
e
a
f
r
am
ew
o
r
k
f
o
r
th
e
in
teg
r
atio
n
a
n
d
im
p
le
m
en
tatio
n
o
f
th
ese
tech
n
iq
u
es
in
to
ex
is
tin
g
cy
b
er
s
ec
u
r
ity
in
f
r
astru
ctu
r
e.
B
y
u
n
d
e
r
tak
in
g
th
is
en
d
ea
v
o
u
r
,
we
en
d
ea
v
o
u
r
to
co
n
tr
ib
u
te
to
th
e
ad
v
a
n
ce
m
en
t
o
f
cy
b
er
s
ec
u
r
ity
p
r
ac
tices
in
f
in
an
cial
in
s
titu
tio
n
s
,
p
av
in
g
th
e
way
f
o
r
m
o
r
e
r
esil
ien
t a
n
d
ad
ap
tiv
e
d
ef
en
ce
m
ec
h
an
is
m
s
in
th
e
f
ac
e
o
f
ev
o
lv
in
g
cy
b
er
th
r
ea
ts
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Ma
licio
u
s
s
o
f
twar
e,
co
m
m
o
n
l
y
r
ef
er
r
e
d
to
as
m
alwa
r
e,
ca
n
s
ev
er
ely
d
eg
r
ad
e
d
e
v
ice
p
e
r
f
o
r
m
a
n
ce
an
d
p
o
s
e
a
r
is
k
o
f
d
ata
m
is
u
s
e
b
y
attac
k
er
s
o
n
ce
a
d
ev
ice
is
af
f
ec
ted
.
Mo
r
eo
v
er
,
ev
o
lv
in
g
m
alwa
r
e
ty
p
es
m
ak
e
co
n
v
e
n
tio
n
al
d
etec
tio
n
t
ec
h
n
iq
u
es c
u
m
b
e
r
s
o
m
e
an
d
in
ef
f
ec
tiv
e
f
o
r
id
en
tif
y
in
g
n
ew
a
n
d
g
en
er
ic
v
ar
ia
n
ts
[
1
3
]
.
I
m
p
lem
en
tin
g
m
ac
h
in
e
l
ea
r
n
in
g
an
d
d
ee
p
lear
n
in
g
m
e
th
o
d
in
o
r
d
e
r
to
r
ed
u
ce
th
e
im
p
ac
t
o
f
cy
b
er
c
r
im
e
h
as
b
ee
n
a
r
em
a
r
k
ab
le
wo
r
k
wh
ich
h
as
b
ee
n
d
o
n
e
b
y
m
an
y
au
th
o
r
s
.
R
o
p
o
n
en
a
et
a
l
.
[
1
4
]
s
aid
th
at
m
ac
h
in
e
lear
n
in
g
p
lay
s
a
cr
itical
r
o
le
in
cy
b
er
s
ec
u
r
ity
s
o
lu
tio
n
s
b
y
en
ab
lin
g
th
e
au
to
m
atic
an
aly
s
is
o
f
d
ata
p
atter
n
s
an
d
lear
n
in
g
f
r
o
m
th
em
t
o
p
r
e
v
e
n
t
s
im
ilar
attac
k
s
o
r
f
o
r
ec
ast
p
o
ten
tial
th
r
ea
ts
.
C
u
r
r
en
tly
,
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
ass
is
t
cy
b
er
s
ec
u
r
ity
p
r
o
f
ess
io
n
als
in
r
ap
id
ly
id
en
t
if
y
in
g
v
ar
io
u
s
ty
p
es
an
d
attr
ib
u
tes
o
f
m
alwa
r
e
[
1
5
]
,
[
1
6
]
.
B
o
k
o
l
o
et
a
l.
[
1
7
]
c
o
m
p
ar
es
s
ev
en
m
ac
h
in
e
lear
n
i
n
g
an
d
d
ee
p
lear
n
in
g
m
eth
o
d
s
to
d
etec
t
m
alwa
r
e
u
s
in
g
b
y
te,
o
p
co
d
e,
an
d
s
ec
tio
n
co
d
es.
T
h
e
s
tu
d
y
aim
s
t
o
ac
cu
r
ately
class
if
y
m
alwa
r
e
in
to
n
in
e
d
is
tin
ct
f
am
ilies
b
y
ex
tr
ac
tin
g
an
d
m
er
g
in
g
b
y
te,
s
ec
tio
n
,
an
d
o
p
co
d
e
d
ata.
T
ec
h
n
iq
u
es
in
c
lu
d
e
r
an
d
o
m
f
o
r
est,
d
ec
is
io
n
tr
ee
,
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
es
(
SVM
)
,
K
-
n
ea
r
est
n
eig
h
b
o
u
r
(
KNN
)
,
s
to
ch
asti
c
g
r
ad
ien
t
d
escen
t
(
SGD)
,
lo
g
is
tic
r
eg
r
ess
io
n
,
n
aïv
e
B
ay
es,
an
d
d
ee
p
lear
n
i
n
g
.
O
n
th
eir
s
id
e,
Ou
ah
a
b
et
a
l.
[
1
8
]
i
n
tr
o
d
u
ce
a
n
o
v
el
m
eth
o
d
f
o
r
id
e
n
tify
in
g
u
n
k
n
o
wn
m
alwa
r
e
ty
p
es
u
s
in
g
m
ac
h
in
e
lear
n
i
n
g
an
d
v
is
u
aliza
tio
n
.
T
h
r
ee
ef
f
icien
t
class
if
ier
s
ac
h
iev
e
u
p
to
9
8
%
p
r
ec
is
io
n
in
m
alwa
r
e
class
if
icatio
n
.
Fo
r
[
1
9
]
,
a
m
eth
o
d
c
o
m
b
in
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ci
n
g
fin
a
n
cia
l c
yb
ers
ec
u
r
ity
via
a
d
va
n
ce
d
ma
ch
i
n
e
le
a
r
n
in
g
:
… (
Gra
ce
Od
ette
B
o
u
s
s
i
)
1283
SVM
class
if
ier
s
an
d
ac
tiv
e
lear
n
in
g
b
y
lear
n
in
g
(
AL
B
L
)
ad
d
r
ess
es
lim
ited
lab
elled
d
ata
i
n
m
alwa
r
e
class
if
icatio
n
was
p
r
o
p
o
s
ed
,
t
h
ey
ev
al
u
atio
n
it
u
s
in
g
th
e
Mic
r
o
s
o
f
t
Ma
lwar
e
class
if
icatio
n
ch
allen
g
e
d
ataset
o
n
Kag
g
le
a
n
d
AL
B
L
d
em
o
n
s
tr
ated
th
e
ca
p
ab
ilit
y
t
o
en
h
a
n
c
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
.
Nu
m
er
o
u
s
s
tu
d
ies
h
a
v
e
ex
p
l
o
r
ed
th
e
d
ev
el
o
p
m
en
t
o
f
ef
f
ec
tiv
e
m
alwa
r
e
class
if
ier
s
,
with
[
2
0
]
s
h
o
wca
s
in
g
th
e
u
s
e
o
f
th
e
KN
N
alg
o
r
ith
m
.
Ad
d
itio
n
ally
,
r
es
ea
r
ch
er
s
h
a
v
e
d
el
v
ed
i
n
to
u
tili
zin
g
d
ee
p
lear
n
in
g
n
etwo
r
k
s
to
en
h
an
ce
m
alwa
r
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
C
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
,
as
d
em
o
n
s
tr
ated
in
[
2
1
]
,
[
2
2
]
,
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
h
av
e
b
ee
n
em
p
lo
y
ed
to
id
e
n
tify
b
o
th
tr
ad
itio
n
al
an
d
co
n
ce
ale
d
m
alwa
r
e
[
2
3
]
.
Desp
ite
t
h
ese
a
d
v
an
ce
m
e
n
ts
,
id
en
tify
i
n
g
e
n
tire
ly
n
ew
m
alwa
r
e
v
ar
ian
ts
r
e
m
ain
s
ch
allen
g
in
g
.
Ou
ah
ab
et
a
l
.
[
2
4
]
in
tr
o
d
u
ce
d
a
m
eth
o
d
f
o
r
d
etec
tin
g
u
p
co
m
in
g
m
alwa
r
e
g
e
n
er
atio
n
s
.
T
h
is
in
v
o
lv
ed
tr
ai
n
in
g
r
an
d
o
m
f
o
r
est
an
d
K
NN
m
o
d
els
o
n
2
4
d
is
tin
ct
m
alwa
r
e
f
a
m
ilies
.
Ven
k
atasu
b
r
am
an
ia
n
e
t
a
l
.
[
2
5
]
w
o
r
k
ed
o
n
I
o
T
m
alwa
r
e
an
aly
s
is
,
th
ey
o
u
tlin
e
v
ar
io
u
s
m
eth
o
d
s
th
at
co
m
b
in
e
f
ed
er
ate
d
lear
n
in
g
(
FL)
with
I
o
T
b
y
ex
p
lo
r
in
g
th
e
p
r
ac
tical
u
s
es
o
f
FL,
r
esear
ch
o
b
s
tacle
s
,
an
d
f
u
tu
r
e
r
esear
ch
p
at
h
s
.
Halb
o
u
n
i
et
a
l
.
[
2
6
]
ex
am
in
ed
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
,
f
o
cu
s
in
g
o
n
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
l
ea
r
n
in
g
alg
o
r
ith
m
s
co
m
b
attin
g
m
alicio
u
s
b
eh
a
v
io
u
r
,
t
h
ey
ex
p
lo
r
ed
r
ec
en
t
ad
v
an
ce
m
e
n
ts
in
n
etwo
r
k
im
p
lem
en
tatio
n
s
,
alg
o
r
ith
m
s
,
an
d
d
atasets
f
o
r
ef
f
ec
tiv
e
d
etec
tio
n
s
y
s
tem
s
.
I
n
th
eir
s
tu
d
y
,
J
in
et
a
l
.
[
2
7
]
in
tr
o
d
u
ce
d
a
m
alwa
r
e
d
etec
tio
n
m
eth
o
d
em
p
l
o
y
in
g
d
ee
p
lear
n
in
g
,
u
tili
zin
g
an
au
to
en
co
d
er
to
d
is
ce
r
n
m
alwa
r
e
'
s
f
u
n
ctio
n
al
tr
aits
.
Ach
iev
ed
ac
cu
r
ac
y
s
tan
d
s
at
9
3
%
[
2
7
]
.
Seth
i
et
a
l
.
[
2
8
]
d
ev
is
ed
a
m
a
lwar
e
d
etec
tio
n
f
r
am
ewo
r
k
u
ti
lizin
g
th
e
C
u
ck
o
o
s
an
d
b
o
x
f
o
r
d
y
n
am
ic
f
ile
an
aly
s
is
,
in
teg
r
atin
g
C
h
i
s
q
u
ar
e
an
d
r
an
d
o
m
f
o
r
est
tech
n
iq
u
es
f
o
r
f
ea
tu
r
e
s
elec
tio
n
,
with
d
ec
is
io
n
tr
ee
class
if
ier
s
ac
h
iev
in
g
th
e
h
ig
h
est
ac
cu
r
ac
y
.
Dar
em
et
a
l
.
[
2
9
]
in
tr
o
d
u
ce
d
a
m
o
d
el
lev
er
a
g
in
g
co
n
ce
p
t
d
r
if
t
d
etec
tio
n
an
d
s
eq
u
en
tial
d
ee
p
lear
n
in
g
,
ac
h
iev
in
g
9
9
.
4
1
%
ac
cu
r
ac
y
f
o
r
n
ew
m
alwa
r
e
v
ar
ia
n
ts
.
W
u
et
a
l
.
[
3
0
]
ad
d
r
ess
ed
u
n
b
alan
ce
d
d
atasets
u
s
in
g
a
th
r
ee
-
tier
ca
s
ca
d
in
g
ex
tr
em
e
g
r
a
d
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
ap
p
r
o
ac
h
an
d
co
s
t
-
s
en
s
itiv
e
lear
n
in
g
te
ch
n
iq
u
es,
d
e
m
o
n
s
tr
atin
g
t
h
e
ef
f
ec
tiv
en
ess
o
f
XGBo
o
s
t
in
m
alwa
r
e
d
etec
tio
n
.
Mc
Gif
f
et
a
l
.
[
3
1
]
en
h
a
n
ce
d
m
alwa
r
e
d
etec
tio
n
b
y
co
m
b
in
in
g
h
ar
d
war
e
f
ea
tu
r
es
an
d
p
er
m
is
s
io
n
d
ata,
r
esu
ltin
g
in
im
p
r
o
v
e
d
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
An
u
ar
et
a
l
.
[
3
2
]
p
r
o
p
o
s
ed
o
p
c
o
d
e
a
n
aly
s
is
f
o
r
m
alwa
r
e
d
etec
tio
n
,
s
h
o
win
g
h
ig
h
er
o
cc
u
r
r
e
n
ce
f
r
eq
u
e
n
cies
in
m
alwa
r
e
co
m
p
ar
ed
to
b
en
i
g
n
ap
p
licati
o
n
s
,
s
u
g
g
esti
n
g
its
s
ig
n
if
ican
ce
in
m
alwa
r
e
class
if
icatio
n
.
So
m
e
s
u
r
v
ey
wer
e
also
co
n
d
u
cted
an
d
th
is
is
th
e
ca
s
e
w
ith
[
3
3
]
wh
o
o
f
f
er
e
d
a
co
m
p
r
eh
en
s
iv
e
r
ev
iew
o
f
r
ec
e
n
t
cy
b
e
r
s
ec
u
r
ity
wo
r
k
s
em
p
lo
y
in
g
d
ee
p
lear
n
in
g
in
m
o
b
ile
an
d
wir
eless
n
etwo
r
k
s
,
en
co
m
p
ass
in
g
in
f
r
astru
ctu
r
e
t
h
r
ea
ts
,
s
o
f
twar
e
attac
k
s
,
an
d
p
r
iv
ac
y
p
r
o
tectio
n
.
T
h
ey
p
r
es
en
ted
d
etailed
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
ex
am
i
n
ed
cy
b
er
s
ec
u
r
it
y
wo
r
k
s
,
d
is
cu
s
s
ed
ch
allen
g
es,
im
p
lem
e
n
tatio
n
d
etails,
an
d
s
o
lu
tio
n
p
er
f
o
r
m
an
ce
,
id
e
n
tify
in
g
th
e
m
o
s
t
ef
f
ec
tiv
e
d
ee
p
lear
n
in
g
m
eth
o
d
s
f
o
r
v
ar
io
u
s
th
r
ea
ts
an
d
attac
k
s
.
I
n
th
eir
s
tu
d
y
,
th
e
a
u
th
o
r
s
[
3
4
]
le
v
er
ag
ed
th
e
m
ac
h
in
e
lear
n
in
g
m
alwa
r
e
d
etec
to
r
(
ML
MD
)
p
r
o
g
r
am
t
o
au
to
m
ate
s
tatic
an
d
d
y
n
am
ic
an
aly
s
is
p
r
o
ce
s
s
es.
T
h
ey
tr
ain
ed
XGBo
o
s
t
m
o
d
els
o
n
d
atasets
f
r
o
m
b
o
th
an
aly
s
es,
ac
h
iev
in
g
d
etec
tio
n
ac
cu
r
ac
ies
o
f
9
1
.
9
%
an
d
9
8
.
2
%,
alo
n
g
with
s
en
s
itiv
itie
s
o
f
9
6
.
4
%
an
d
9
8
.
5
%
f
o
r
s
tatic
an
d
d
y
n
am
ic
d
atasets
,
r
esp
ec
tiv
ely
.
T
o
im
p
r
o
v
e
c
y
b
er
s
ec
u
r
ity
,
s
ig
n
if
ican
t
ef
f
o
r
ts
h
av
e
b
ee
n
m
a
d
e
in
th
e
last
d
ec
a
d
e
to
u
tili
ze
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
ef
f
ec
tiv
el
y
.
E
n
h
an
ci
n
g
s
ec
u
r
ity
in
th
e
co
m
p
lex
tech
n
ical
lan
d
s
ca
p
e
r
eq
u
ir
es
a
ca
u
tio
u
s
an
d
s
tr
ateg
ic
ap
p
r
o
ac
h
to
a
d
d
r
ess
th
e
ev
o
lv
in
g
cy
b
er
th
r
ea
ts
[
3
5
]
a
n
d
Ma
lwar
e
v
ar
ian
ts
co
n
tin
u
e
t
o
ev
o
l
v
e
th
r
o
u
g
h
th
e
u
s
e
o
f
a
d
v
an
ce
d
p
ac
k
in
g
an
d
o
b
f
u
s
ca
tio
n
te
ch
n
iq
u
es,
p
o
s
in
g
in
c
r
ea
s
ed
c
h
allen
g
es
f
o
r
th
eir
class
if
icatio
n
an
d
d
etec
tio
n
[
3
6
]
.
As
th
e
i
n
ter
n
et
ex
p
an
d
s
a
n
d
s
o
cial
m
ed
ia
b
ec
o
m
es
m
o
r
e
wid
esp
r
ea
d
,
d
ata
b
r
ea
ch
es h
av
e
co
n
s
eq
u
e
n
tly
b
ec
o
m
e
a
p
r
im
a
r
y
c
o
n
ce
r
n
in
th
e
r
ea
lm
o
f
c
y
b
er
s
ec
u
r
ity
[
3
7
]
.
3.
M
E
T
H
O
D
T
h
e
m
eth
o
d
o
lo
g
y
e
n
co
m
p
a
s
s
es
d
ata
co
llect
io
n
,
m
o
d
el
s
elec
tio
n
,
ex
p
er
im
en
tal
d
e
s
ig
n
,
an
d
p
er
f
o
r
m
an
ce
ev
alu
atio
n
.
W
e
u
tili
ze
d
iv
er
s
e
d
atasets
r
ef
l
ec
tin
g
v
ar
ied
cy
b
er
-
attac
k
p
atter
n
s
an
d
n
o
r
m
a
l
o
p
er
atio
n
al
d
ata.
Selecte
d
m
o
d
els,
in
clu
d
in
g
lo
g
is
tic
r
eg
r
ess
io
n
,
r
an
d
o
m
f
o
r
est,
SVM
,
K
NN,
n
aïv
e
B
ay
es,
XGBo
o
s
t,
an
d
d
ee
p
lear
n
in
g
,
ar
e
ch
o
s
en
f
o
r
th
eir
ef
f
ec
tiv
en
ess
in
an
o
m
aly
d
etec
tio
n
.
Pre
-
p
r
o
ce
s
s
in
g
in
v
o
lv
es
d
ata
clea
n
in
g
,
n
o
r
m
aliza
tio
n
,
an
d
f
ea
tu
r
e
en
g
in
ee
r
in
g
.
Hy
p
e
r
p
ar
am
eter
tu
n
i
n
g
o
p
tim
izes
m
o
d
el
p
er
f
o
r
m
an
ce
.
E
v
alu
atio
n
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
a
r
ea
u
n
d
er
th
e
c
u
r
v
e
(
AUC
)
ass
ess
m
o
d
el
ef
f
ec
tiv
e
n
ess
.
Data
s
o
u
r
ce
d
f
r
o
m
th
e
C
an
ad
ian
I
n
s
titu
te
f
o
r
C
y
b
e
r
s
ec
u
r
ity
co
n
s
is
ts
o
f
1
1
,
5
9
8
r
o
ws
an
d
4
7
1
co
l
u
m
n
s
,
with
f
iv
e
lab
els r
ep
r
esen
tin
g
d
if
f
er
e
n
t c
lass
es.
3
.
1
.
P
r
o
ce
s
s
o
utline
T
h
e
r
esear
ch
p
r
o
ce
s
s
is
s
h
o
wn
in
Fig
u
r
e
1
.
T
h
e
d
iag
r
am
p
r
o
v
id
es
an
o
v
er
v
iew
o
f
th
e
wo
r
k
f
lo
w,
an
d
ea
ch
s
tep
is
ex
p
lain
ed
in
m
o
r
e
d
etail
in
th
e
tex
t
th
at
f
o
llo
ws th
e
d
iag
r
am
.
E
v
er
y
s
tag
e
o
f
th
e
p
r
o
ce
s
s
is
clea
r
ly
o
u
tlin
ed
to
h
elp
m
a
k
e
th
e
in
f
o
r
m
atio
n
ea
s
ier
to
u
n
d
er
s
tan
d
a
n
d
f
o
llo
w.
T
h
e
p
r
o
ce
s
s
d
escr
ib
ed
o
u
tlin
es
a
co
m
p
r
eh
e
n
s
iv
e
wo
r
k
f
lo
w
f
o
r
d
e
v
elo
p
in
g
an
d
ev
alu
atin
g
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
m
o
d
els.
L
et'
s
b
r
ea
k
it d
o
wn
s
tep
b
y
s
tep
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
8
1
-
1
2
8
9
1284
Step
1
: D
ata
p
re
-
p
r
o
ce
s
s
in
g
an
d
tr
ain
in
g
f
o
r
m
ac
h
in
e
lear
n
in
g
m
o
d
els
:
−
T
h
e
p
r
o
ce
s
s
b
eg
in
s
with
p
r
ep
ar
in
g
th
e
d
ata
f
o
r
tr
ain
i
n
g
m
a
ch
in
e
lear
n
in
g
m
o
d
els.
T
h
is
in
v
o
lv
es
s
tep
s
lik
e
clea
n
in
g
th
e
d
ata,
h
a
n
d
lin
g
m
is
s
in
g
v
alu
es,
en
co
d
in
g
ca
t
eg
o
r
ical
v
ar
ia
b
les,
an
d
s
ca
lin
g
f
ea
tu
r
es.
−
On
ce
th
e
d
ata
is
p
r
e
p
ar
ed
,
it'
s
s
p
lit
in
to
tr
ai
n
in
g
an
d
test
in
g
s
ets.
T
h
e
tr
ain
in
g
s
et
is
u
s
ed
to
tr
ain
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
wh
i
le
th
e
test
in
g
s
et
is
r
eser
v
ed
f
o
r
ev
alu
atin
g
t
h
eir
p
er
f
o
r
m
an
ce
.
Step
2
: Sele
ctio
n
o
f
m
ac
h
in
e
l
ea
r
n
in
g
m
o
d
els b
ased
o
n
an
al
y
s
is
o
f
v
ar
ian
ce
(
ANOV
A)
:
−
ANOV
A
is
a
s
tati
s
tical
m
eth
o
d
u
s
ed
to
co
m
p
ar
e
th
e
m
ea
n
s
o
f
d
if
f
e
r
en
t
g
r
o
u
p
s
to
d
eter
m
i
n
e
if
th
er
e
ar
e
s
ig
n
if
ican
t d
if
f
er
e
n
ce
s
b
etwe
en
th
em
.
−
I
n
t
h
i
s
s
t
e
p
,
A
N
O
V
A
i
s
e
m
p
l
o
y
e
d
t
o
c
o
m
p
a
r
e
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
v
a
r
i
o
u
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
o
n
t
h
e
t
r
a
i
n
i
n
g
d
a
t
a
.
T
h
i
s
h
e
l
p
s
i
n
s
e
l
e
c
t
i
n
g
t
h
e
m
o
s
t
p
r
o
m
i
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
f
o
r
f
u
r
t
h
e
r
e
v
a
l
u
a
t
i
o
n
.
Step
3
: T
r
ain
in
g
an
d
test
in
g
f
iv
e
d
if
f
er
e
n
t
m
ac
h
in
e
lear
n
in
g
m
o
d
els
:
−
Af
ter
s
elec
tin
g
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els
b
ased
o
n
ANOV
A,
th
e
n
ex
t
s
tep
in
v
o
lv
es
tr
ain
in
g
an
d
test
in
g
th
ese
m
o
d
els
o
n
t
h
e
d
a
taset.
T
h
is
allo
ws
f
o
r
ass
ess
in
g
th
eir
p
e
r
f
o
r
m
an
ce
in
ter
m
s
o
f
m
etr
ics
s
u
ch
as a
cc
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
−
T
h
e
ev
al
u
atio
n
o
f
ea
ch
m
o
d
el
p
r
o
v
id
es
in
s
ig
h
ts
in
to
its
s
tr
en
g
th
s
an
d
wea
k
n
ess
es,
aid
in
g
i
n
th
e
s
elec
tio
n
o
f
th
e
b
est
-
p
e
r
f
o
r
m
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
.
Step
4
: E
n
g
ag
e
m
en
t w
ith
d
ee
p
lear
n
in
g
a
n
d
m
o
d
el
cu
s
to
m
iza
tio
n
:
−
M
o
v
i
n
g
b
e
y
o
n
d
t
r
a
d
i
t
i
o
n
a
l
m
ac
h
i
n
e
l
e
a
r
n
i
n
g
,
t
h
e
w
o
r
k
f
l
o
w
t
r
a
n
s
i
ti
o
n
s
t
o
e
x
p
l
o
r
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
.
−
Prio
r
to
tr
ain
in
g
d
ee
p
lear
n
i
n
g
m
o
d
els,
th
e
d
ata
u
n
d
er
g
o
es
p
r
e
-
p
r
o
ce
s
s
in
g
s
im
ilar
t
o
th
e
m
ac
h
in
e
lear
n
in
g
p
h
ase.
On
ce
p
r
e
-
p
r
o
c
ess
ed
,
d
ee
p
lear
n
in
g
m
o
d
els ar
e
co
n
s
tr
u
cted
a
n
d
cu
s
to
m
ized
.
−
Mo
d
el
cu
s
to
m
izatio
n
in
v
o
lv
es
ad
ju
s
tin
g
th
e
a
r
ch
itectu
r
e,
h
y
p
er
p
ar
am
eter
s
,
an
d
o
t
h
er
s
etti
n
g
s
to
en
h
a
n
ce
p
er
f
o
r
m
an
ce
o
n
th
e
g
iv
en
task
.
−
H
o
w
e
v
e
r
,
d
e
s
p
i
t
e
c
u
s
t
o
m
i
z
a
t
i
o
n
e
f
f
o
r
t
s
,
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
h
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
a
l
l
s
s
h
o
r
t
o
f
e
x
p
e
c
t
a
t
i
o
n
s
.
Step
5
: T
r
an
s
f
er
l
ea
r
n
in
g
with
m
ac
h
in
e
lear
n
in
g
(
XGBo
o
s
t)
:
−
I
n
r
esp
o
n
s
e
to
th
e
s
u
b
o
p
tim
al
p
er
f
o
r
m
an
ce
o
f
th
e
cu
s
to
m
ize
d
d
ee
p
lear
n
in
g
m
o
d
el,
a
d
ec
is
io
n
is
m
ad
e
to
ex
p
lo
r
e
alter
n
ativ
e
ap
p
r
o
ac
h
es
.
−
T
r
an
s
f
er
lear
n
in
g
is
em
p
lo
y
e
d
,
wh
er
e
f
ea
tu
r
es
lear
n
e
d
f
r
o
m
th
e
d
ee
p
lear
n
i
n
g
m
o
d
el
ar
e
tr
an
s
f
er
r
ed
to
a
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
s
p
ec
if
ically
XGBo
o
s
t.
−
XGBo
o
s
t,
k
n
o
wn
f
o
r
its
r
o
b
u
s
tn
ess
an
d
p
er
f
o
r
m
an
ce
,
is
s
elec
ted
f
o
r
its
ab
ilit
y
to
h
a
n
d
le
co
m
p
le
x
d
atasets
ef
f
ec
tiv
ely
,
it
e
m
p
lo
y
s
d
ec
is
io
n
tr
ee
-
b
ased
tech
n
iq
u
es
to
class
if
y
m
alicio
u
s
e
x
ec
u
t
ab
les
th
r
o
u
g
h
a
g
r
ad
ien
t
b
o
o
s
tin
g
a
p
p
r
o
ac
h
[
3
8
]
.
Step
6
: Co
m
p
ar
is
o
n
o
f
m
ac
h
i
n
e
lear
n
in
g
,
d
ee
p
lear
n
in
g
,
an
d
XGBo
o
s
t
r
esu
lts
:
−
T
h
e
f
in
al
s
tep
in
v
o
lv
es
co
m
p
ar
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
d
ee
p
lear
n
in
g
m
o
d
el,
an
d
XGBo
o
s
t.
−
Me
tr
ics s
u
ch
as a
cc
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ar
e
u
s
ed
to
ev
alu
ate
a
n
d
co
m
p
ar
e
th
e
m
o
d
els.
−
B
ased
o
n
th
e
co
m
p
ar
is
o
n
,
X
GB
o
o
s
t
em
er
g
es
as
th
e
to
p
-
p
er
f
o
r
m
in
g
m
o
d
el,
s
u
r
p
ass
in
g
b
o
th
tr
a
d
itio
n
al
m
ac
h
in
e
lear
n
in
g
an
d
cu
s
to
m
i
ze
d
d
ee
p
lear
n
in
g
a
p
p
r
o
ac
h
es.
Fig
u
r
e
1
.
Pro
ce
s
s
o
u
tlin
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ci
n
g
fin
a
n
cia
l c
yb
ers
ec
u
r
ity
via
a
d
va
n
ce
d
ma
ch
i
n
e
le
a
r
n
in
g
:
… (
Gra
ce
Od
ette
B
o
u
s
s
i
)
1285
3
.
1
.
1
.
M
a
chine le
a
rning
m
o
dels
Ou
r
wo
r
k
is
d
o
n
e
u
s
in
g
m
ac
h
i
n
e
lear
n
i
n
g
a
n
d
d
ee
p
lear
n
in
g
,
s
o
in
th
is
p
ar
t,
we
will
b
e
talk
in
g
ab
o
u
t
th
e
s
tep
s
u
s
ed
in
o
r
d
e
r
to
tr
ai
n
o
u
r
m
ac
h
in
e
lear
n
in
g
m
o
d
el
s
.
Her
e
ar
e
th
e
f
iv
e
m
ac
h
in
e
l
ea
r
n
in
g
w
h
ich
h
av
e
b
ee
n
u
s
ed
:
n
aïv
e
B
ay
es
;
r
an
d
o
m
f
o
r
est
;
lo
g
is
tic
r
eg
r
ess
io
n
;
SVM
;
an
d
K
-
n
ea
r
est
.
Du
r
in
g
o
u
r
tr
ai
n
in
g
o
f
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
we
o
b
s
er
v
ed
th
at
r
a
n
d
o
m
f
o
r
est
ex
h
ib
ited
s
tr
o
n
g
p
er
f
o
r
m
an
ce
,
wh
ile
n
aïv
e
B
ay
es
p
er
f
o
r
m
ed
th
e
least e
f
f
ec
tiv
ely
.
T
ab
le
1
d
em
o
n
s
tr
ates th
eir
r
esp
ec
tiv
e
p
er
f
o
r
m
an
ce
.
a)
Data
p
re
-
p
r
o
ce
s
s
in
g
:
i
n
t
h
e
p
r
ep
ar
atio
n
o
f
o
u
r
d
ata
f
o
r
tr
ain
i
n
g
o
u
r
d
iv
er
s
e
m
ac
h
in
e
lea
r
n
i
n
g
m
o
d
els,
we
h
av
e
d
r
o
p
p
e
d
less
im
p
o
r
tan
t c
l
ass
es a
n
d
f
ea
tu
r
es b
y
r
u
n
n
in
g
th
ese
co
d
es:
X
=
d
f
.
d
r
o
p
(
c
o
lu
m
n
s
=[
'
C
lass
'
]
)
#
Featu
r
es
y
=
d
f
[
'
C
lass
'
]
#
T
ar
g
et
b)
Sp
lit
o
u
r
d
ata
in
to
tr
ai
n
in
g
a
n
d
test
in
g
wh
er
e
8
0
%
o
f
d
ata
wer
e
f
o
r
tr
ain
in
g
an
d
th
e
r
e
m
ain
in
g
2
0
%
f
o
r
test
in
g
.
#
Sp
lit th
e
d
ata
in
to
tr
a
in
in
g
an
d
test
s
ets
X_
tr
ain
,
X_
test
,
y
_
tr
ain
,
y
_
tes
t =
tr
ain
_
test
_
s
p
lit(X,
y
,
s
tr
atif
y
=y
,
test
_
s
ize=
0
.
2
,
r
a
n
d
o
m
_
s
tate=
4
2
)
c)
W
e
h
av
e
u
s
ed
ANOV
A
-
b
ased
to
h
elp
u
s
s
elec
tin
g
o
u
r
f
ea
tu
r
es
:
n
u
m
_
f
ea
t
u
r
es_
to
_
s
elec
t =
1
2
0
s
elec
to
r
=
SelectKBe
s
t(
s
co
r
e_
f
u
n
c=
f
_
class
if
,
k
=n
u
m
_
f
ea
tu
r
es_
to
_
s
elec
t)
X_
tr
ain
_
s
elec
ted
=
s
elec
to
r
.
f
it
_
tr
an
s
f
o
r
m
(
X_
tr
ain
,
y
_
tr
ain
)
X_
test
_
s
elec
ted
=
s
elec
to
r
.
tr
an
s
f
o
r
m
(
X_
test
)
T
ab
le
1
.
Ma
ch
i
n
e
lean
in
g
m
o
d
els p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
S
.
N
M
o
d
e
l
s
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%
)
R
e
c
a
l
l
(
%)
F1
-
s
c
o
r
e
(
%)
1
Lo
g
i
s
t
i
c
R
e
g
r
e
ssi
o
n
0
.
8
0
0
.
8
0
0
.
8
0
0
.
8
0
2
S
V
M
0
.
8
2
0
.
8
2
0
.
8
2
0
.
8
2
3
R
a
n
d
o
m F
o
r
e
s
t
0
.
9
4
0
.
9
4
0
.
9
4
0
.
9
4
4
K
N
N
0
.
9
0
0
.
9
0
0
.
9
0
0
.
9
0
5
N
a
ï
v
e
B
a
y
e
s
0
.
5
8
0
.
6
9
0
.
5
8
0
.
5
4
3
.
1
.
2
.
Dee
p lea
rning
m
o
del
Fo
llo
win
g
th
e
tr
ain
in
g
o
f
o
u
r
d
ata
u
s
in
g
m
ac
h
in
e
lear
n
in
g
,
we
u
tili
ze
d
th
e
s
am
e
d
ata
an
d
class
to
co
n
s
tr
u
ct
o
u
r
m
o
d
el
u
s
in
g
d
ee
p
lear
n
in
g
.
a)
Data
p
r
e
-
p
r
o
ce
s
s
in
g
1
-
W
e
p
r
ep
ar
e
d
d
ata
b
y
e
x
tr
a
ctin
g
th
e
in
p
u
t
f
ea
tu
r
es
(
X)
a
n
d
th
e
tar
g
et
v
ar
iab
le
(
y
)
f
o
r
tr
ain
in
g
a
p
r
ed
ictiv
e
m
o
d
el.
X
=
d
ata.
ilo
c[
:,
:
-
1
]
.
v
alu
es
y
=
d
ata.
ilo
c[
:,
-
1
]
.
v
alu
es
b)
C
o
n
v
er
t la
b
els to
s
tar
t f
r
o
m
0
y
-
= 1
c)
C
o
n
v
er
t ta
r
g
et
lab
els to
o
n
e
-
h
o
t
en
co
d
i
n
g
n
u
m
_
class
es =
len
(
n
p
.
u
n
iq
u
e(
y
)
)
y
_
en
co
d
ed
=
t
o
_
ca
teg
o
r
ical(
y
,
n
u
m
_
class
es=n
u
m
_
class
es)
d)
Sp
lit th
e
d
ata
in
to
tr
ain
in
g
an
d
test
in
g
s
ets
X_
tr
ain
,
X_
test
,
y
_
tr
ain
,
y
_
tes
t =
tr
ain
_
test
_
s
p
lit(X,
y
_
en
c
o
d
ed
,
test
_
s
ize=
0
.
2
,
r
an
d
o
m
_
s
tate=
4
2
)
e)
No
r
m
alize
th
e
f
ea
tu
r
es
s
ca
ler
=
Stan
d
ar
d
Scaler
(
)
X_
tr
ain
=
s
ca
ler
.
f
it_
tr
an
s
f
o
r
m
(
X_
tr
ain
)
X_
test
=
s
ca
ler
.
tr
an
s
f
o
r
m
(
X_
t
est)
f)
T
h
en
we
b
u
ild
o
u
r
m
o
d
el
m
o
d
el
=
Seq
u
e
n
tial(
)
m
o
d
el.
ad
d
(
Den
s
e(
1
2
8
,
in
p
u
t_
d
im
=X
_
tr
ain
.
s
h
ap
e[
1
]
,
ac
tiv
at
io
n
='
r
elu
'
)
)
m
o
d
el.
ad
d
(
Den
s
e(
6
4
,
ac
tiv
atio
n
='
r
elu
'
)
)
m
o
d
el.
ad
d
(
Den
s
e(
n
u
m
_
class
es,
ac
tiv
atio
n
='
s
o
f
tm
ax
'
)
)
Giv
en
th
e
s
u
b
o
p
tim
al
p
er
f
o
r
m
an
ce
o
f
o
u
r
cu
r
r
e
n
t m
o
d
el,
we
h
av
e
o
p
ted
to
tr
a
n
s
f
er
its
f
ea
tu
r
es to
an
XGBo
o
s
t
m
ac
h
in
e
lear
n
in
g
m
o
d
el.
T
h
is
s
tr
ateg
ic
d
ec
is
io
n
i
s
aim
ed
at
ex
p
lo
r
in
g
th
e
p
o
te
n
tial
f
o
r
ac
h
iev
in
g
im
p
r
o
v
e
d
r
esu
lts
co
m
p
ar
ed
to
th
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
p
r
ev
i
o
u
s
ly
tr
ain
e
d
m
o
d
els.
3
.
1
.
3
.
XG
B
o
o
s
t
Af
ter
our
m
o
d
el'
s
u
n
d
er
p
er
f
o
r
m
an
ce
,
we
tr
an
s
f
er
r
e
d
its
f
ea
tu
r
es
to
XGBo
o
s
t,
wh
er
e
it
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t im
p
r
o
v
em
en
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
8
1
-
1
2
8
9
1286
y
=
d
ata[
'
C
las
s
'
]
y
=
y
-
1
X_
tr
ain
,
X_
test
,
y
_
tr
ain
,
y
_
tes
t =
tr
ain
_
test
_
s
p
lit(X_
s
ca
led
,
y
,
test
_
s
ize=
0
.
2
,
r
an
d
o
m
_
s
tate=
4
2
)
#
I
n
itialize
m
o
d
els
x
g
b
_
m
o
d
el
=
XGBC
lass
if
ier
(
r
an
d
o
m
_
s
tate=
4
2
)
#
T
r
ain
a
n
d
ev
al
u
ate
ea
ch
m
o
d
el
x
g
b
_
ac
c
u
r
ac
y
,
x
g
b
_
p
r
ec
is
io
n
,
x
g
b
_
r
ec
all,
x
g
b
_
f
1
=
tr
ain
_
ev
alu
ate_
m
o
d
el(
x
g
b
_
m
o
d
el,
X_
tr
ain
,
y
_
tr
ain
,
X_
test
,
y
_
test
)
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
Af
ter
ex
ten
s
iv
e
test
in
g
,
XGBo
o
s
t,
r
an
d
o
m
f
o
r
est,
an
d
Den
s
e
l
ay
er
em
er
g
e
d
as
th
e
t
o
p
m
o
d
els
f
o
r
m
alwa
r
e
p
r
ev
e
n
tio
n
.
XGBo
o
s
t
d
em
o
n
s
tr
ated
e
x
ce
p
tio
n
al
p
e
r
f
o
r
m
a
n
ce
with
a
9
5
%
ac
cu
r
a
cy
r
ate,
ea
r
n
in
g
its
s
elec
tio
n
as th
e
f
in
al
d
ep
lo
y
ed
m
o
d
el.
E
v
alu
atio
n
m
etr
ics ar
e
p
r
esen
ted
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
Mo
d
el
ev
alu
atio
n
m
etr
ics h
ea
tm
ap
T
h
is
ca
p
ab
ilit
y
is
p
ar
ticu
lar
ly
v
alu
ab
le
in
task
s
lik
e
m
alwa
r
e
an
aly
s
is
,
wh
er
e
o
u
tlier
s
ar
e
s
ig
n
if
ican
t
an
o
m
alies
an
d
r
em
o
v
in
g
th
e
m
co
u
ld
lead
to
m
is
lead
in
g
c
o
n
clu
s
io
n
s
.
I
n
itially
,
we
tr
ain
ed
o
u
r
d
ata
u
s
in
g
f
iv
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
a
m
o
n
g
wh
ich
r
a
n
d
o
m
f
o
r
est
d
em
o
n
s
tr
ated
s
tr
o
n
g
p
er
f
o
r
m
an
ce
with
a
9
4
%
ac
cu
r
ac
y
r
ate.
R
an
d
o
m
f
o
r
est,
a
wid
ely
u
s
ed
s
u
p
er
v
is
ed
m
a
ch
in
e
lear
n
in
g
alg
o
r
ith
m
,
em
p
lo
y
s
d
ec
is
io
n
tr
ee
s
o
n
m
u
ltip
le
s
am
p
les.
Fo
r
class
if
icatio
n
,
it
co
n
s
id
er
s
th
e
m
ajo
r
ity
v
o
te,
wh
ile
f
o
r
r
e
g
r
ess
io
n
,
it
u
s
es
th
e
av
er
ag
e
v
o
te
[
3
9
]
.
Sin
ce
o
u
r
cu
s
to
m
ized
m
o
d
el
f
ell
s
h
o
r
t
at
9
1
%,
to
ca
p
italize
o
n
th
e
s
tr
en
g
th
s
o
f
o
u
r
cu
s
to
m
ized
m
o
d
el,
we
tr
an
s
f
er
r
ed
its
f
ea
tu
r
es
to
XGBo
o
s
t,
r
esu
ltin
g
in
a
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
f
9
5
%,
s
u
r
p
ass
in
g
ev
en
r
an
d
o
m
f
o
r
est.
XGBo
o
s
t,
a
h
ig
h
-
p
e
r
f
o
r
m
in
g
m
ac
h
in
e
lear
n
in
g
a
lg
o
r
ith
m
,
ac
h
iev
es
ex
ce
p
tio
n
al
ac
c
u
r
ac
y
b
y
e
m
p
l
o
y
in
g
XGBo
o
s
t
.
I
t
o
u
tp
ac
es
o
th
er
im
p
lem
en
tatio
n
s
in
s
p
ee
d
an
d
p
er
f
o
r
m
an
ce
,
p
u
s
h
in
g
co
m
p
u
tin
g
to
o
ls
f
o
r
b
o
o
s
ted
tr
ee
alg
o
r
it
h
m
s
to
th
eir
lim
its
[
4
0
]
.
C
o
n
s
eq
u
en
t
ly
,
XGBo
o
s
t
was
s
elec
ted
as
o
u
r
f
in
al
m
o
d
el
f
o
r
its
o
u
ts
tan
d
in
g
p
e
r
f
o
r
m
an
ce
an
d
ab
ilit
y
to
ef
f
ec
tiv
ely
h
an
d
le
d
ataset
co
m
p
lex
ities
.
T
o
h
ig
h
lig
h
t
th
e
s
ig
n
if
ican
ce
o
f
o
u
r
r
esu
lts
,
T
ab
le
2
p
r
esen
ts
a
co
m
p
ar
at
iv
e
an
aly
s
is
o
f
o
u
r
wo
r
k
ag
ain
s
t
ex
is
tin
g
m
eth
o
d
s
.
T
h
is
co
m
p
ar
is
o
n
clea
r
ly
d
em
o
n
s
tr
ates
th
at
o
u
r
ap
p
r
o
a
ch
y
ield
s
s
u
p
er
io
r
o
u
tco
m
es c
o
m
p
ar
ed
t
o
th
e
cu
r
r
en
t state
-
of
-
th
e
-
a
r
t te
ch
n
iq
u
es.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
with
th
e
ex
is
tin
g
m
o
d
els
R
e
f
e
r
e
n
c
e
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F
-
sco
r
e
(
%)
A
c
c
u
r
a
c
y
(
%)
[
4
1
]
95
93
94
91
[
4
2
]
94
94
93
95
[
4
3
]
91
94
94
94
[
4
4
]
94
94
94
95
O
u
r
p
r
o
p
o
s
e
d
mo
d
e
l
95
95
95
95
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ci
n
g
fin
a
n
cia
l c
yb
ers
ec
u
r
ity
via
a
d
va
n
ce
d
ma
ch
i
n
e
le
a
r
n
in
g
:
… (
Gra
ce
Od
ette
B
o
u
s
s
i
)
1287
5.
CO
M
P
ARA
T
I
V
E
ANA
L
YS
I
S
T
h
e
d
ec
is
io
n
b
etwe
en
tr
ad
iti
o
n
al
m
ac
h
i
n
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
m
o
d
els
d
ep
en
d
s
o
n
f
ac
to
r
s
s
u
ch
as
th
e
n
atu
r
e
o
f
th
e
p
r
o
b
lem
,
d
ata
co
m
p
lex
ity
,
an
d
th
e
n
ee
d
f
o
r
f
ea
tu
r
e
en
g
i
n
ee
r
in
g
.
E
ac
h
m
o
d
el
h
as
its
o
wn
s
tr
en
g
th
s
tailo
r
ed
to
d
if
f
er
en
t
s
ce
n
ar
io
s
.
I
n
o
u
r
ca
s
e,
am
o
n
g
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
XGBo
o
s
t
em
er
g
es
as
th
e
s
tan
d
o
u
t
p
er
f
o
r
m
er
with
n
ea
r
-
p
er
f
ec
t m
etr
ics
(
ar
o
u
n
d
0
.
9
5
)
,
s
h
o
wca
s
in
g
its
ex
ce
p
tio
n
al
ab
ilit
y
to
h
an
d
le
n
u
an
ce
s
with
in
th
e
d
ataset.
T
h
e
p
er
f
o
r
m
an
ce
o
f
all
m
o
d
els is
d
ep
icted
in
Fig
u
r
e
3
.
Fig
u
r
e
3
.
Per
f
o
r
m
an
c
e
m
etr
ics co
m
p
ar
is
o
n
f
o
r
d
if
f
er
e
n
t c
lass
if
ier
s
6.
CO
NCLU
SI
O
N
F
UT
URE
S
CO
P
E
Ou
r
r
esear
ch
f
o
c
u
s
es
o
n
im
p
r
o
v
in
g
cy
b
er
s
ec
u
r
ity
in
b
an
k
s
an
d
s
im
ilar
in
s
titu
tio
n
s
u
s
in
g
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
.
T
h
ese
in
s
titu
tio
n
s
f
ac
e
s
er
io
u
s
r
is
k
s
f
r
o
m
cy
b
er
attac
k
s
d
u
e
to
th
e
s
en
s
itiv
e
d
ata
th
ey
m
an
a
g
e,
s
o
ef
f
ec
tiv
e
s
ec
u
r
ity
m
ea
s
u
r
es
ar
e
cr
u
cial
.
W
e
s
tu
d
ied
h
o
w
d
if
f
er
e
n
t
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
ca
n
h
el
p
d
etec
t
an
d
p
r
ev
e
n
t
cy
b
e
r
th
r
ea
ts
,
esp
ec
i
ally
m
alwa
r
e.
W
e
co
m
p
ar
ed
s
ix
m
ain
tech
n
iq
u
es:
lo
g
is
tic
r
eg
r
ess
io
n
,
r
an
d
o
m
f
o
r
est,
SVM,
KNN,
n
aïv
e
B
a
y
es
,
an
d
XGBo
o
s
t,
as
well
as
a
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
with
De
n
s
e
L
ay
er
.
Ou
r
f
in
d
in
g
s
s
h
o
w
th
at
XGBo
o
s
t
p
er
f
o
r
m
e
d
th
e
b
est,
ac
h
iev
in
g
a
n
im
p
r
ess
iv
e
ac
cu
r
ac
y
o
f
9
5
%.
T
h
is
d
em
o
n
s
tr
ates
it
s
ef
f
ec
tiv
en
ess
in
h
an
d
lin
g
co
m
p
le
x
cy
b
er
s
ec
u
r
ity
d
ata,
esp
ec
ially
f
o
r
task
s
lik
e
m
alwa
r
e
d
etec
tio
n
.
Ou
r
s
tu
d
y
em
p
h
asizes
th
e
im
p
o
r
tan
ce
o
f
i
n
teg
r
atin
g
a
d
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els
in
to
c
u
r
r
e
n
t
cy
b
e
r
s
ec
u
r
ity
s
y
s
tem
s
to
b
etter
p
r
o
tect
ag
ain
s
t
ev
o
lv
i
n
g
c
y
b
er
th
r
e
ats.
W
e
p
r
o
p
o
s
e
a
f
r
am
ewo
r
k
f
o
r
im
p
lem
en
tin
g
th
ese
tech
n
iq
u
es
to
ad
v
an
ce
cy
b
e
r
s
ec
u
r
ity
p
r
ac
tices
in
f
i
n
an
cial
in
s
titu
tio
n
s
.
Mo
v
in
g
f
o
r
war
d
,
f
u
tu
r
e
r
ese
ar
ch
en
d
ea
v
o
u
r
s
s
h
o
u
ld
f
o
cu
s
o
n
r
ef
in
in
g
an
d
o
p
tim
izin
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
ex
p
lo
r
in
g
th
eir
in
teg
r
atio
n
in
to
r
ea
l
-
tim
e
t
h
r
ea
t
d
et
ec
tio
n
s
y
s
tem
s
,
an
d
ex
p
a
n
d
in
g
th
eir
ap
p
licatio
n
ac
r
o
s
s
d
if
f
er
en
t
v
ec
to
r
s
o
f
cy
b
er
th
r
ea
ts
.
B
y
s
tay
in
g
ah
ea
d
o
f
cy
b
er
c
r
im
in
als
th
r
o
u
g
h
th
e
s
tr
ateg
ic
u
tili
za
tio
n
o
f
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es,
f
i
n
an
cial
in
s
titu
tio
n
s
ca
n
f
o
r
tify
th
eir
cy
b
er
s
ec
u
r
ity
d
ef
en
ce
s
a
n
d
s
af
eg
u
ar
d
th
ei
r
d
ig
ital a
s
s
ets ag
ain
s
t e
m
er
g
in
g
th
r
ea
ts
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
A
l
j
a
b
r
i
e
t
a
l
.
,
“
D
e
t
e
c
t
i
n
g
m
a
l
i
c
i
o
u
s
U
R
Ls
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s:
r
e
v
i
e
w
a
n
d
r
e
s
e
a
r
c
h
d
i
r
e
c
t
i
o
n
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
2
1
3
9
5
–
1
2
1
4
1
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
2
2
3
0
7
.
[
2
]
E.
H
o
sam
,
H
.
H
o
s
n
y
,
W
.
A
s
h
r
a
f
,
a
n
d
A
.
S
.
K
a
se
b
,
“
S
Q
L
i
n
j
e
c
t
i
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
i
n
2
0
2
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
o
f
t
C
o
m
p
u
t
i
n
g
&
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
(
I
S
C
MI)
,
2
0
2
1
,
p
p
.
1
5
–
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
M
I
5
3
8
4
0
.
2
0
2
1
.
9
6
5
4
8
2
0
.
[
3
]
S
.
R
a
z
a
u
l
l
a
e
t
a
l
.
,
“
T
h
e
a
g
e
o
f
r
a
n
s
o
m
w
a
r
e
:
A
s
u
r
v
e
y
o
n
t
h
e
e
v
o
l
u
t
i
o
n
,
t
a
x
o
n
o
m
y
,
a
n
d
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
4
0
6
9
8
–
4
0
7
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
6
8
5
3
5
.
[
4
]
D
.
D
a
s
g
u
p
t
a
,
Z
.
A
k
h
t
a
r
,
a
n
d
S
.
S
e
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
c
y
b
e
r
se
c
u
r
i
t
y
:
a
c
o
m
p
r
e
h
e
n
si
v
e
s
u
r
v
e
y
,
”
J
o
u
r
n
a
l
o
f
D
e
f
e
n
se
M
o
d
e
l
i
n
g
a
n
d
S
i
m
u
l
a
t
i
o
n
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
5
7
–
1
0
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
7
7
/
1
5
4
8
5
1
2
9
2
0
9
5
1
2
7
5
.
[
5
]
M
.
O
z
k
a
n
-
O
k
a
y
e
t
a
l
.
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
:
Ev
a
l
u
a
t
i
n
g
t
h
e
e
f
f
i
c
i
e
n
c
y
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
o
n
c
y
b
e
r
s
e
c
u
r
i
t
y
s
o
l
u
t
i
o
n
s
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
2
2
2
9
–
1
2
2
5
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
5
5
5
4
7
.
[
6
]
Y
.
Li
a
n
d
Q
.
Li
u
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
st
u
d
y
o
f
c
y
b
e
r
-
a
t
t
a
c
k
s a
n
d
c
y
b
e
r
sec
u
r
i
t
y
;
e
merg
i
n
g
t
r
e
n
d
s
a
n
d
r
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
s,”
En
e
r
g
y
Re
p
o
rt
s
,
v
o
l
.
7
,
p
p
.
8
1
7
6
–
8
1
8
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
r
.
2
0
2
1
.
0
8
.
1
2
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
8
1
-
1
2
8
9
1288
[
7
]
Ö
.
A
sl
a
n
,
S
.
S
.
A
k
t
u
ğ
,
M
.
O
z
k
a
n
-
O
k
a
y
,
A
.
A
.
Y
i
l
m
a
z
,
a
n
d
E
.
A
k
i
n
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
c
y
b
e
r
sec
u
r
i
t
y
v
u
l
n
e
r
a
b
i
l
i
t
i
e
s,
t
h
r
e
a
t
s
,
a
t
t
a
c
k
s,
a
n
d
so
l
u
t
i
o
n
s,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
0
6
1
3
3
3
.
[
8
]
S
.
Li
m
a
e
t
a
l
.
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
b
a
se
d
a
n
t
i
v
i
r
u
s
i
n
o
r
d
e
r
t
o
d
e
t
e
c
t
mal
w
a
r
e
p
r
e
v
e
n
t
i
v
e
l
y
,
”
Pr
o
g
ress
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
1
–
2
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
7
4
8
-
0
2
0
-
0
0
2
2
0
-
4.
[
9
]
N
.
M
o
h
a
p
a
t
r
a
,
B
.
S
a
t
a
p
a
t
h
y
,
B
.
M
o
h
a
p
a
t
r
a
,
a
n
d
B
.
K
.
M
o
h
a
n
t
a
,
“
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
i
n
2
0
2
2
1
3
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
N
e
t
w
o
r
k
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
C
C
N
T
)
,
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
N
T
5
4
8
2
7
.
2
0
2
2
.
9
9
8
4
2
1
8
.
[
1
0
]
G
.
T.
R
e
d
d
y
e
t
a
l
.
,
“
A
n
e
n
sem
b
l
e
b
a
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Em
e
r
g
i
n
g
T
re
n
d
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
i
c
-
ETI
T
E
2
0
2
0
,
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
-
ETI
TE4
7
9
0
3
.
2
0
2
0
.
2
3
5
.
[
1
1
]
R
.
K
u
m
a
r
a
n
d
S
.
G
e
e
t
h
a
,
“
M
a
l
w
a
r
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
X
G
b
o
o
s
t
-
G
r
a
d
i
e
n
t
b
o
o
st
e
d
d
e
c
i
si
o
n
t
r
e
e
,
”
Ad
v
a
n
c
e
s
i
n
S
c
i
e
n
c
e
,
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
r
i
n
g
S
y
s
t
e
m
s
,
v
o
l
.
5
,
n
o
.
5
,
p
p
.
5
3
6
–
5
4
9
,
2
0
2
0
,
d
o
i
:
1
0
.
2
5
0
4
6
/
A
J
0
5
0
5
6
6
.
[
1
2
]
P
.
M
a
n
i
r
i
h
o
,
A
.
N
.
M
a
h
m
o
o
d
,
a
n
d
M
.
J.
M
.
C
h
o
w
d
h
u
r
y
,
“
A
st
u
d
y
o
n
mal
i
c
i
o
u
s
so
f
t
w
a
r
e
b
e
h
a
v
i
o
u
r
a
n
a
l
y
s
i
s
a
n
d
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s:
Ta
x
o
n
o
m
y
,
c
u
r
r
e
n
t
t
r
e
n
d
s
a
n
d
c
h
a
l
l
e
n
g
e
s,
”
Fu
t
u
r
e
G
e
n
e
ra
t
i
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
,
v
o
l
.
1
3
0
,
p
p
.
1
–
1
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
1
.
1
1
.
0
3
0
.
[
1
3
]
U
.
V
N
i
k
a
m
a
n
d
V
.
M
.
D
e
s
h
m
u
h
,
“
P
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
s
i
n
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
2
2
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
i
st
r
i
b
u
t
e
d
C
o
m
p
u
t
i
n
g
a
n
d
E
l
e
c
t
r
i
c
a
l
C
i
r
c
u
i
t
s
a
n
d
E
l
e
c
t
r
o
n
i
c
s
(
I
C
D
C
E
C
E)
,
2
0
2
2
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
C
EC
E5
3
9
0
8
.
2
0
2
2
.
9
7
9
3
1
0
2
.
[
1
4
]
E.
R
o
p
o
n
e
n
a
,
J.
K
a
mp
a
r
s,
A
.
G
a
i
l
i
t
i
s,
a
n
d
J.
S
t
r
o
d
s,
“
A
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
c
y
b
e
r
sec
u
r
i
t
y
i
n
d
a
t
a
c
e
n
t
e
r
s
,
”
i
n
2
0
2
1
6
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
S
c
i
e
n
t
i
f
i
c
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
Ma
n
a
g
e
m
e
n
t
S
c
i
e
n
c
e
o
f
R
i
g
a
T
e
c
h
n
i
c
a
l
U
n
i
v
e
rs
i
t
y
,
Pro
c
e
e
d
i
n
g
s
,
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
TM
S
5
2
8
2
6
.
2
0
2
1
.
9
6
1
5
3
2
1
.
[
1
5
]
J.
L.
G
.
To
r
r
e
s
,
C
.
A
.
C
a
t
a
n
i
a
,
a
n
d
E.
V
e
a
s,
“
A
c
t
i
v
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
l
a
b
e
l
n
e
t
w
o
r
k
t
r
a
f
f
i
c
d
a
t
a
se
t
s,
”
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
s
a
.
2
0
1
9
.
1
0
2
3
8
8
.
[
1
6
]
K
.
S
e
t
h
i
,
S
.
K
.
C
h
a
u
d
h
a
r
y
,
B
.
K
.
T
r
i
p
a
t
h
y
,
a
n
d
P
.
B
e
r
a
,
“
A
n
o
v
e
l
m
a
l
w
a
r
e
a
n
a
l
y
si
s
f
r
a
mew
o
r
k
f
o
r
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
i
s
t
ri
b
u
t
e
d
C
o
m
p
u
t
i
n
g
a
n
d
N
e
t
w
o
rk
i
n
g
,
2
0
1
8
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
4
5
/
3
1
5
4
2
7
3
.
3
1
5
4
3
2
6
.
[
1
7
]
B
.
B
o
k
o
l
o
,
R
.
Ji
n
a
d
,
a
n
d
Q
.
Li
u
,
“
A
c
o
mp
a
r
i
s
o
n
st
u
d
y
t
o
d
e
t
e
c
t
m
a
l
w
a
r
e
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
3
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
Bi
g
D
a
t
a
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
B
D
A
I
5
9
1
6
5
.
2
0
2
3
.
1
0
2
5
6
9
5
7
.
[
1
8
]
I
.
B
.
A
.
O
u
a
h
a
b
,
L.
E
l
a
a
c
h
a
k
,
Y
.
A
.
A
l
l
u
h
a
i
,
a
n
d
M
.
B
o
u
h
o
r
m
a
,
“
A
n
e
w
a
p
p
r
o
a
c
h
t
o
d
e
t
e
c
t
n
e
x
t
g
e
n
e
r
a
t
i
o
n
o
f
mal
w
a
r
e
b
a
se
d
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
n
o
v
a
t
i
o
n
a
n
d
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
I
n
f
o
rm
a
t
i
c
s
,
C
o
m
p
u
t
i
n
g
,
a
n
d
T
e
c
h
n
o
l
o
g
i
e
s
,
3
I
C
T
2
0
2
1
,
2
0
2
1
,
p
p
.
2
3
0
–
2
3
5
,
d
o
i
:
1
0
.
1
1
0
9
/
3
I
C
T5
3
4
4
9
.
2
0
2
1
.
9
5
8
1
6
2
5
.
[
1
9
]
C
.
W
.
C
h
e
n
,
C
.
H
.
S
u
,
K
.
W
.
Le
e
,
a
n
d
P
.
H
.
B
a
i
r
,
“
M
a
l
w
a
r
e
f
a
mi
l
y
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
a
c
t
i
v
e
l
e
a
r
n
i
n
g
b
y
l
e
a
r
n
i
n
g
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
C
AC
T
,
2
0
2
0
,
v
o
l
.
2
0
2
0
,
p
p
.
5
9
0
–
5
9
5
,
d
o
i
:
1
0
.
2
3
9
1
9
/
I
C
A
C
T
4
8
6
3
6
.
2
0
2
0
.
9
0
6
1
4
1
9
.
[
2
0
]
I
.
B
.
A
.
O
u
a
h
a
b
,
M
.
B
o
u
h
o
r
m
a
,
A
.
A
.
B
o
u
d
h
i
r
,
a
n
d
L.
El
A
a
c
h
a
k
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
g
r
a
y
sc
a
l
e
ma
l
w
a
r
e
i
ma
g
e
s
u
si
n
g
t
h
e
k
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
a
l
g
o
r
i
t
h
m,”
i
n
I
n
n
o
v
a
t
i
o
n
s
i
n
S
m
a
r
t
C
i
t
i
e
s
A
p
p
l
i
c
a
t
i
o
n
s
Ed
i
t
i
o
n
3
,
2
0
2
0
,
p
p
.
1
0
3
8
–
1
0
5
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
3
7
6
2
9
-
1
_
7
5
.
[
2
1
]
Y
.
M
o
u
r
t
a
j
i
,
M
.
B
o
u
h
o
r
m
a
,
a
n
d
D
.
A
l
g
h
a
z
z
a
w
i
,
“
I
n
t
e
l
l
i
g
e
n
t
f
r
a
mew
o
r
k
f
o
r
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
A
C
M
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
S
e
ri
e
s
,
2
0
1
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
2
0
3
2
6
.
3
3
2
0
3
3
3
.
[
2
2
]
D
.
V
a
sa
n
,
M
.
A
l
a
z
a
b
,
S
.
W
a
ss
a
n
,
B
.
S
a
f
a
e
i
,
a
n
d
Q
.
Zh
e
n
g
,
“
I
mag
e
-
b
a
se
d
ma
l
w
a
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
e
n
sem
b
l
e
o
f
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
(
I
M
C
EC
)
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
9
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se.
2
0
2
0
.
1
0
1
7
4
8
.
[
2
3
]
S
.
S
h
u
k
l
a
,
G
.
K
o
l
h
e
,
S
.
M
.
P
D
,
a
n
d
S
.
R
a
f
a
t
i
r
a
d
,
“
R
N
N
-
b
a
se
d
c
l
a
ss
i
f
i
e
r
t
o
d
e
t
e
c
t
s
t
e
a
l
t
h
y
ma
l
w
a
r
e
u
s
i
n
g
l
o
c
a
l
i
z
e
d
f
e
a
t
u
r
e
s
a
n
d
c
o
m
p
l
e
x
sy
m
b
o
l
i
c
s
e
q
u
e
n
c
e
,
”
i
n
2
0
1
9
1
8
t
h
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
O
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
A
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
MLA)
,
2
0
1
9
,
p
p
.
4
0
6
–
4
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
LA
.
2
0
1
9
.
0
0
0
7
6
.
[
2
4
]
I
.
B
.
A
.
O
u
a
h
a
b
,
M
.
B
o
u
h
o
r
ma,
L.
E
l
A
a
c
h
a
k
,
a
n
d
A
.
A
.
B
o
u
d
h
i
r
,
“
P
r
o
p
o
sed
p
r
e
c
a
u
t
i
o
n
s
f
o
r
n
e
w
b
o
r
n
ma
l
w
a
r
e
f
a
m
i
l
y
i
n
s
p
i
r
e
d
f
r
o
m
t
h
e
C
O
V
I
D
1
9
e
p
i
d
e
mi
c
o
u
t
b
r
e
a
k
,
”
i
n
Em
e
rg
i
n
g
T
r
e
n
d
s
i
n
I
C
T
f
o
r
S
u
s
t
a
i
n
a
b
l
e
D
e
v
e
l
o
p
m
e
n
t
,
2
0
2
1
,
p
p
.
5
3
–
61
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
5
3
4
4
0
-
0
_
7
.
[
2
5
]
M
.
V
e
n
k
a
t
a
s
u
b
r
a
ma
n
i
a
n
,
A
.
H
.
L
a
s
h
k
a
r
i
,
a
n
d
S
.
H
a
k
a
k
,
“
I
o
T
m
a
l
w
a
r
e
a
n
a
l
y
si
s
u
s
i
n
g
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
:
a
c
o
m
p
r
e
h
e
n
si
v
e
su
r
v
e
y
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
5
0
0
4
–
5
0
1
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ES
S
.
2
0
2
3
.
3
2
3
5
3
8
9
.
[
2
6
]
A
.
H
a
l
b
o
u
n
i
,
T.
S
.
G
u
n
a
w
a
n
,
M
.
H
.
H
a
b
a
e
b
i
,
M
.
H
a
l
b
o
u
n
i
,
M
.
K
a
r
t
i
w
i
,
a
n
d
R
.
A
h
ma
d
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s f
o
r
c
y
b
e
r
se
c
u
r
i
t
y
:
a
r
e
v
i
e
w
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
9
5
7
2
–
1
9
5
8
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
5
1
2
4
8
.
[
2
7
]
X
.
J
i
n
,
X
.
X
i
n
g
,
H
.
E
l
a
h
i
,
G
.
W
a
n
g
,
a
n
d
H
.
Ji
a
n
g
,
“
A
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
u
s
i
n
g
ma
l
w
a
r
e
i
ma
g
e
s
a
n
d
a
u
t
o
e
n
c
o
d
e
r
s
,
”
i
n
2
0
2
0
I
EEE
1
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Mo
b
i
l
e
Ad
H
o
c
a
n
d
S
e
n
s
o
r
S
y
st
e
m
s
(
MA
S
S
)
,
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
M
A
S
S
5
0
6
1
3
.
2
0
2
0
.
0
0
0
0
9
.
[
2
8
]
K
.
S
e
t
h
i
,
R
.
K
u
m
a
r
,
L.
S
e
t
h
i
,
P
.
B
e
r
a
,
a
n
d
P
.
K
.
P
a
t
r
a
,
“
A
n
o
v
e
l
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
f
r
a
mew
o
r
k
,
”
i
n
2
0
1
9
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
y
b
e
r
S
e
c
u
r
i
t
y
a
n
d
Pr
o
t
e
c
t
i
o
n
o
f
D
i
g
i
t
a
l
S
e
r
v
i
c
e
s
(
C
y
b
e
r
S
e
c
u
r
i
t
y
)
,
2
0
1
9
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
y
b
e
r
S
e
c
P
O
D
S
.
2
0
1
9
.
8
8
8
5
1
9
6
.
[
2
9
]
A
.
A
.
D
a
r
e
m,
F
.
A
.
G
h
a
l
e
b
,
A
.
A
.
A
l
-
H
a
sh
m
i
,
J.
H
.
A
b
a
w
a
j
y
,
S
.
M
.
A
l
a
n
a
z
i
,
a
n
d
A
.
Y
.
A
l
-
R
e
z
a
mi
,
“
A
n
a
d
a
p
t
i
v
e
b
e
h
a
v
i
o
r
a
l
-
b
a
s
e
d
i
n
c
r
e
me
n
t
a
l
b
a
t
c
h
l
e
a
r
n
i
n
g
m
a
l
w
a
r
e
v
a
r
i
a
n
t
s
d
e
t
e
c
t
i
o
n
m
o
d
e
l
u
si
n
g
c
o
n
c
e
p
t
d
r
i
f
t
d
e
t
e
c
t
i
o
n
a
n
d
se
q
u
e
n
t
i
a
l
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
9
7
1
8
0
–
9
7
1
9
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
9
3
3
6
6
.
[
3
0
]
D
.
W
u
,
P
.
G
u
o
,
a
n
d
P
.
W
a
n
g
,
“
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
c
a
sca
d
i
n
g
X
G
b
o
o
s
t
a
n
d
c
o
st
s
e
n
si
t
i
v
e
,
”
2
0
2
0
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
N
e
t
w
o
rk
S
e
c
u
r
i
t
y
,
C
C
N
S
2
0
2
0
,
p
p
.
2
0
1
–
2
0
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
N
S
5
0
7
3
1
.
2
0
2
0
.
0
0
0
5
1
.
[
3
1
]
J.
M
c
G
i
f
f
,
W
.
G
.
H
a
t
c
h
e
r
,
J
.
N
g
u
y
e
n
,
W
.
Y
u
,
E.
B
l
a
sc
h
,
a
n
d
C
.
L
u
,
“
To
w
a
r
d
s
mu
l
t
i
mo
d
a
l
l
e
a
r
n
i
n
g
f
o
r
A
n
d
r
o
i
d
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
9
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
,
N
e
t
w
o
rki
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
N
C
)
,
2
0
1
9
,
p
p
.
4
3
2
–
4
3
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
N
C
.
2
0
1
9
.
8
6
8
5
5
0
2
.
[
3
2
]
N
.
A
.
A
n
u
a
r
,
M
.
Z.
M
a
s’
u
d
,
N
.
B
a
h
a
m
a
n
,
a
n
d
N
.
A
.
M
.
A
r
i
f
f
,
“
A
n
a
l
y
si
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
i
n
a
n
d
r
o
i
d
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
o
p
c
o
d
e
,
”
i
n
2
0
2
0
I
EEE
C
o
n
f
e
re
n
c
e
o
n
A
p
p
l
i
c
a
t
i
o
n
,
I
n
f
o
rm
a
t
i
o
n
a
n
d
N
e
t
w
o
r
k
S
e
c
u
r
i
t
y
(
AI
N
S
)
,
2
0
2
0
,
p
p
.
7
–
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
N
S
5
0
1
5
5
.
2
0
2
0
.
9
3
1
5
0
6
0
.
[
3
3
]
E.
R
o
d
r
i
g
u
e
z
,
B
.
O
t
e
r
o
,
N
.
G
u
t
i
e
r
r
e
z
,
a
n
d
R
.
C
a
n
a
l
,
“
A
s
u
r
v
e
y
o
f
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
c
y
b
e
r
se
c
u
r
i
t
y
i
n
m
o
b
i
l
e
n
e
t
w
o
r
k
s,”
I
EEE
C
o
m
m
u
n
i
c
a
t
i
o
n
s
S
u
rv
e
y
s
a
n
d
T
u
t
o
ri
a
l
s
,
v
o
l
.
2
3
,
n
o
.
3
,
p
p
.
1
9
2
0
–
1
9
5
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
M
S
T
.
2
0
2
1
.
3
0
8
6
2
9
6
.
[
3
4
]
J.
P
a
l
š
a
e
t
a
l
.
,
“
M
L
M
D
—
a
ma
l
w
a
r
e
-
d
e
t
e
c
t
i
n
g
a
n
t
i
v
i
r
u
s
t
o
o
l
b
a
s
e
d
o
n
t
h
e
X
G
B
o
o
s
t
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
3
6
6
7
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ci
n
g
fin
a
n
cia
l c
yb
ers
ec
u
r
ity
via
a
d
va
n
ce
d
ma
ch
i
n
e
le
a
r
n
in
g
:
… (
Gra
ce
Od
ette
B
o
u
s
s
i
)
1289
[
3
5
]
C
.
T.
T
h
a
n
h
,
“
A
st
u
d
y
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
c
y
b
e
r
se
c
u
r
i
t
y
,
”
i
n
2
0
2
1
1
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
A
C
O
M
P
2
0
2
1
,
2
0
2
1
,
p
p
.
5
4
–
6
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
O
M
P
5
3
7
4
6
.
2
0
2
1
.
0
0
0
1
4
.
[
3
6
]
H
.
A
l
a
mr
o
,
W
.
M
t
o
u
a
a
,
S
.
A
l
j
a
m
e
e
l
,
A
.
S
.
S
a
l
a
m
a
,
M
.
A
.
H
a
m
z
a
,
a
n
d
A
.
Y
.
O
t
h
ma
n
,
“
A
u
t
o
ma
t
e
d
a
n
d
r
o
i
d
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
o
p
t
i
ma
l
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
c
y
b
e
r
s
e
c
u
r
i
t
y
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
7
2
5
0
9
–
7
2
5
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
4
2
6
3
.
[
3
7
]
Y
.
W
e
i
a
n
d
Y
.
S
e
k
i
y
a
,
“
S
u
f
f
i
c
i
e
n
c
y
o
f
e
n
s
e
m
b
l
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
f
o
r
p
h
i
s
h
i
n
g
w
e
b
s
i
t
e
s
d
e
t
e
c
t
i
o
n
,
”
I
E
EE
A
c
c
e
s
s
,
v
o
l
.
1
0
,
p
p
.
1
2
4
1
0
3
–
1
2
4
1
1
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
2
4
7
8
1
.
[
3
8
]
S
.
S
h
a
r
m
a
,
N
.
G
u
p
t
a
,
a
n
d
B
.
B
u
n
d
e
l
a
,
“
A
G
W
O
-
X
G
B
o
o
st
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
f
o
r
d
e
t
e
c
t
i
n
g
ma
l
w
a
r
e
e
x
e
c
u
t
a
b
l
e
s,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
i
s
ru
p
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
D
T
)
,
2
0
2
3
,
p
p
.
2
4
7
–
2
5
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
T5
7
9
2
9
.
2
0
2
3
.
1
0
1
5
0
9
9
3
.
[
3
9
]
N
.
M
o
h
a
p
a
t
r
a
,
K
.
S
h
r
e
y
a
,
a
n
d
A
.
C
h
i
n
ma
y
,
“
O
p
t
i
m
i
z
a
t
i
o
n
o
f
t
h
e
r
a
n
d
o
m
f
o
r
e
st
a
l
g
o
r
i
t
h
m,
”
i
n
A
d
v
a
n
c
e
s
i
n
D
a
t
a
S
c
i
e
n
c
e
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
3
7
,
2
0
2
0
,
p
p
.
2
0
1
–
2
0
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
0
9
7
8
-
0
_
1
9
.
[
4
0
]
M
.
E.
N
a
r
a
y
a
n
a
n
,
“
M
a
l
w
a
r
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
X
GB
o
o
st
w
i
t
h
v
o
t
e
b
a
s
e
d
b
a
c
k
w
a
r
d
f
e
a
t
u
r
e
e
l
i
m
i
n
a
t
i
o
n
t
e
c
h
n
i
q
u
e
,
”
T
u
r
k
i
s
h
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
Ma
t
h
e
m
a
t
i
c
s
E
d
u
c
a
t
i
o
n
(
T
U
RC
O
MA
T
)
,
v
o
l
.
1
2
,
n
o
.
1
0
,
p
p
.
5
9
1
5
–
5
9
2
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
7
7
6
2
/
t
u
r
c
o
mat
.
v
1
2
i
1
0
.
5
4
1
2
.
[
4
1
]
S
.
G
u
a
n
a
n
d
W
.
L
i
,
“
En
sem
b
l
e
D
r
o
i
d
:
A
mal
w
a
r
e
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
A
n
d
r
o
i
d
s
y
st
e
m
b
a
s
e
d
o
n
e
n
s
e
mb
l
e
Le
a
r
n
i
n
g
,
”
i
n
2
0
2
2
I
EEE
MIT
U
n
d
e
r
g
ra
d
u
a
t
e
Re
s
e
a
rc
h
T
e
c
h
n
o
l
o
g
y
C
o
n
f
e
r
e
n
c
e
(
U
RT
C
)
,
2
0
2
2
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
U
R
T
C
5
6
8
3
2
.
2
0
2
2
.
1
0
0
0
2
2
1
3
.
[
4
2
]
N
.
P
a
c
h
h
a
l
a
,
S
.
Jo
t
h
i
l
a
k
sh
m
i
,
a
n
d
B
.
P
.
B
a
t
t
u
l
a
,
“
P
r
e
d
i
c
t
i
o
n
o
f
n
o
v
e
l
ma
l
w
a
r
e
u
s
i
n
g
h
y
b
r
i
d
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
l
o
n
g
sh
o
r
t
-
t
e
r
m
me
mo
r
y
a
p
p
r
o
a
c
h
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
4
5
0
8
-
4
5
1
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
4
.
p
p
4
5
0
8
-
4
5
1
7
.
[
4
3
]
R
.
K
.
D
u
b
e
y
,
N
.
D
a
n
d
o
t
i
y
a
,
A
.
S
h
a
r
ma,
S
.
M
i
sh
r
a
,
a
n
d
S
.
K
.
G
u
p
t
a
,
“
C
y
b
e
r
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
3
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
I
C
T
i
n
B
u
si
n
e
ss
I
n
d
u
s
t
r
y
&
G
o
v
e
rn
m
e
n
t
(
I
C
T
BI
G
)
,
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
TB
I
G
5
9
7
5
2
.
2
0
2
3
.
1
0
4
5
6
0
8
0
.
[
4
4
]
Z.
S
a
w
a
d
o
g
o
,
J
.
-
M
.
D
e
m
b
e
l
e
,
G
.
M
e
n
d
y
,
a
n
d
S
.
O
u
y
a
,
“
A
n
d
r
o
i
d
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
:
A
n
i
n
-
d
e
p
t
h
i
n
v
e
st
i
g
a
t
i
o
n
o
f
t
h
e
i
mp
a
c
t
o
f
t
h
e
u
se
o
f
i
m
b
a
l
a
n
c
e
d
a
t
a
s
e
t
s
o
n
t
h
e
e
f
f
i
c
i
e
n
c
y
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s,
”
i
n
2
0
2
3
2
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
A
C
T
)
,
2
0
2
3
,
p
p
.
1
4
6
0
–
1
4
6
7
,
d
o
i
:
1
0
.
2
3
9
1
9
/
I
C
A
C
T5
6
8
6
8
.
2
0
2
3
.
1
0
0
7
9
2
4
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
G
r
a
c
e
O
d
e
tte
Bo
u
ss
i
o
b
t
a
in
e
d
h
e
r
Ba
c
h
e
lo
r
o
f
C
o
m
p
u
t
e
r
Ap
p
li
c
a
ti
o
n
in
Ha
ry
a
n
a
,
In
d
ia,
in
2
0
1
6
.
S
h
e
t
h
e
n
p
u
rs
u
e
d
a
M
a
ste
r
o
f
S
c
ien
c
e
i
n
n
e
two
r
k
i
n
g
tec
h
n
o
lo
g
y
a
n
d
m
a
n
a
g
e
m
e
n
t
a
t
Am
it
y
Un
i
v
e
rsit
y
No
id
a
fr
o
m
2
0
1
6
to
2
0
1
8
,
wh
e
re
sh
e
re
c
e
iv
e
d
t
h
e
sil
v
e
r
m
e
d
a
l
fo
r
h
e
r
a
c
a
d
e
m
ic
a
c
h
iev
e
m
e
n
ts.
S
in
c
e
2
0
1
9
,
sh
e
h
a
s
b
e
e
n
p
u
rsu
i
n
g
h
e
r
P
h
.
D.
i
n
c
y
b
e
r
se
c
u
rit
y
a
t
Am
it
y
U
n
iv
e
rsit
y
No
i
d
a
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
ra
c
e
b
o
u
ss
i@
g
m
a
il
.
c
o
m
.
Dr
.
H
im
a
shu
G
u
p
ta
is
a
re
sp
e
c
ted
s
e
n
io
r
fa
c
u
lt
y
m
e
m
b
e
r
a
t
Am
it
y
Un
i
v
e
rsity
in
Uttar
P
ra
d
e
sh
,
In
d
ia.
He
c
o
m
p
le
ted
h
is
e
d
u
c
a
ti
o
n
a
t
Alig
a
r
h
M
u
slim
Un
iv
e
rsit
y
a
n
d
h
a
s
a
n
e
x
ten
siv
e
a
c
a
d
e
m
ic
a
n
d
p
ro
fe
ss
io
n
a
l
b
a
c
k
g
ro
u
n
d
in
in
f
o
rm
a
ti
o
n
te
c
h
n
o
l
o
g
y
.
He
h
a
s
p
u
b
li
s
h
e
d
n
u
m
e
ro
u
s
re
se
a
rc
h
p
a
p
e
rs
a
n
d
a
r
ti
c
les
in
th
e
fiel
d
,
wit
h
h
is
f
irst
p
a
ten
t
i
n
n
e
two
r
k
se
c
u
rit
y
b
e
in
g
p
u
b
li
sh
e
d
in
t
h
e
i
n
tern
a
t
io
n
a
l
jo
u
rn
a
l
o
f
p
a
ten
ts
b
y
th
e
G
o
v
e
rn
m
e
n
t
o
f
I
n
d
ia
in
De
c
e
m
b
e
r
2
0
1
0
.
A
d
d
i
ti
o
n
a
ll
y
,
h
e
is
a
m
e
m
b
e
r
o
f
v
a
rio
u
s
p
re
stig
io
u
s
i
n
tern
a
ti
o
n
a
l
tec
h
n
ica
l
a
n
d
re
se
a
rc
h
o
rg
a
n
iza
ti
o
n
s
a
n
d
h
a
s
d
e
li
v
e
re
d
o
n
li
n
e
lec
tu
re
s
to
stu
d
e
n
ts
fr
o
m
1
6
Afric
a
n
c
o
u
n
tr
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
g
u
p
ta@
a
m
it
y
.
e
d
u
.
S
y
e
d
Akh
te
r
H
o
ss
a
in
is
a
n
e
ste
e
m
e
d
c
o
m
p
u
ter
sc
ien
ti
st,
e
d
u
c
a
to
r,
c
o
lu
m
n
ist
,
a
n
d
tec
h
n
o
l
o
g
y
c
o
n
s
u
lt
a
n
t
fro
m
Ba
n
g
lad
e
sh
.
He
is
c
u
rre
n
tl
y
se
rv
in
g
a
s
a
p
r
o
fe
ss
o
r
a
n
d
th
e
h
e
a
d
o
f
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
th
e
Un
i
v
e
rsity
o
f
Li
b
e
ra
l
Arts Ba
n
g
lad
e
sh
.
He
c
a
n
b
e
c
o
n
ta
c
ted
a
t
e
m
a
il
:
a
k
tarh
o
ss
a
in
@
d
a
ff
o
d
il
v
a
rsity
.
e
d
u
.
b
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.