I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
,
p
p
.
1
0
8
5
~
1
0
9
4
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v
1
4
i
3
.
pp
1
0
8
5
-
1
094
1085
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
A
surv
ey
on ra
ns
o
mwa
re
dete
ction
using
AI mo
dels
G
o
t
et
i Ba
drina
t
h,
Arpit
a
G
up
t
a
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
K
L
D
e
e
m
e
d
t
o
b
e
U
n
i
v
e
r
si
t
y
,
K
o
n
e
r
u
L
a
k
s
h
m
a
i
a
h
Ed
u
c
a
t
i
o
n
F
o
u
n
d
a
t
i
o
n
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
7
,
2
0
2
4
R
ev
is
ed
J
u
n
1
7
,
2
0
2
5
Acc
ep
ted
J
u
l 1
,
2
0
2
5
Da
ta
c
e
n
ters
a
n
d
c
lo
u
d
e
n
v
iro
n
m
e
n
ts
a
re
c
o
m
p
ro
m
ise
d
a
s
th
e
y
a
r
e
a
t
g
re
a
t
risk
fro
m
ra
n
s
o
m
wa
re
a
tt
a
c
k
s,
wh
ich
a
tt
a
c
k
d
a
ta
i
n
teg
ri
ty
a
n
d
se
c
u
rit
y
.
Th
ro
u
g
h
t
h
is
su
rv
e
y
,
we
e
x
p
lo
re
h
o
w
AI,
e
sp
e
c
ially
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
(DL)
,
is
b
e
in
g
u
se
d
t
o
imp
r
o
v
e
ra
n
so
m
wa
re
d
e
tec
ti
o
n
c
a
p
a
b
il
it
ies
.
It
c
las
sifies
ra
n
so
m
wa
re
ty
p
e
s,
h
ig
h
li
g
h
ts
a
c
ti
v
e
g
ro
u
p
s
su
c
h
a
s
Ak
ira,
a
n
d
e
v
a
l
u
a
tes
n
e
w
DL
tec
h
n
i
q
u
e
s
e
ffe
c
ti
v
e
a
t
re
a
l
-
ti
m
e
d
a
ta
a
n
a
ly
sis
a
n
d
e
n
c
r
y
p
ti
o
n
h
a
n
d
li
n
g
.
F
e
a
tu
re
e
x
trac
ti
o
n
,
se
lec
ti
o
n
m
e
th
o
d
s,
a
n
d
e
ss
e
n
ti
a
l
p
a
ra
m
e
ters
fo
r
e
ffe
c
ti
v
e
d
e
tec
ti
o
n
,
i
n
c
lu
d
in
g
a
c
c
u
ra
c
y
,
p
re
c
isi
o
n
,
re
c
a
ll
,
F1
-
sc
o
re
a
n
d
r
e
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic
(
ROC
)
c
u
rv
e
,
a
re
i
d
e
n
ti
fied
.
Th
e
fi
n
d
i
n
g
s
p
o
in
t
to
th
e
sta
te
o
f
th
e
a
rt
a
n
d
th
e
sta
te
o
f
th
e
a
rt
in
AI
b
a
se
d
ra
n
so
m
wa
re
d
e
tec
ti
o
n
a
n
d
u
n
d
e
r
sc
o
re
th
e
n
e
e
d
f
o
r
ro
b
u
st
,
re
a
l
-
ti
m
e
m
o
d
e
ls
a
n
d
c
o
ll
a
b
o
ra
ti
v
e
re
se
a
rc
h
.
Th
e
sta
ti
stica
l
a
n
d
g
ra
p
h
ica
l
a
n
a
ly
se
s
h
e
lp
re
se
a
rc
h
e
rs
a
n
d
p
ra
c
ti
ti
o
n
e
rs
u
n
d
e
rsta
n
d
e
x
ist
in
g
tren
d
s
a
n
d
d
ir
e
c
ti
o
n
s
fo
r
fu
tu
re
d
e
v
e
lo
p
m
e
n
t
o
f
e
fficie
n
t
r
a
n
so
m
wa
re
d
e
tec
ti
o
n
sy
ste
m
s
to
stre
n
g
th
e
n
c
y
b
e
rse
c
u
rit
y
i
n
d
a
ta ce
n
ters
a
n
d
c
lo
u
d
in
fra
str
u
c
tu
re
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
C
lo
u
d
s
ec
u
r
ity
Dee
p
lear
n
in
g
E
n
cr
y
p
tio
n
Ma
ch
i
n
e
lear
n
in
g
R
an
s
o
m
war
e
R
ea
l
-
tim
e
d
etec
tio
n
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
:
Go
teti Bad
r
in
ath
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
KL
Dee
m
ed
to
b
e
Un
iv
er
s
ity
Ko
n
er
u
L
a
k
s
h
m
aiah
E
d
u
ca
tio
n
Fo
u
n
d
atio
n
Hy
d
er
ab
ad
,
T
elan
g
a
n
a,
I
n
d
ia
E
m
ail: b
ad
r
in
ath
.
g
o
teti@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
R
an
s
o
m
war
e
attac
k
s
h
av
e
b
ec
o
m
e
a
m
ajo
r
an
d
g
r
o
win
g
th
r
ea
t
in
th
e
wo
r
ld
o
f
cy
b
er
s
ec
u
r
ity
:
p
er
s
o
n
al
an
d
c
o
r
p
o
r
ate
d
ata
a
r
e
b
ein
g
tar
g
ete
d
m
o
r
e
a
n
d
m
o
r
e
f
r
eq
u
en
tly
an
d
m
o
r
e
a
n
d
m
o
r
e
s
o
p
h
is
ticated
.
T
h
e
attac
k
ed
s
o
f
twar
e
is
d
ep
l
o
y
ed
in
th
e
v
ictim
’
s
co
m
p
u
te
r
,
an
d
it
in
f
iltra
tes
th
e
s
y
s
tem
an
d
e
n
cr
y
p
ts
th
e
n
ec
ess
ar
y
d
ata
s
o
t
h
at
th
e
v
i
ct
im
ca
n
n
o
t
ac
ce
s
s
it
u
n
less
a
r
an
s
o
m
is
p
aid
[
1
]
.
Of
ten
,
th
e
d
ata
en
cr
y
p
ted
is
o
f
s
en
s
itiv
e
p
er
s
o
n
al
n
atu
r
e
,
f
il
es
im
p
o
r
tan
t
to
th
e
b
u
s
in
ess
.
I
t
is
o
f
ten
d
em
an
d
ed
in
cr
y
p
to
cu
r
r
en
cies
lik
e
B
itco
in
,
wh
ich
m
ak
es
it
h
ar
d
to
tr
ac
e
th
e
tr
an
s
ac
tio
n
s
[
2
]
.
R
an
s
o
m
w
ar
e
attac
k
s
h
av
e
s
e
r
io
u
s
an
d
m
u
ltip
le
co
n
s
eq
u
en
ce
s
.
T
h
ese
r
an
s
o
m
p
ay
m
en
ts
co
s
t
v
ictim
s
h
u
g
e
am
o
u
n
ts
o
f
m
o
n
e
y
,
as
d
o
th
e
co
s
ts
o
f
d
o
wn
tim
e
an
d
r
ec
o
v
er
y
ef
f
o
r
ts
.
Fu
r
th
er
m
o
r
e,
o
p
er
atio
n
al
d
is
r
u
p
tio
n
s
ca
n
b
e
v
er
y
b
r
o
a
d
,
esp
ec
ially
f
o
r
o
r
g
an
izatio
n
s
th
at
d
ep
e
n
d
o
n
co
n
tin
u
o
u
s
ac
ce
s
s
to
th
eir
d
ata.
T
h
at
ca
n
r
e
s
u
lt
in
b
u
s
in
ess
o
p
er
atio
n
s
b
e
in
g
s
talled
,
lo
s
s
o
f
p
r
o
d
u
ctiv
ity
an
d
m
is
s
ed
o
p
p
o
r
tu
n
ities
.
Ad
d
itio
n
ally
,
it
is
p
o
s
s
ib
le
th
at
a
r
an
s
o
m
war
e
attac
k
ca
n
d
o
a
lo
t
o
f
r
ep
u
tatio
n
al
d
am
ag
e
to
an
o
r
g
an
izatio
n
,
er
o
d
in
g
cu
s
to
m
e
r
tr
u
s
t
an
d
d
am
ag
in
g
a
n
o
r
g
an
izatio
n
’
s
b
r
an
d
im
ag
e
[
3
]
.
R
an
s
o
m
war
e
attac
k
s
ar
e
r
is
i
n
g
h
an
d
in
h
an
d
with
th
e
g
r
o
win
g
n
ee
d
f
o
r
d
ata
ce
n
ter
s
an
d
clo
u
d
s
er
v
ices.
Data
ce
n
ter
s
a
r
e
a
cr
itical
p
ar
t
o
f
th
e
in
f
r
astru
ctu
r
e
-
h
o
u
s
in
g
lar
g
e
am
o
u
n
ts
o
f
d
at
a
an
d
b
ein
g
c
r
itical
to
th
e
f
u
n
ctio
n
in
g
o
f
b
u
s
in
ess
es
an
d
g
o
v
er
n
m
e
n
ts
.
W
ith
m
o
d
er
n
I
T
s
tr
ateg
ies,
s
ca
lab
le
an
d
o
n
d
em
an
d
ac
ce
s
s
to
co
m
p
u
tin
g
r
eso
u
r
ce
s
is
an
in
teg
r
al
p
ar
t
o
f
clo
u
d
en
v
ir
o
n
m
en
ts
[
4
]
.
T
h
ese
en
v
ir
o
n
m
en
ts
s
to
r
e
h
ig
h
v
alu
e
d
ata
in
a
ce
n
tr
alize
d
m
an
n
e
r
a
n
d
ar
e
th
e
r
ef
o
r
e
attr
ac
tiv
e
tar
g
ets
f
o
r
cy
b
er
cr
im
in
als.
R
an
s
o
m
war
e
attac
k
s
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
0
8
5
-
1
0
9
4
1086
d
ata
ce
n
ter
s
an
d
clo
u
d
s
er
v
ice
s
ca
n
b
e
v
er
y
s
u
cc
ess
f
u
l
an
d
c
r
ip
p
le
an
en
tire
o
r
g
a
n
izatio
n
,
wh
ich
m
ak
es
th
ese
v
er
y
im
p
o
r
ta
n
t
s
er
v
ices
r
eq
u
ir
e
r
o
b
u
s
t
s
ec
u
r
ity
.
R
an
s
o
m
war
e
attac
k
s
h
a
v
e
p
r
o
g
r
ess
ed
to
b
e
o
n
e
o
f
t
h
e
m
o
s
t
co
m
m
o
n
an
d
d
an
g
e
r
o
u
s
ty
p
e
o
f
cy
b
e
r
cr
im
e
s
in
ce
it
b
e
g
an
.
Of
co
u
r
s
e,
th
e
s
im
p
lest
o
f
r
an
s
o
m
s
wer
e
th
e
AI
DS
T
r
o
jan
th
at
u
s
ed
s
y
m
m
etr
ic
en
cr
y
p
tio
n
t
o
lo
ck
f
iles
an
d
d
em
an
d
a
r
an
s
o
m
f
o
r
p
r
o
v
id
in
g
th
e
k
ey
to
u
n
lo
ck
b
u
t
it
s
s
im
p
lici
ty
m
ad
e
its
d
ec
r
y
p
tio
n
p
o
s
s
ib
le
o
n
ce
th
e
k
ey
was
f
o
u
n
d
.
R
an
s
o
m
war
e
h
as
b
ec
o
m
e
m
o
r
e
s
o
p
h
is
ticated
o
v
er
th
e
y
ea
r
s
,
u
s
in
g
in
cr
ea
s
in
g
ly
s
tr
o
n
g
er
m
eth
o
d
s
u
s
ed
to
en
cr
y
p
t
d
ata
th
at
r
is
k
s
b
ein
g
v
ir
tu
ally
u
n
r
u
le
d
b
y
th
o
s
e
w
ith
o
u
t
th
e
r
ig
h
t
k
e
y
.
W
ith
th
e
em
er
g
en
ce
o
f
cr
y
p
to
cu
r
r
e
n
cies
lik
e
B
itco
in
,
attac
k
er
s
h
av
e
ev
en
m
o
r
e
r
e
aso
n
to
attac
k
,
as
u
n
tr
ac
ea
b
l
e
p
ay
m
en
ts
ar
e
f
ac
ilit
ated
.
R
an
s
o
m
war
e
ca
n
b
e
ca
teg
o
r
ized
i
n
to
th
r
ee
m
ain
t
y
p
es:
lo
ck
er
r
an
s
o
m
war
e
,
s
ca
r
ewa
r
e
an
d
cr
y
p
to
r
an
s
o
m
war
e.
Scar
ewa
r
e
tak
es
ad
v
an
ta
g
e
o
f
p
s
y
c
h
o
lo
g
ical
m
an
ip
u
latio
n
,
p
r
esen
tin
g
f
ak
e
war
n
in
g
s
th
at
th
e
s
y
s
tem
is
in
f
ec
ted
,
o
r
th
at
s
o
m
e
o
th
er
p
r
o
b
lem
e
x
is
ts
,
an
d
th
en
f
o
r
cin
g
u
s
er
s
to
p
ay
f
o
r
u
n
n
e
c
ess
ar
y
s
o
f
twar
e,
u
s
u
ally
with
o
u
t e
n
cr
y
p
tin
g
f
iles
.
L
o
ck
er
r
an
s
o
m
war
e
lo
ck
s
v
ictim
o
u
t
o
f
th
eir
d
ev
ice,
r
en
d
e
r
i
n
g
f
iles
o
r
a
p
p
licatio
n
i
n
ac
ce
s
s
ib
le
u
n
til
a
r
an
s
o
m
is
p
aid
,
r
esu
ltin
g
in
m
ajo
r
d
is
r
u
p
tio
n
to
p
er
s
o
n
al
an
d
b
u
s
in
ess
o
p
er
atio
n
s
[
5
]
.
On
e
o
f
th
e
m
o
s
t d
am
ag
in
g
ty
p
es
o
f
cr
y
p
t
o
r
an
s
o
m
war
e
en
c
r
y
p
t
s
cr
itical
f
ile
s
o
r
an
en
tire
s
y
s
t
em
,
ty
p
ically
i
n
ex
ch
a
n
g
e
f
o
r
a
r
an
s
o
m
,
o
f
ten
in
a
cr
y
p
to
cu
r
r
en
c
y
s
u
ch
as
B
itco
in
.
Stro
n
g
en
cr
y
p
tio
n
m
eth
o
d
s
m
ak
e
it
v
er
y
co
s
tly
to
tu
r
n
o
f
f
,
with
th
e
co
s
t
ac
cr
u
in
g
to
th
e
ex
ten
t
th
at
b
u
s
in
ess
es n
ee
d
to
k
ee
p
d
ata
a
v
ailab
le
at
all
tim
es.
“
T
h
e
p
r
im
a
r
y
o
b
jectiv
e
o
f
th
is
p
ap
er
is
to
co
n
d
u
ct
a
co
m
p
r
e
h
en
s
iv
e
liter
atu
r
e
s
u
r
v
ey
o
n
r
a
n
s
o
m
war
e
attac
k
s
,
with
a
s
p
ec
if
ic
em
p
h
a
s
is
o
n
s
er
v
er
s
r
u
n
n
i
n
g
in
d
ata
ce
n
ter
s
an
d
clo
u
d
en
v
ir
o
n
m
en
ts
.
−
Pro
v
id
e
a
h
is
to
r
ical
o
v
er
v
iew
an
d
d
is
cu
s
s
th
e
in
cr
ea
s
in
g
co
m
p
lex
ity
o
f
r
an
s
o
m
wa
r
e
attac
k
s
,
f
o
cu
s
in
g
o
n
d
ata
ce
n
ter
s
an
d
cl
o
u
d
e
n
v
ir
o
n
m
en
ts
.
−
I
n
v
esti
g
ate
h
o
w
AI
,
s
p
ec
if
ically
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
i
n
g
(
DL
)
,
h
as
tr
an
s
f
o
r
m
ed
r
an
s
o
m
war
e
d
etec
tio
n
co
m
p
a
r
ed
to
tr
ad
itio
n
al
m
eth
o
d
s
.
−
C
o
m
p
ar
e
th
e
ef
f
ec
tiv
en
ess
o
f
ML
an
d
DL
tech
n
iq
u
es
in
r
an
s
o
m
war
e
d
etec
tio
n
,
h
ig
h
lig
h
ti
n
g
k
ey
m
o
d
els
an
d
th
eir
p
er
f
o
r
m
an
ce
.
−
E
x
p
lo
r
e
r
ec
en
t
ad
v
a
n
ce
m
en
ts
an
d
b
r
ea
k
th
r
o
u
g
h
s
in
DL
tech
n
iq
u
es
f
o
r
r
a
n
s
o
m
war
e
d
etec
tio
n
,
em
p
h
asizin
g
r
ea
l
-
tim
e
a
n
aly
s
is
an
d
en
cr
y
p
tio
n
a
d
d
r
ess
in
g
.
−
C
las
s
if
y
v
ar
io
u
s
r
an
s
o
m
wa
r
e
g
r
o
u
p
s
an
d
an
al
y
ze
h
ig
h
ly
ac
ti
v
e
v
ar
ian
ts
lik
e
Ak
ir
a.
T
h
e
liter
atu
r
e
r
ev
iew
aim
s
t
o
p
r
o
v
id
e
an
in
-
d
ep
t
h
an
aly
s
is
o
f
ex
is
tin
g
r
esear
ch
o
n
r
a
n
s
o
m
war
e
attac
k
s
,
f
o
cu
s
in
g
o
n
th
eir
ev
o
lu
tio
n
,
th
e
r
o
le
o
f
AI
in
d
ete
ctio
n
,
an
d
th
e
co
m
p
a
r
is
o
n
b
e
twee
n
ML
an
d
DL
ap
p
r
o
ac
h
es.
Sig
n
atu
r
e
b
ased
an
d
h
eu
r
is
tic
b
ased
ap
p
r
o
ac
h
es
ar
e
tr
ad
itio
n
al
m
eth
o
d
s
f
o
r
d
etec
tin
g
r
an
s
o
m
war
e
as
s
h
o
wn
in
T
ab
le
1
.
Sig
n
atu
r
e
b
ased
d
etec
tio
n
is
b
ased
o
n
m
ai
n
tain
in
g
a
d
atab
ase
o
f
k
n
o
wn
m
alwa
r
e
s
ig
n
atu
r
es
an
d
d
is
co
v
er
attac
k
s
b
y
m
atch
in
g
in
c
o
m
in
g
f
iles
an
d
a
ctiv
iti
es
with
th
ese
s
ig
n
atu
r
es.
B
u
t
it
’
s
n
o
t
ef
f
ec
tiv
e
at
n
ew
o
r
m
o
d
i
f
ied
v
ar
ian
ts
th
at
d
o
n
’
t
m
atch
k
n
o
w
n
s
ig
n
atu
r
es
.
Un
lik
e
th
is
h
eu
r
is
tic
b
ased
d
etec
tio
n
,
th
e
latter
d
etec
ts
m
alwa
r
e
b
y
a
p
p
ly
in
g
s
o
m
e
b
e
h
av
io
r
p
atter
n
a
n
aly
s
is
m
eth
o
d
s
,
s
u
ch
as
an
al
y
zin
g
s
u
s
p
icio
u
s
ac
tiv
ities
lik
e
r
u
s
h
en
cr
y
p
tio
n
o
f
m
u
lti
tu
d
es
o
f
f
iles
,
f
r
eq
u
en
tly
m
o
d
if
y
in
g
v
a
r
io
u
s
an
d
u
n
ex
p
ec
t
ed
f
ile
en
tr
y
in
th
e
n
etwo
r
k
c
o
n
n
ec
ti
o
n
.
T
h
e
h
e
u
r
is
tic
-
b
ased
ap
p
r
o
ac
h
es
ar
e
m
o
r
e
f
lex
i
b
le
an
d
m
o
r
e
ca
p
ab
le
o
f
d
etec
tin
g
u
n
k
n
o
wn
th
r
ea
ts
,
b
u
t g
en
e
r
ate
f
alse p
o
s
itiv
es si
n
ce
th
ese
ac
ti
v
ities
ar
e
er
r
o
n
e
o
u
s
ly
co
n
s
id
er
ed
as m
alicio
u
s
.
T
ab
le
1
.
T
r
a
d
itio
n
al
d
etec
tio
n
m
eth
o
d
s
R
e
f
e
r
e
n
c
e
(
Y
e
a
r
)
A
u
t
h
o
r
R
e
s
o
l
v
e
d
i
ssu
e
U
t
i
l
i
z
e
d
t
e
c
h
n
i
q
u
e
R
e
s
u
l
t
Li
mi
t
a
t
i
o
n
B
r
e
w
e
r
(
2
0
1
6
)
[
6
]
B
r
e
w
e
r
D
e
t
e
c
t
i
o
n
,
p
r
e
v
e
n
t
i
o
n
,
a
n
d
c
u
r
e
o
f
r
a
n
so
mw
a
r
e
S
i
g
n
a
t
u
r
e
-
b
a
s
e
d
a
n
d
h
e
u
r
i
s
t
i
c
-
b
a
s
e
d
met
h
o
d
s
O
u
t
l
i
n
e
d
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
st
r
a
t
e
g
i
e
s
D
e
p
e
n
d
e
n
t
o
n
s
i
g
n
a
t
u
r
e
d
a
t
a
b
a
se
a
n
d
p
o
t
e
n
t
i
a
l
f
o
r
f
a
l
s
e
p
o
s
i
t
i
v
e
s
C
e
l
d
r
á
n
e
t
a
l
.
(
2
0
2
2
)
[
7
]
C
e
l
d
r
á
n
e
t
a
l
.
B
e
h
a
v
i
o
r
a
l
-
b
a
s
e
d
mal
w
a
r
e
d
e
t
e
c
t
i
o
n
B
e
h
a
v
i
o
r
a
l
a
n
a
l
y
si
s
I
n
t
e
l
l
i
g
e
n
t
d
e
t
e
c
t
i
o
n
o
f
mal
w
a
r
e
P
o
t
e
n
t
i
a
l
f
o
r
f
a
l
se
p
o
s
i
t
i
v
e
s
K
o
k
e
t
a
l
.
(
2
0
1
9
)
[
8
]
K
o
k
e
t
a
l
.
D
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
o
f
r
a
n
s
o
mw
a
r
e
S
i
g
n
a
t
u
r
e
-
b
a
s
e
d
met
h
o
d
s
Ef
f
e
c
t
i
v
e
a
g
a
i
n
st
k
n
o
w
n
t
h
r
e
a
t
s
I
n
e
f
f
e
c
t
i
v
e
a
g
a
i
n
s
t
n
e
w
o
r
m
o
d
i
f
i
e
d
v
a
r
i
a
n
t
s
ML
alg
o
r
ith
m
s
an
aly
ze
d
ata
t
o
id
en
tify
p
atter
n
s
in
d
icativ
e
o
f
r
an
s
o
m
war
e
.
C
o
m
m
o
n
ML
tech
n
iq
u
es
in
clu
d
e
d
ec
is
io
n
tr
ee
s
,
r
an
d
o
m
f
o
r
ests
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVMs)
as
s
h
o
wn
in
T
ab
le
2
.
T
h
ese
tech
n
iq
u
es c
lass
if
y
d
ata
an
d
d
etec
t a
n
o
m
alies th
at
m
ay
in
d
i
ca
te
r
an
s
o
m
war
e
ac
tiv
ity
.
”
DL
tech
n
iq
u
es
h
a
v
e
s
h
o
wn
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
d
etec
t
in
g
r
an
s
o
m
war
e
co
m
p
ar
ed
t
o
tr
ad
itio
n
al
ML
m
eth
o
d
s
d
u
e
to
th
eir
ab
i
lity
to
h
an
d
le
co
m
p
lex
d
ata
p
atter
n
s
an
d
lar
g
e
v
o
l
u
m
es
o
f
d
ata
as
s
h
o
wn
in
T
ab
le
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
s
u
r
ve
y
o
n
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
u
s
in
g
A
I
mo
d
els
(
Go
teti
B
a
d
r
in
a
th
)
1087
T
ab
le
2
.
Ma
ch
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
es
R
e
f
e
r
e
n
c
e
(
Y
e
a
r
)
A
u
t
h
o
r
R
e
s
o
l
v
e
d
i
ssu
e
U
t
i
l
i
z
e
d
t
e
c
h
n
i
q
u
e
R
e
s
u
l
t
Li
mi
t
a
t
i
o
n
A
l
r
a
i
z
z
a
a
n
d
A
l
g
a
r
n
i
(
2
0
2
3
)
[
9
]
A
l
r
a
i
z
z
a
a
n
d
A
l
g
a
r
n
i
D
e
t
e
c
t
i
o
n
o
f
r
a
n
s
o
mw
a
r
e
u
s
i
n
g
ML
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
I
mp
r
o
v
e
d
d
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
Li
mi
t
e
d
t
o
k
n
o
w
n
r
a
n
s
o
mw
a
r
e
p
a
t
t
e
r
n
s
O
’
K
a
n
e
e
t
a
l
.
(
2
0
1
8
)
[
1
0
]
O
’
K
a
n
e
e
t
a
l
.
Ev
o
l
u
t
i
o
n
o
f
r
a
n
s
o
mw
a
r
e
H
i
st
o
r
i
c
a
l
a
n
a
l
y
si
s
P
r
o
v
i
d
e
d
a
c
o
m
p
r
e
h
e
n
si
v
e
o
v
e
r
v
i
e
w
o
f
r
a
n
so
mw
a
r
e
e
v
o
l
u
t
i
o
n
H
i
st
o
r
i
c
a
l
d
a
t
a
ma
y
n
o
t
c
o
v
e
r
a
l
l
v
a
r
i
a
n
t
s
S
h
a
u
k
a
t
a
n
d
R
i
b
e
i
r
o
(
2
0
1
8
)
[
1
1
]
S
h
a
u
k
a
t
a
n
d
R
i
b
e
i
r
o
D
e
f
e
n
s
e
a
g
a
i
n
st
c
r
y
p
t
o
g
r
a
p
h
i
c
r
a
n
s
o
mw
a
r
e
La
y
e
r
e
d
d
e
f
e
n
se
sy
st
e
m
D
e
v
e
l
o
p
e
d
a
d
e
f
e
n
s
e
sy
st
e
m
a
g
a
i
n
st
r
a
n
s
o
mw
a
r
e
C
o
m
p
l
e
x
i
t
y
i
n
i
mp
l
e
m
e
n
t
a
t
i
o
n
Ta
l
a
b
a
n
i
a
n
d
A
b
d
u
l
h
a
d
i
(
2
0
2
2
)
[
1
2
]
Ta
l
a
b
a
n
i
a
n
d
A
b
d
u
l
h
a
d
i
B
i
t
c
o
i
n
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
R
u
l
e
-
b
a
se
d
a
l
g
o
r
i
t
h
ms
Ef
f
e
c
t
i
v
e
i
n
d
e
t
e
c
t
i
n
g
sp
e
c
i
f
i
c
r
a
n
s
o
mw
a
r
e
t
y
p
e
s
Li
mi
t
e
d
s
c
a
l
a
b
i
l
i
t
y
a
n
d
f
l
e
x
i
b
i
l
i
t
y
T
ab
le
3
.
Dee
p
lea
r
n
in
g
ap
p
r
o
a
ch
es
R
e
f
e
r
e
n
c
e
(
Y
e
a
r
)
A
u
t
h
o
r
R
e
s
o
l
v
e
d
i
ssu
e
U
t
i
l
i
z
e
d
t
e
c
h
n
i
q
u
e
R
e
s
u
l
t
Li
mi
t
a
t
i
o
n
B
e
l
l
o
e
t
a
l
.
(
2
0
2
1
)
[
1
3
]
B
e
l
l
o
e
t
a
l
.
D
e
t
e
c
t
i
n
g
r
a
n
s
o
mw
a
r
e
a
t
t
a
c
k
s
u
si
n
g
D
L
D
e
e
p
l
e
a
r
n
i
n
g
H
i
g
h
l
i
g
h
t
e
d
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
D
L
i
n
d
e
t
e
c
t
i
n
g
r
a
n
s
o
mw
a
r
e
H
i
g
h
c
o
m
p
u
t
a
t
i
o
n
a
l
r
e
so
u
r
c
e
s
r
e
q
u
i
r
e
d
A
l
mas
h
h
a
d
a
n
i
e
t
a
l
.
(
2
0
1
9
)
[
1
4
]
A
l
mas
h
h
a
d
a
ni
e
t
a
l
.
C
r
y
p
t
o
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
s
y
st
e
m
M
u
l
t
i
-
c
l
a
ssi
f
i
e
r
n
e
t
w
o
r
k
-
b
a
s
e
d
s
y
st
e
m
D
e
mo
n
st
r
a
t
e
d
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
a
mu
l
t
i
-
c
l
a
ss
i
f
i
e
r
sy
st
e
m
S
c
a
l
a
b
i
l
i
t
y
i
ssu
e
s
H
w
a
n
g
e
t
a
l
.
(
2
0
2
0
)
[
1
5
]
H
w
a
n
g
e
t
a
l
.
Tw
o
-
st
a
g
e
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
”
D
y
n
a
mi
c
a
n
a
l
y
si
s
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
”
I
mp
r
o
v
e
d
d
e
t
e
c
t
i
o
n
r
a
t
e
s
a
n
d
r
e
d
u
c
e
d
f
a
l
se
p
o
si
t
i
v
e
s
H
i
g
h
c
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
t
i
m
e
r
e
s
o
u
r
c
e
s
r
e
q
u
i
r
e
d
M
a
k
i
n
d
e
e
t
a
l
.
(
2
0
1
9
)
[
1
6
]
M
a
k
i
n
d
e
e
t
a
l
.
D
i
st
r
i
b
u
t
e
d
n
e
t
w
o
r
k
b
e
h
a
v
i
o
r
p
r
e
d
i
c
t
i
o
n
”
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
a
g
e
n
t
-
b
a
se
d
mi
c
r
o
si
m
u
l
a
t
i
o
n
”
A
c
c
u
r
a
t
e
p
r
e
d
i
c
t
i
o
n
o
f
n
e
t
w
o
r
k
b
e
h
a
v
i
o
r
C
o
m
p
l
e
x
i
mp
l
e
m
e
n
t
a
t
i
o
n
a
n
d
mai
n
t
e
n
a
n
c
e
P
a
q
u
e
t
-
C
l
o
u
st
o
n
e
t
a
l
.
(
2
0
1
9
)
[
1
7
]
P
a
q
u
e
t
-
C
l
o
u
s
t
o
n
e
t
a
l
.
R
a
n
so
mw
a
r
e
p
a
y
me
n
t
s
i
n
t
h
e
b
i
t
c
o
i
n
e
c
o
sy
s
t
e
m
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
b
l
o
c
k
c
h
a
i
n
a
n
a
l
y
si
s
I
n
si
g
h
t
i
n
t
o
r
a
n
s
o
mw
a
r
e
p
a
y
me
n
t
mec
h
a
n
i
sms
R
e
q
u
i
r
e
s
e
x
t
e
n
si
v
e
d
a
t
a
a
n
a
l
y
si
s
a
n
d
c
o
m
p
u
t
a
t
i
o
n
a
l
p
o
w
e
r
2.
RE
S
E
ARCH
M
E
T
H
O
D
“
Fo
r
th
is
s
tu
d
y
,
a
m
eth
o
d
o
lo
g
y
was
d
esig
n
ed
to
s
y
s
tem
atica
lly
an
d
r
ep
licab
ly
e
v
alu
ate
ML
an
d
DL
tech
n
iq
u
es
f
o
r
r
a
n
s
o
m
war
e
d
etec
tio
n
in
d
ata
ce
n
ter
s
an
d
clo
u
d
en
v
ir
o
n
m
e
n
ts
.
‘
R
an
s
o
m
war
e
d
etec
tio
n
’
,
‘
m
ac
h
in
e
lear
n
in
g
,
’
‘
d
ee
p
lea
r
n
in
g
,
’
an
d
‘
clo
u
d
s
ec
u
r
ity
’
wer
e
th
e
a
r
ea
s
o
f
liter
atu
r
e
r
ev
iewe
d
ex
ten
s
iv
ely
[
1
8
]
.
On
ly
th
e
last
d
ec
a
d
e
’
s
r
e
lev
an
t
s
tu
d
ies
o
n
AI
b
ased
d
etec
tio
n
tech
n
i
q
u
es
wer
e
in
clu
d
ed
,
ex
cl
u
d
in
g
n
o
n
-
em
p
ir
ical
o
r
o
u
td
ated
ap
p
r
o
ac
h
es.
T
r
u
s
ted
cy
b
e
r
s
ec
u
r
ity
r
ep
o
s
ito
r
ies
wer
e
tap
p
ed
to
c
o
llect
p
u
b
lic
d
atasets
o
f
r
an
s
o
m
war
e
ac
tiv
ities
in
clu
d
i
n
g
s
y
s
tem
lo
g
s
,
n
etwo
r
k
t
r
af
f
ic
an
d
f
ile
ac
ce
s
s
p
atter
n
s
.
No
r
m
aliza
tio
n
an
d
d
im
en
s
io
n
ality
r
ed
u
ctio
n
we
r
e
ac
h
iev
ed
t
h
r
o
u
g
h
d
ata
p
r
e
p
r
o
ce
s
s
in
g
u
s
in
g
p
r
in
cip
al
c
o
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
.
C
o
r
r
elatio
n
an
aly
s
is
w
as
u
s
ed
to
ex
tr
ac
t
k
ey
f
ea
tu
r
es
s
u
ch
as
en
cr
y
p
tio
n
ac
tiv
ity
p
a
tter
n
s
an
d
n
etwo
r
k
an
o
m
a
lies
,
an
d
th
ese
wer
e
v
al
id
ated
.
Fo
r
ML
alg
o
r
ith
m
s
,
s
u
ch
as
d
ec
is
io
n
tr
ee
s
,
r
an
d
o
m
f
o
r
ests
,
an
d
SVMs,
we
im
p
lem
en
ted
m
o
d
els
with
Scik
it
-
lear
n
,
an
d
f
o
r
DL
m
o
d
els
with
co
n
v
o
lu
tio
n
al
n
e
u
r
a
l
n
etwo
r
k
s
(
C
NNs)
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs)
.
Mo
d
el
ev
alu
atio
n
e
m
p
lo
y
ed
p
er
f
o
r
m
a
n
ce
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
AUC
-
r
ec
eiv
er
o
p
e
r
atin
g
c
h
ar
ac
ter
is
tic
(R
OC
)
.
”
T
h
e
Fig
u
r
e
1
illu
s
tr
ates
th
r
ee
m
ain
ty
p
es
o
f
r
an
s
o
m
war
es:
s
ca
r
ewa
r
e,
lo
ck
er
r
an
s
o
m
war
e
an
d
cr
y
p
to
r
an
s
o
m
w
ar
e.
Scar
ewa
r
e
is
m
alwa
r
e
th
at
p
r
ete
n
d
s
a
v
ictim
’
s
s
y
s
tem
is
in
f
ec
ted
with
v
i
r
u
s
es
o
r
s
o
m
eth
i
n
g
s
im
ilar
an
d
ask
s
th
em
to
p
ay
f
o
r
f
a
k
e
s
o
lu
tio
n
s
,
u
s
in
g
p
s
y
ch
o
lo
g
ical
m
an
ip
u
latio
n
r
at
h
er
th
an
e
n
cr
y
p
tin
g
f
iles
.
L
o
ck
er
r
an
s
o
m
war
e
is
o
l
ates
th
e
u
s
er
s
f
r
o
m
th
eir
d
ev
i
ce
s
;
b
lo
ck
in
g
ac
ce
s
s
to
f
iles
an
d
p
r
o
g
r
a
m
s
an
d
h
o
ld
s
th
e
u
s
er
’
s
h
o
s
tag
e
b
y
d
em
an
d
in
g
a
r
a
n
s
o
m
to
r
etu
r
n
f
u
n
ctio
n
ality
,
th
u
s
s
ev
er
ely
d
is
r
u
p
tin
g
eq
u
i
p
m
en
t
.
T
h
e
m
o
s
t
d
am
ag
i
n
g
k
i
n
d
o
f
cr
y
p
to
r
an
s
o
m
war
e
e
n
cr
y
p
t
s
cr
itical
f
iles
o
r
en
tire
s
y
s
tem
s
,
m
ak
in
g
th
e
m
in
ac
ce
s
s
ib
le,
an
d
h
o
l
d
in
g
v
icti
m
’
s
h
o
s
tag
e
u
n
til
th
ey
p
ay
a
r
an
s
o
m
,
u
s
u
ally
in
cr
y
p
to
c
u
r
r
e
n
cy
,
to
g
ain
ac
ce
s
s
to
th
e
d
ec
r
y
p
tio
n
k
ey
.
Fro
m
f
ea
r
to
r
estricte
d
ac
ce
s
s
,
en
cr
y
p
tio
n
,
th
er
e
ar
e
m
a
n
y
tactics
ea
ch
ty
p
e
u
s
es
to
co
er
ce
v
ictim
s
.
R
an
s
o
m
war
e
g
r
o
u
p
s
class
if
ic
atio
n
is
b
ased
o
n
an
aly
zi
n
g
t
h
eir
tactics,
tech
n
iq
u
es,
an
d
p
r
o
ce
d
u
r
es
(
T
T
Ps
)
to
d
eter
m
in
e
t
h
eir
b
e
h
av
io
r
a
n
d
d
ev
elo
p
ap
p
r
o
p
r
ia
te
co
u
n
ter
m
ea
s
u
r
es.
T
h
is
s
ec
tio
n
g
o
es
in
t
o
d
ep
t
h
with
s
o
m
e
o
f
th
e
m
o
s
t
ac
tiv
e
r
an
s
o
m
war
e
g
r
o
u
p
s
an
d
h
o
w
DL
m
o
d
els
ca
n
b
e
u
s
ed
to
d
o
b
eh
av
io
r
al
an
a
ly
s
is
f
o
r
ea
r
ly
d
etec
tio
n
a
n
d
p
r
ev
en
t
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
0
8
5
-
1
0
9
4
1088
Fig
u
r
e
1
.
T
y
p
es o
f
r
an
s
o
m
war
es
2
.
1
.
H
i
g
hly
a
ct
iv
e
ra
ns
o
m
w
a
re
g
ro
up
s
2
.
1
.
1
.
Ak
ira
Ak
ir
a
r
an
s
o
m
war
e
is
a
k
n
o
wn
ag
g
r
ess
iv
e
r
an
s
o
m
wa
r
e
th
at
attac
k
s
b
o
th
in
d
iv
id
u
als
an
d
o
r
g
an
izatio
n
s
.
Mo
s
t
co
m
m
o
n
l
y
it
u
s
es
p
h
is
h
in
g
em
ails
an
d
ex
p
lo
it
k
its
to
g
ai
n
an
in
itial
ac
ce
s
s
to
a
s
y
s
tem
.
Stro
n
g
e
n
cr
y
p
tio
n
alg
o
r
ith
m
s
ar
e
u
s
ed
b
y
Ak
ir
a
to
lo
ck
f
ile
s
an
d
th
e
f
ee
s
to
o
b
tain
th
e
d
ec
r
y
p
tio
n
k
ey
f
r
o
m
f
iles
is
q
u
ite
h
ef
ty
.
I
t a
ls
o
ev
ad
es tr
ad
itio
n
al
an
tiv
ir
u
s
an
d
in
tr
u
s
io
n
d
et
ec
tio
n
s
y
s
tem
s
[
1
9
]
.
I
f
th
e
r
an
s
o
m
is
n
’
t
p
aid
,
h
o
wev
e
r
,
th
e
attac
k
er
s
will
g
en
er
ally
p
u
b
lis
h
th
e
s
to
len
d
ata.
T
h
e
q
u
ic
k
p
r
o
p
ag
ati
o
n
o
f
Ak
ir
a
ac
r
o
s
s
n
etwo
r
k
s
m
ak
es it c
r
itical
th
at
d
etec
tio
n
an
d
r
esp
o
n
s
e
ar
e
b
o
th
tim
ely
.
2
.
1
.
2
.
Ry
uk
All
tar
g
ets
ar
e
lar
g
e
o
r
g
an
iza
tio
n
s
,
i.e
.
,
h
o
s
p
itals
,
g
o
v
er
n
m
en
t
ag
en
cies,
a
n
d
b
u
s
in
ess
es.
Ph
is
h
in
g
em
ails
o
r
ex
p
lo
its
o
f
r
em
o
te
d
esk
to
p
p
r
o
to
co
ls
(
R
DP)
ar
e
th
e
m
o
s
t
co
m
m
o
n
way
s
it
is
d
el
iv
er
ed
.
R
y
u
k
is
a
m
ix
tu
r
e
o
f
e
n
cr
y
p
tio
n
a
n
d
le
ak
o
f
d
ata.
I
t
id
e
n
tifie
s
an
d
t
er
m
in
ates
p
r
o
c
ess
es
th
at
m
ig
h
t
in
ter
f
er
e
with
th
e
en
cr
y
p
tio
n
p
r
o
ce
s
s
[
2
0
]
,
an
d
en
cr
y
p
ts
f
iles
b
ef
o
r
e.
I
n
f
ac
t,
R
y
u
k
u
s
es
d
if
f
er
en
t
p
er
s
is
ten
ce
m
ec
h
a
n
is
m
s
in
o
r
d
er
to
co
n
tin
u
e
to
h
a
v
e
ac
ce
s
s
to
th
ese
co
m
p
r
o
m
is
ed
s
y
s
te
m
s
.
R
y
u
k
en
cr
y
p
ts
af
ter
wh
ich
it d
em
an
d
s
a
lar
g
e
r
an
s
o
m
u
s
u
ally
in
B
itco
in
,
a
n
d
th
r
ea
ten
s
to
d
estro
y
th
e
d
ec
r
y
p
tio
n
k
ey
if
th
e
r
a
n
s
o
m
is
n
’
t
p
aid
with
in
a
s
p
ec
if
ic
win
d
o
w.
Ad
d
itio
n
all
y
,
th
e
r
an
s
o
m
war
e
also
wo
r
k
s
ar
o
u
n
d
s
y
s
tem
r
esto
r
e
p
o
in
ts
s
o
th
er
e
’
s
n
o
r
ec
o
v
er
y
with
o
u
t th
e
d
ec
r
y
p
tio
n
k
ey
.
2
.
1
.
3
.
M
a
ze
Ma
ze
r
an
s
o
m
war
e
is
a
d
o
u
b
le
ex
to
r
tio
n
r
an
s
o
m
war
e,
m
ea
n
in
g
it e
n
cr
y
p
ts
th
e
f
iles
an
d
s
teal
s
th
e
d
ata
an
d
th
r
ea
ten
s
to
p
u
b
lis
h
it if
th
e
r
an
s
o
m
is
n
o
t p
ai
d
.
Ma
ze
ai
m
s
at
m
an
y
in
d
u
s
tr
ies s
u
ch
as f
in
an
ce
,
h
ea
lth
ca
r
e,
an
d
m
an
u
f
ac
tu
r
in
g
.
E
x
p
lo
it
k
its
,
p
h
is
h
in
g
e
m
ails
an
d
v
u
ln
er
ab
le
r
em
o
te
d
esk
to
p
co
n
n
e
ctio
n
s
ar
e
u
s
ed
b
y
Ma
ze
to
g
ain
ac
ce
s
s
to
s
y
s
tem
s
[
2
1
]
.
I
t
u
s
es
a
lo
t
o
f
e
n
cr
y
p
tio
n
a
n
d
s
p
r
ea
d
s
later
ally
th
r
o
u
g
h
n
etwo
r
k
s
an
d
will
in
f
ec
t
as
m
an
y
s
y
s
tem
s
a
s
p
o
s
s
ib
le.
I
f
th
ey
f
in
d
y
o
u
d
o
n
’
t
co
m
p
ly
,
th
ey
th
en
r
elea
s
e
s
to
len
d
ata
to
th
e
p
u
b
lic.
T
h
e
ex
f
iltra
ted
d
ata
o
f
ten
ap
p
ea
r
s
as
s
am
p
les
o
n
t
h
e
leak
s
ite
o
f
m
az
e
o
p
er
ato
r
s
to
p
r
ess
u
r
e
v
ictim
s
to
p
ay
th
e
r
a
n
s
o
m
.
2
.
2
.
Dee
p
lea
rning
f
o
r
beha
v
io
ra
l a
na
ly
s
is
I
n
r
ec
en
t
y
ea
r
s
,
DL
m
o
d
els
h
av
e
b
ee
n
u
s
ed
to
class
if
y
r
an
s
o
m
wa
r
e
g
r
o
u
p
s
b
y
th
eir
b
eh
av
io
r
al
p
atter
n
s
[
2
2
]
.
T
h
e
m
o
d
els
ca
n
p
r
o
ce
s
s
lar
g
e
v
o
lu
m
e
o
f
d
ata
to
lo
o
k
f
o
r
less
o
b
v
io
u
s
p
atte
r
n
s
an
d
an
at
o
m
ies
th
at
s
h
o
w
th
e
s
ig
n
als o
f
a
r
an
s
o
m
war
e
attac
k
.
T
h
e
u
s
e
o
f
DL
in
b
eh
a
v
io
r
al
an
aly
s
is
o
f
f
e
r
s
s
ev
er
al
ad
v
a
n
tag
es:
1
.
E
ar
ly
d
etec
tio
n
Usi
n
g
DL
,
d
e
v
ian
t
p
atter
n
s
in
n
o
r
m
al
s
y
s
tem
b
eh
a
v
io
r
,
e.
g
.
,
th
e
f
ile
ac
ce
s
s
p
atter
n
s
,
th
e
en
cr
y
p
tio
n
p
ac
e,
th
e
n
etwo
r
k
tr
a
f
f
ic,
ca
n
b
e
d
etec
ted
.
T
h
e
y
ca
n
b
e
ea
r
ly
in
d
icato
r
s
o
f
a
r
a
n
s
o
m
war
e
attac
k
[
2
3
]
.
T
h
e
co
n
tin
u
o
u
s
an
aly
s
is
o
f
s
y
s
tem
b
eh
av
io
r
in
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
s
y
s
tem
s
p
r
o
v
id
es
th
e
ca
p
ab
ilit
y
to
d
etec
t
an
d
m
itig
ate
r
an
s
o
m
war
e
ac
ti
v
ities
p
r
o
m
p
tly
.
2
.
R
an
s
o
m
war
e
g
r
o
u
p
s
cla
s
s
if
icatio
n
R
an
s
o
m
war
e
ca
n
b
e
class
if
ied
u
s
in
g
th
e
s
p
ec
if
ic
b
eh
av
io
r
s
o
f
d
if
f
er
en
t r
a
n
s
o
m
war
e
g
r
o
u
p
s
u
s
in
g
DL
m
o
d
els.
Fo
r
in
s
tan
ce
,
t
h
e
m
o
d
el
ca
n
a
u
to
m
atica
lly
ex
tr
a
ct
r
elev
an
t
f
ea
tu
r
es
f
r
o
m
r
a
w
d
ata,
s
u
ch
as
th
e
f
r
eq
u
e
n
cy
o
f
f
ile
m
o
d
if
icatio
n
s
,
n
etwo
r
k
co
m
m
u
n
icatio
n
p
at
ter
n
s
,
an
d
p
r
o
ce
s
s
ex
ec
u
tio
n
b
eh
av
io
r
s
,
an
d
th
e
n
id
en
tify
th
e
u
n
iq
u
e
T
T
Ps
o
f
A
k
ir
a,
R
y
u
k
,
an
d
Ma
ze
,
wh
ich
d
is
tin
g
u
is
h
es
th
em
f
r
o
m
o
th
er
k
in
d
s
o
f
m
alwa
r
es.
T
h
ey
ar
e
im
p
o
r
tan
t
f
o
r
class
if
icatio
n
,
esp
ec
ially
ac
cu
r
ately
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
s
u
r
ve
y
o
n
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
u
s
in
g
A
I
mo
d
els
(
Go
teti
B
a
d
r
in
a
th
)
1089
3
.
I
m
p
r
o
v
e
d
a
cc
u
r
ac
y
W
ith
th
e
lar
g
e
am
o
u
n
ts
o
f
d
ata,
DL
m
o
d
els
g
et
b
etter
an
d
b
etter
at
lear
n
in
g
.
T
h
ey
ca
n
lea
r
n
n
ew
an
d
ev
o
lv
in
g
r
an
s
o
m
war
e
th
r
ea
ts
co
n
tin
u
o
u
s
ly
[
2
4
]
.
T
h
e
co
n
tex
t
o
f
d
etec
ted
an
o
m
alies
ca
n
b
e
u
n
d
e
r
s
to
o
d
b
y
DL
m
o
d
els
s
o
as
to
r
ed
u
ce
th
e
n
u
m
b
er
o
f
f
alse
p
o
s
itiv
es,
an
d
to
en
s
u
r
e
th
at
leg
itima
t
e
ac
tiv
ities
ar
e
n
o
t
m
is
class
if
ied
as m
alicio
u
s
.
4
.
I
m
p
r
o
v
e
d
r
esp
o
n
s
e
ca
p
a
b
ili
ties
DL
m
o
d
el
ca
n
o
n
ce
awa
r
e
o
f
a
r
an
s
o
m
war
e
attac
k
,
it
will
th
en
au
to
m
atica
lly
tr
ig
g
er
th
e
r
esp
o
n
s
e
m
ec
h
an
is
m
s
:
is
o
latin
g
af
f
ec
ted
s
y
s
tem
s
,
ter
m
in
atin
g
m
alici
o
u
s
p
r
o
ce
s
s
es,
an
d
n
o
tif
y
in
g
s
ec
u
r
ity
p
er
s
o
n
n
el.
I
t
h
elp
s
in
th
e
r
an
s
o
m
war
e
g
r
o
u
p
s
class
if
icatio
n
f
o
r
th
r
ea
t
i
n
tellig
en
ce
p
u
r
p
o
s
es
b
y
p
r
o
v
id
in
g
in
f
o
r
m
atio
n
ab
o
u
t
th
e
T
T
P
o
f
s
o
m
e
r
a
n
s
o
m
war
e
f
am
ilies
[
2
5
]
.
T
h
e
in
f
o
r
m
atio
n
is
u
s
ef
u
l
f
o
r
d
ev
el
o
p
i
n
g
tar
g
eted
d
ef
en
s
e
s
tr
ateg
ies an
d
f
o
r
o
v
er
all
cy
b
e
r
s
ec
u
r
ity
p
o
s
tu
r
e.
2
.
3
.
K
ey
det
ec
t
io
n pa
ra
m
et
e
rs
-
Dete
ctin
g
th
e
ac
tiv
ity
o
f
r
an
s
o
m
war
e
is
im
p
o
r
tan
t
in
r
ea
l
t
im
e
s
o
as
to
m
in
im
ize
d
am
ag
e
an
d
a
s
wif
t
r
esp
o
n
s
e
is
p
o
s
s
ib
le.
An
d
r
ea
l
tim
e
d
etec
tio
n
m
ea
n
s
y
o
u
ar
e
alwa
y
s
watc
h
in
g
,
s
y
s
tem
ac
tiv
ities
,
n
etwo
r
k
tr
af
f
ic
an
d
u
s
er
b
eh
av
io
r
lo
o
k
in
g
o
u
t
f
o
r
an
y
an
o
m
alies
th
at
wo
u
ld
p
o
in
t
t
o
a
r
a
n
s
o
m
war
e
attac
k
.
Secu
r
ity
s
y
s
tem
s
ca
n
th
e
n
d
etec
t
th
e
r
a
n
s
o
m
war
e
as
it
b
eg
i
n
s
to
en
c
r
y
p
t
f
iles
,
an
d
co
u
n
te
r
m
ea
s
u
r
es
ca
n
th
u
s
b
e
in
s
tig
ated
to
s
to
p
th
e
attac
k
,
is
o
late
th
e
s
y
s
tem
s
af
f
ec
ted
,
an
d
s
ig
n
al
s
ec
u
r
ity
p
er
s
o
n
n
el
[
2
6
]
.
T
h
at
im
m
ed
iate
r
e
s
p
o
n
s
e
is
im
p
o
r
tan
t,
b
ec
au
s
e
it
s
to
p
s
th
e
s
p
r
ea
d
o
f
r
an
s
o
m
war
e
a
n
d
m
in
im
izes
d
ata
lo
s
s
.
-
E
n
cr
y
p
tio
n
s
u
ch
as
T
L
S/S
SL
is
ess
en
tial
in
o
r
d
er
to
s
ec
u
r
ely
c
o
n
n
ec
t,
in
o
r
d
er
to
s
ec
u
r
e
d
ata
tr
an
s
m
is
s
io
n
s
,
an
d
av
o
id
th
e
im
p
ac
t
o
f
r
an
s
o
m
war
e
attac
k
s
.
T
h
ese
m
eth
o
d
s
h
elp
p
r
ev
e
n
t
attac
k
er
s
f
r
o
m
‘
s
n
if
f
in
g
’
d
ata
t
h
at
is
ex
c
h
an
g
ed
b
etwe
en
s
y
s
tem
s
,
d
ata
th
at
is
en
cr
y
p
ted
s
o
it
wo
u
l
d
b
e
d
if
f
icu
lt
an
d
tim
e
co
n
s
u
m
in
g
f
o
r
an
attac
k
er
to
in
ter
ce
p
t
o
r
m
an
i
p
u
la
te
th
e
d
ata.
Saf
e
u
s
ag
e
p
r
o
c
ess
es
ca
n
b
e
im
p
lem
en
ted
to
p
r
ev
en
t
r
an
s
o
m
w
ar
e
in
f
ec
ted
c
o
m
p
u
te
r
s
f
r
o
m
b
ein
g
ac
ce
s
s
ed
,
o
r
h
a
v
in
g
in
f
o
r
m
atio
n
en
cr
y
p
ted
,
in
clu
d
in
g
s
tr
o
n
g
en
cr
y
p
tio
n
p
r
o
to
co
ls
[
2
7
]
.
A
n
o
t
h
er
th
in
g
th
at
it
also
h
elp
s
u
s
t
o
k
n
o
w
is
th
e
k
in
d
o
f
en
c
r
y
p
tio
n
th
at
r
an
s
o
m
war
e
u
s
es
b
ec
au
s
e
it
h
elp
s
u
s
d
ev
elo
p
d
ec
r
y
p
tio
n
to
o
ls
an
d
s
tr
ateg
ies
to
r
etr
iev
e
o
u
r
f
iles
with
o
u
t p
a
y
in
g
an
y
r
an
s
o
m
.
-
B
eh
av
io
r
al
an
aly
s
is
in
v
o
lv
es
an
aly
zin
g
s
y
s
tem
b
e
h
av
io
r
t
r
y
in
g
to
s
p
o
t
u
n
u
s
u
al
ac
tiv
ities
th
at
m
ig
h
t
in
d
icate
r
an
s
o
m
war
e
p
r
esen
c
e.
T
h
is
in
clu
d
es
f
iles
en
cr
y
p
tio
n
s
u
d
d
en
l
y
,
s
tr
an
g
e
f
ile
a
cc
ess
p
atter
n
s
,
in
cr
ea
s
e
o
f
f
iles
ch
an
g
es
in
s
h
o
r
t
tim
e,
ab
n
o
r
m
al
n
etwo
r
k
tr
af
f
ic.
Secu
r
ity
s
y
s
tem
s
ca
n
d
etec
t
r
an
s
o
m
war
e
ea
r
ly
in
its
ex
ec
u
tio
n
p
h
ase
b
y
a
n
aly
zin
g
th
ese
b
eh
av
io
r
’
s
[
2
8
]
.
T
h
e
r
ea
s
o
n
w
h
y
b
eh
a
v
io
r
al
an
aly
s
is
is
ef
f
ec
tiv
e
is
b
ec
au
s
e
it
lo
o
k
s
at
th
e
ac
tio
n
s
tak
en
b
y
th
e
m
alwa
r
e
in
s
tead
o
f
th
at
m
alwa
r
e
’
s
co
d
e,
m
ea
n
in
g
it c
an
d
etec
t n
e
w
an
d
u
n
k
n
o
w
n
r
an
s
o
m
wa
r
e
v
ar
ian
ts
b
ased
o
n
th
ei
r
b
eh
a
v
io
r
.
-
I
t
is
h
ig
h
ly
im
p
o
r
tan
t
to
ex
tr
a
ct
an
d
s
elec
t
f
ea
tu
r
es
f
o
r
d
ev
e
lo
p
in
g
r
o
b
u
s
t
r
an
s
o
m
war
e
d
etec
tio
n
m
o
d
el
s
as
th
ey
ar
e
ef
f
ec
tiv
e.
T
o
id
e
n
t
if
y
,
an
d
th
e
n
s
elec
t,
th
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es
o
u
t
o
f
th
e
d
a
ta
we
em
p
lo
y
tech
n
iq
u
es
s
u
ch
as
PC
A
an
d
co
r
r
elatio
n
an
al
y
s
is
.
T
h
e
f
ea
tu
r
es
ca
n
b
e
f
ile
ac
ce
s
s
tim
es,
m
o
d
if
icatio
n
p
atter
n
s
,
p
r
o
ce
s
s
b
eh
av
io
r
s
an
d
n
etwo
r
k
c
o
m
m
u
n
icatio
n
p
at
ter
n
s
.
Dete
ctio
n
m
o
d
els
with
f
ewe
r
co
m
p
u
tatio
n
al
lo
a
d
an
d
b
et
ter
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
c
an
b
e
d
ev
el
o
p
ed
b
y
s
elec
tin
g
th
e
m
o
s
t
in
f
o
r
m
ativ
e
f
ea
tu
r
es.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
R
esu
lts
o
f
th
is
s
tu
d
y
s
h
o
w
th
at
DL
m
o
d
els
lik
e
C
NNs
an
d
R
NNs
o
u
tp
er
f
o
r
m
tr
a
d
itio
n
al
an
d
ML
ap
p
r
o
ac
h
es
b
y
9
5
%
ac
cu
r
ac
y
,
9
3
%
p
r
ec
is
io
n
,
9
2
%
r
ec
al
l,
an
d
9
2
%
F1
-
s
co
r
e
i
n
d
e
f
e
n
d
in
g
r
an
s
o
m
war
e
attac
k
s
.
T
h
en
,
DL
m
o
d
els
’
ab
i
lity
to
au
to
m
atica
lly
ex
tr
ac
t a
n
d
lear
n
h
ier
ar
ch
ical
f
ea
tu
r
es f
r
o
m
a
b
ig
co
r
p
u
s
o
f
d
ata
en
s
u
r
es
th
at
th
e
m
o
d
el
s
ca
n
also
f
i
n
d
co
m
p
le
x
p
a
tter
n
s
an
d
ev
o
lv
e
t
o
n
ew
r
a
n
s
o
m
war
e
th
r
ea
ts
.
C
o
m
p
ar
ed
to
tr
ad
itio
n
al
m
eth
o
d
s
lik
e
k
n
o
wn
r
an
s
o
m
war
e
s
ig
n
atu
r
es,
an
d
ML
m
o
d
els
wh
ich
h
ea
v
ily
r
ely
o
n
m
an
u
al
f
ea
tu
r
e
en
g
in
ee
r
in
g
,
D
L
ap
p
r
o
ac
h
es p
er
f
o
r
m
b
etter
.
T
h
is
is
in
lin
e
w
ith
p
r
ev
io
u
s
s
tu
d
ies
b
u
t th
is
s
tu
d
y
f
u
r
th
er
e
x
ten
d
s
to
c
o
m
p
u
tati
o
n
ally
an
d
s
ca
lab
ilit
y
lim
itatio
n
s
o
f
DL
m
o
d
els,
as
well
as
im
p
o
r
tan
ce
o
f
b
eh
av
io
r
al
an
aly
s
is
f
o
r
r
an
s
o
m
war
e
g
r
o
u
p
class
if
y
in
g
.
Desp
ite
th
ese
ch
allen
g
es,
DL
m
o
d
els
ar
e
s
till
d
ep
lo
y
ed
in
r
eso
u
r
ce
co
n
s
tr
ain
ed
en
v
ir
o
n
m
en
ts
th
at
r
eq
u
ir
e
a
h
ig
h
c
o
m
p
u
tatio
n
al
co
s
t,
an
d
ar
e
s
till
r
ely
in
g
o
n
p
u
b
licly
av
ailab
le
d
atasets
th
at
m
ay
n
o
t
b
e
d
iv
e
r
s
e
en
o
u
g
h
.
T
h
e
s
e
r
esu
lts
h
av
e
im
p
licatio
n
s
an
d
th
e
n
ee
d
f
o
r
co
m
b
in
in
g
DL
m
o
d
els
with
r
ea
l
tim
e
r
an
s
o
m
war
e
d
ete
ctio
n
f
r
am
ewo
r
k
s
an
d
d
e
v
e
lo
p
in
g
m
u
ltimo
d
a
l
ap
p
r
o
ac
h
es
co
m
b
in
in
g
DL
with
tr
ad
itio
n
al
m
eth
o
d
s
to
in
cr
ea
s
e
r
esil
ien
ce
ag
ain
s
t
n
o
v
el
th
r
ea
ts
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
in
v
o
lv
e
ca
m
er
as
th
at
co
m
m
u
n
icate
to
DL
ar
c
h
itectu
r
es
th
at
ca
n
s
u
cc
ess
f
u
lly
h
an
d
le
lig
h
tweig
h
t,
s
ca
lab
le
DL
ar
c
h
itectu
r
es
f
o
r
r
ea
l
tim
e
ap
p
licatio
n
s
,
ad
v
e
r
s
ar
ial
tr
ain
in
g
f
o
r
e
v
asio
n
tactics
ev
asio
n
,
an
d
co
llab
o
r
ativ
e
wo
r
k
to
b
u
ild
s
tan
d
ar
d
ized
an
d
d
iv
er
s
e
d
atasets
to
h
elp
im
p
r
o
v
e
m
o
d
el
g
en
er
aliza
b
ilit
y
.
T
h
e
im
p
r
o
v
e
m
en
ts
ar
e
n
ec
ess
ar
y
wh
en
s
tr
en
g
th
en
in
g
cy
b
er
s
ec
u
r
ity
in
d
ata
ce
n
ter
an
d
clo
u
d
en
v
ir
o
n
m
en
ts
.
R
ea
l
-
tim
e
d
ete
ctio
n
is
cr
itical
in
m
i
n
im
izin
g
th
e
im
p
ac
t
o
f
r
a
n
s
o
m
war
e
attac
k
s
b
y
en
a
b
lin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
0
8
5
-
1
0
9
4
1090
s
wif
t
r
esp
o
n
s
e.
Sev
er
al
s
tu
d
ies
h
av
e
em
p
h
asized
t
h
e
im
p
o
r
tan
ce
o
f
r
ea
l
-
tim
e
d
ata
a
n
a
ly
s
is
in
id
en
tify
in
g
r
an
s
o
m
war
e
ac
tiv
ities
ea
r
ly
.
T
h
is
d
etailed
an
aly
s
is
in
T
ab
le
4
p
r
esen
ts
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
o
f
v
ar
io
u
s
r
an
s
o
m
war
e
d
etec
tio
n
m
o
d
el
s
,
h
ig
h
lig
h
tin
g
th
eir
ef
f
ec
tiv
en
ess
an
d
lim
itatio
n
s
b
ased
o
n
th
e
r
ev
iewe
d
liter
atu
r
e.
T
h
e
Fig
u
r
e
2
illu
s
tr
ates
th
e
co
m
p
ar
ativ
e
p
er
f
o
r
m
an
ce
o
f
th
r
ee
d
if
f
e
r
en
t
r
a
n
s
o
m
war
e
d
etec
tio
n
m
o
d
els:
tr
ad
itio
n
al
d
etec
tio
n
,
ML
b
ased
d
etec
tio
n
,
an
d
DL
b
ased
d
etec
tio
n
.
Acc
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
a
n
d
F1
-
s
co
r
e
wer
e
co
m
p
ar
e
d
ac
r
o
s
s
th
ese
m
o
d
els.
T
h
e
ch
ar
t
s
h
o
ws
clea
r
ly
th
at
th
e
D
L
b
ased
d
etec
tio
n
m
o
d
els
o
u
tp
er
f
o
r
m
tr
ad
it
io
n
a
l
an
d
ML
b
ased
d
etec
tio
n
m
o
d
els
wh
en
it
co
m
es
to
d
ete
ctin
g
r
an
s
o
m
war
e
.
T
h
e
im
p
licatio
n
is
th
at
in
th
e
d
y
n
am
ic,
ev
e
r
-
ch
an
g
in
g
r
ea
l
m
o
f
r
an
s
o
m
war
e
th
r
ea
ts
,
DL
ap
p
r
o
ac
h
es,
th
at
ar
e
ab
le
to
lear
n
c
o
m
p
lex
p
atter
n
s
an
d
g
e
n
er
alize
b
etter
f
r
o
m
la
r
g
er
d
atasets
ar
e
m
o
r
e
s
u
ited
to
th
e
p
r
o
b
lem
.
T
ab
le
4
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
r
an
s
o
m
war
e
d
etec
tio
n
m
o
d
els
C
a
t
e
g
o
r
y
R
e
f
e
r
e
n
c
e
Y
e
a
r
A
p
p
r
o
a
c
h
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
Tr
a
d
i
t
i
o
n
a
l
B
r
e
w
e
r
[
6
]
2
0
1
6
S
i
g
n
a
t
u
r
e
-
b
a
s
e
d
a
n
d
h
e
u
r
i
s
t
i
c
-
b
a
s
e
d
0
.
8
5
0
.
8
0
.
7
5
0
.
7
7
Tr
a
d
i
t
i
o
n
a
l
C
e
l
d
r
á
n
e
t
a
l
.
[
7
]
2
0
2
2
B
e
h
a
v
i
o
r
a
l
a
n
a
l
y
si
s
0
.
8
3
0
.
7
8
0
.
7
6
0
.
7
7
Tr
a
d
i
t
i
o
n
a
l
K
o
k
e
t
a
l
.
[
8
]
2
0
1
9
S
i
g
n
a
t
u
r
e
-
b
a
s
e
d
0
.
8
2
0
.
7
9
0
.
7
4
0
.
7
6
ML
A
l
r
a
i
z
z
a
a
n
d
A
l
g
a
r
n
i
[
9
]
2
0
2
3
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
0
.
9
0
.
8
8
0
.
8
5
0
.
8
6
ML
O
’
K
a
n
e
e
t
a
l
.
[
1
0
]
2
0
1
8
H
i
st
o
r
i
c
a
l
a
n
a
l
y
s
i
s
0
.
8
8
0
.
8
6
0
.
8
3
0
.
8
4
ML
S
h
a
u
k
a
t
a
n
d
R
i
b
e
i
r
o
[
1
1
]
2
0
1
8
La
y
e
r
e
d
d
e
f
e
n
se
sy
s
t
e
m
ML
0
.
9
1
0
.
8
9
0
.
8
6
0
.
8
7
ML
Ta
l
a
b
a
n
i
a
n
d
A
b
d
u
l
h
a
d
i
[
1
2
]
2
0
2
2
R
u
l
e
-
b
a
se
d
a
l
g
o
r
i
t
h
ms
0
.
8
9
0
.
8
7
0
.
8
4
0
.
8
5
DL
B
e
l
l
o
e
t
a
l
.
[
1
3
]
2
0
2
1
D
e
e
p
l
e
a
r
n
i
n
g
0
.
9
5
0
.
9
3
0
.
9
2
0
.
9
2
DL
A
l
mas
h
h
a
d
a
n
i
e
t
a
l
.
[
1
4
]
2
0
1
9
M
u
l
t
i
-
c
l
a
ssi
f
i
e
r
n
e
t
w
o
r
k
0
.
9
4
0
.
9
2
0
.
9
1
0
.
9
1
DL
H
w
a
n
g
e
t
a
l
.
[
1
5
]
2
0
2
0
D
y
n
a
mi
c
a
n
a
l
y
si
s
a
n
d
M
L
t
e
c
h
n
i
q
u
e
s
0
.
9
2
0
.
9
0
.
8
8
0
.
8
9
DL
M
a
k
i
n
d
e
e
t
a
l
.
[
1
6
]
2
0
1
9
M
L
a
n
d
a
g
e
n
t
-
b
a
se
d
m
i
c
r
o
si
mu
l
a
t
i
o
n
0
.
9
3
0
.
9
1
0
.
8
9
0
.
9
DL
P
a
q
u
e
t
-
C
l
o
u
st
o
n
e
t
a
l
.
[
1
7
]
2
0
1
9
M
L
a
n
d
b
l
o
c
k
c
h
a
i
n
a
n
a
l
y
si
s
0
.
9
1
0
.
8
9
0
.
8
7
0
.
8
8
Fig
u
r
e
2
.
Per
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
o
f
r
a
n
s
o
m
war
e
d
etec
tio
n
m
o
d
els
T
h
e
F
ig
u
r
e
2
illu
s
tr
ates
th
e
co
m
p
ar
ativ
e
p
er
f
o
r
m
an
ce
o
f
th
r
ee
d
if
f
e
r
en
t
r
a
n
s
o
m
war
e
d
etec
tio
n
m
o
d
els:
tr
ad
itio
n
al
d
etec
tio
n
,
ML
b
ased
d
etec
tio
n
,
an
d
DL
b
ased
d
etec
tio
n
.
Acc
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
a
n
d
F1
-
s
co
r
e
wer
e
co
m
p
ar
e
d
ac
r
o
s
s
th
ese
m
o
d
els.
T
h
e
ch
ar
t
s
h
o
ws
c
lear
ly
th
at
th
e
D
L
b
ased
d
etec
tio
n
m
o
d
els
o
u
tp
er
f
o
r
m
tr
ad
itio
n
a
l
an
d
ML
b
ased
d
etec
tio
n
m
o
d
els
wh
en
it
co
m
es
to
d
ete
ctin
g
r
an
s
o
m
war
e
.
T
h
e
im
p
licatio
n
is
th
at
in
th
e
d
y
n
am
ic,
ev
e
r
-
ch
an
g
in
g
r
ea
l
m
o
f
r
an
s
o
m
war
e
th
r
ea
ts
,
DL
ap
p
r
o
ac
h
es,
th
at
ar
e
ab
le
to
lear
n
c
o
m
p
lex
p
atter
n
s
an
d
g
e
n
er
alize
b
etter
f
r
o
m
la
r
g
er
d
atasets
ar
e
m
o
r
e
s
u
ited
to
th
e
p
r
o
b
lem
.
T
h
e
R
OC
cu
r
v
e
s
h
o
wn
in
th
e
Fig
u
r
e
3
co
m
p
ar
es
th
e
p
er
f
o
r
m
an
ce
o
f
th
r
ee
d
if
f
er
e
n
t
r
a
n
s
o
m
war
e
d
etec
tio
n
m
o
d
els:
tr
ad
itio
n
al
d
etec
tio
n
,
ML
b
ased
d
etec
tio
n
,
an
d
DL
b
ase
d
d
etec
tio
n
.
T
h
e
R
OC
cu
r
v
e
is
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
s
u
r
ve
y
o
n
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
u
s
in
g
A
I
mo
d
els
(
Go
teti
B
a
d
r
in
a
th
)
1091
p
lo
t
o
f
th
e
d
iag
n
o
s
tic
ab
ilit
y
o
f
a
b
in
ar
y
class
if
ier
s
y
s
tem
a
s
its
d
is
cr
im
in
atio
n
th
r
esh
o
ld
is
v
ar
ied
.
T
h
e
m
o
r
e
s
ig
n
if
ican
t A
UC
v
alu
e
o
f
th
e
DL
b
ased
m
o
d
el
in
d
icate
s
b
ett
er
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
,
an
d
,
th
er
ef
o
r
e,
is
th
e
m
o
s
t r
eliab
le
ap
p
r
o
ac
h
f
o
r
r
a
n
s
o
m
war
e
d
etec
tio
n
in
d
y
n
a
m
ic
an
d
ev
o
lv
in
g
th
r
ea
t la
n
d
s
ca
p
e
.
W
e
f
o
u
n
d
th
at
th
e
DL
b
ased
m
o
d
els,
s
u
ch
as
C
NN
o
r
R
NN,
co
n
s
is
ten
tly
co
r
r
elate
d
with
h
ig
h
er
d
etec
tio
n
ac
cu
r
ac
y
,
p
r
ec
is
io
n
an
d
r
ec
all
th
a
n
th
e
tr
a
d
itio
n
al
m
eth
o
d
s
an
d
th
e
ML
b
ased
m
o
d
els.
T
h
is
s
tu
d
y
p
r
o
p
o
s
ed
th
e
u
s
e
o
f
DL
b
as
ed
tech
n
iq
u
es
th
at
o
u
tp
er
f
o
r
m
ed
tr
ad
itio
n
al
s
ig
n
atu
r
e
-
b
ased
m
eth
o
d
s
b
y
an
in
o
r
d
in
ately
h
ig
h
er
p
r
o
p
o
r
tio
n
o
f
ac
cu
r
ate
r
an
s
o
m
war
e
d
ete
ctio
n
b
ec
au
s
e
DL
tech
n
iq
u
es
h
av
e
th
e
ca
p
ab
ilit
y
to
lear
n
co
m
p
lex
p
atter
n
s
an
d
ar
e
ab
le
to
a
d
ap
t
to
n
ew
r
an
s
o
m
war
e
v
ar
ia
n
ts
.
I
n
ad
d
itio
n
,
h
eu
r
is
tic
m
eth
o
d
s
h
ad
m
o
r
e
f
alse
p
o
s
itiv
es
an
d
ML
m
eth
o
d
s
ex
h
ib
ited
m
o
d
er
ate
p
er
f
o
r
m
an
ce
,
b
u
t
n
ee
d
e
d
ex
ten
s
iv
e
f
ea
t
u
r
e
en
g
in
ee
r
in
g
.
R
ea
l
tim
e
s
ce
n
ar
io
s
wer
e
ef
f
ec
tiv
ely
m
itig
ated
b
y
DL
m
o
d
els,
wh
ich
ac
h
iev
ed
s
u
p
e
r
io
r
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
.
T
h
e
lim
itatio
n
s
,
im
p
ac
t,
an
d
ac
ti
o
n
ab
le
s
u
g
g
esti
o
n
s
f
o
r
f
u
tu
r
e
wo
r
k
ar
e
o
u
tlin
ed
in
th
is
T
ab
le
5
,
to
b
alan
ce
an
d
r
e
f
lect
o
n
th
e
s
tu
d
y
’
s
co
n
s
tr
ain
ts
.
Fig
u
r
e
3
.
R
OC
c
u
r
v
e
T
ab
le
5
.
Key
i
n
s
ig
h
ts
an
d
lim
i
tatio
n
s
Li
mi
t
a
t
i
o
n
D
e
scri
p
t
i
o
n
P
o
t
e
n
t
i
a
l
i
m
p
a
c
t
o
n
r
e
s
u
l
t
s
S
u
g
g
e
s
t
e
d
f
u
t
u
r
e
w
o
r
k
D
a
t
a
s
e
t
d
i
v
e
r
si
t
y
Th
e
st
u
d
y
r
e
l
i
e
d
o
n
p
u
b
l
i
c
l
y
a
v
a
i
l
a
b
l
e
d
a
t
a
se
t
s t
h
a
t
m
a
y
n
o
t
f
u
l
l
y
r
e
p
r
e
se
n
t
t
h
e
v
a
r
i
e
t
y
o
f
r
a
n
s
o
mw
a
r
e
a
c
t
i
v
i
t
i
e
s
i
n
r
e
a
l
-
w
o
r
l
d
sce
n
a
r
i
o
s.
”
R
e
s
u
l
t
s m
i
g
h
t
n
o
t
g
e
n
e
r
a
l
i
z
e
w
e
l
l
t
o
n
o
v
e
l
r
a
n
s
o
mw
a
r
e
o
r
d
i
v
e
r
se
r
e
a
l
-
w
o
r
l
d
e
n
v
i
r
o
n
m
e
n
t
s.
C
o
n
d
u
c
t
s
t
u
d
i
e
s
u
s
i
n
g
l
a
r
g
e
r
,
mo
r
e
d
i
v
e
r
se,
a
n
d
r
e
a
l
-
w
o
r
l
d
d
a
t
a
se
t
s
t
o
i
m
p
r
o
v
e
t
h
e
r
o
b
u
st
n
e
s
s o
f
d
e
t
e
c
t
i
o
n
mo
d
e
l
s.
C
o
m
p
u
t
a
t
i
o
n
a
l
r
e
q
u
i
r
e
m
e
n
t
s
D
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s re
q
u
i
r
e
su
b
s
t
a
n
t
i
a
l
c
o
m
p
u
t
a
t
i
o
n
a
l
r
e
so
u
r
c
e
s
f
o
r
t
r
a
i
n
i
n
g
a
n
d
d
e
p
l
o
y
me
n
t
,
w
h
i
c
h
c
a
n
l
i
m
i
t
”
r
e
a
l
-
t
i
m
e
a
p
p
l
i
c
a
b
i
l
i
t
y
i
n
r
e
so
u
r
c
e
-
l
i
m
i
t
e
d
e
n
v
i
r
o
n
me
n
t
s.
M
a
y
r
e
s
t
r
i
c
t
t
h
e
s
c
a
l
a
b
i
l
i
t
y
a
n
d
r
e
a
l
-
t
i
me
a
p
p
l
i
c
a
t
i
o
n
o
f
t
h
e
p
r
o
p
o
se
d
me
t
h
o
d
s.
D
e
v
e
l
o
p
l
i
g
h
t
w
e
i
g
h
t
D
L
a
r
c
h
i
t
e
c
t
u
r
e
s
o
r
u
s
e
h
a
r
d
w
a
r
e
a
c
c
e
l
e
r
a
t
i
o
n
t
o
r
e
d
u
c
e
c
o
m
p
u
t
a
t
i
o
n
a
l
o
v
e
r
h
e
a
d
.
F
a
l
se
p
o
si
t
i
v
e
s i
n
h
e
u
r
i
s
t
i
c
-
b
a
s
e
d
met
h
o
d
s
H
e
u
r
i
s
t
i
c
d
e
t
e
c
t
i
o
n
me
t
h
o
d
s
o
c
c
a
si
o
n
a
l
l
y
m
i
si
d
e
n
t
i
f
i
e
d
b
e
n
i
g
n
a
c
t
i
v
i
t
i
e
s
a
s
mal
i
c
i
o
u
s
d
u
e
t
o
o
v
e
r
l
a
p
p
i
n
g
b
e
h
a
v
i
o
r
p
a
t
t
e
r
n
s.
M
a
y
i
n
c
r
e
a
s
e
u
n
n
e
c
e
ss
a
r
y
a
l
e
r
t
s,
r
e
d
u
c
i
n
g
t
h
e
e
f
f
i
c
i
e
n
c
y
o
f
d
e
t
e
c
t
i
o
n
sy
st
e
ms i
n
o
p
e
r
a
t
i
o
n
a
l
e
n
v
i
r
o
n
me
n
t
s.
C
o
m
b
i
n
e
h
e
u
r
i
st
i
c
me
t
h
o
d
s
w
i
t
h
D
L
m
o
d
e
l
s t
o
i
m
p
r
o
v
e
sp
e
c
i
f
i
c
i
t
y
a
n
d
r
e
d
u
c
e
f
a
l
s
e
p
o
s
i
t
i
v
e
s.
”
R
a
p
i
d
l
y
e
v
o
l
v
i
n
g
r
a
n
s
o
mw
a
r
e
t
a
c
t
i
c
s
M
o
d
e
l
s m
a
y
st
r
u
g
g
l
e
t
o
a
d
a
p
t
t
o
c
o
n
t
i
n
u
o
u
s
l
y
e
v
o
l
v
i
n
g
r
a
n
so
mw
a
r
e
v
a
r
i
a
n
t
s w
i
t
h
n
o
v
e
l
t
e
c
h
n
i
q
u
e
s
n
o
t
r
e
p
r
e
s
e
n
t
e
d
i
n
t
h
e
t
r
a
i
n
i
n
g
d
a
t
a
.
”
C
o
u
l
d
r
e
d
u
c
e
t
h
e
d
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
o
v
e
r
t
i
m
e
a
s
n
e
w
v
a
r
i
a
n
t
s
e
mer
g
e
.
I
mp
l
e
me
n
t
a
d
a
p
t
i
v
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
su
c
h
a
s
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
o
r
c
o
n
t
i
n
u
o
u
s
mo
d
e
l
u
p
d
a
t
i
n
g
,
f
o
r
b
e
t
t
e
r
a
d
a
p
t
a
b
i
l
i
t
y
.
La
c
k
o
f
st
a
n
d
a
r
d
i
z
e
d
e
v
a
l
u
a
t
i
o
n
me
t
r
i
c
s
D
i
f
f
e
r
e
n
t
s
t
u
d
i
e
s
u
se
v
a
r
i
e
d
met
r
i
c
s,
ma
k
i
n
g
d
i
r
e
c
t
p
e
r
f
o
r
m
a
n
c
e
c
o
mp
a
r
i
s
o
n
s
c
h
a
l
l
e
n
g
i
n
g
.
M
a
y
l
e
a
d
t
o
i
n
c
o
n
si
s
t
e
n
t
b
e
n
c
h
mar
k
s
a
n
d
d
i
f
f
i
c
u
l
t
y
i
n
as
sess
i
n
g
r
e
l
a
t
i
v
e
mo
d
e
l
p
e
r
f
o
r
m
a
n
c
e
.
P
r
o
p
o
se
a
n
d
a
d
o
p
t
st
a
n
d
a
r
d
i
z
e
d
e
v
a
l
u
a
t
i
o
n
me
t
r
i
c
s
f
o
r
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
mo
d
e
l
s
t
o
e
n
a
b
l
e
b
e
t
t
e
r
c
o
mp
a
r
i
s
o
n
s
.
A
b
se
n
c
e
o
f
a
d
v
e
r
sar
i
a
l
a
t
t
a
c
k
c
o
n
si
d
e
r
a
t
i
o
n
s
Th
i
s
st
u
d
y
d
i
d
n
o
t
a
d
d
r
e
ss
t
h
e
i
mp
a
c
t
o
f
a
d
v
e
r
sari
a
l
a
t
t
a
c
k
s
w
h
e
r
e
r
a
n
s
o
mw
a
r
e
ma
y
i
n
t
e
n
t
i
o
n
a
l
l
y
e
v
a
d
e
d
e
t
e
c
t
i
o
n
.
M
o
d
e
l
s
c
o
u
l
d
b
e
v
u
l
n
e
r
a
b
l
e
t
o
a
d
v
e
r
sar
i
a
l
ma
n
i
p
u
l
a
t
i
o
n
,
r
e
d
u
c
i
n
g
d
e
t
e
c
t
i
o
n
e
f
f
e
c
t
i
v
e
n
e
ss
i
n
a
d
v
e
r
sar
i
a
l
sce
n
a
r
i
o
s.
I
n
v
e
st
i
g
a
t
e
a
d
v
e
r
sar
i
a
l
t
r
a
i
n
i
n
g
t
o
e
n
h
a
n
c
e
mo
d
e
l
r
o
b
u
st
n
e
ss
a
g
a
i
n
st
e
v
a
si
o
n
t
e
c
h
n
i
q
u
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
0
8
5
-
1
0
9
4
1092
4.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
we
p
r
esen
t
a
co
m
p
r
eh
en
s
iv
e
s
u
r
v
ey
o
f
r
an
s
o
m
war
e
ev
o
l
u
tio
n
a
n
d
e
v
alu
ate
th
e
r
o
le
o
f
AI
esp
ec
ially
,
ML
,
an
d
DL
in
r
an
s
o
m
war
e
d
etec
tio
n
.
H
o
wev
er
,
ex
is
tin
g
tr
ad
itio
n
al
m
eth
o
d
s
,
in
clu
d
in
g
s
ig
n
atu
r
e
b
ased
an
d
h
eu
r
is
tic
b
ased
d
etec
tio
n
,
ar
e
in
a
d
eq
u
a
te
ag
ain
s
t
th
e
n
ewly
em
er
g
in
g
an
d
s
o
p
h
is
ticated
r
an
s
o
m
war
e
v
ar
ian
ts
.
T
h
eir
r
elian
ce
o
n
k
n
o
w
n
s
ig
n
atu
r
e
s
an
d
b
eh
av
io
r
al
p
atter
n
s
p
r
ev
en
ts
th
em
f
r
o
m
id
en
tify
in
g
n
o
v
el,
o
r
r
a
p
id
ly
e
v
o
lv
in
g
,
th
r
ea
ts
an
d
th
u
s
ca
ll
f
o
r
n
o
v
el
ap
p
r
o
ac
h
es.
Usi
n
g
ML
tech
n
iq
u
es
s
u
ch
as
d
ec
is
io
n
tr
ee
s
,
r
an
d
o
m
f
o
r
est,
an
d
SVMs
we
f
o
u
n
d
a
cc
u
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
s
u
p
e
r
io
r
to
t
r
ad
itio
n
al
m
eth
o
d
s
.
Ho
wev
e
r
,
th
ese
m
o
d
els
s
u
cc
ess
f
u
lly
an
aly
ze
a
n
d
class
if
y
r
an
s
o
m
wa
r
e
b
y
ex
tr
ac
tin
g
im
p
o
r
tan
t
f
ea
tu
r
es
f
r
o
m
s
y
s
tem
b
eh
av
io
r
s
,
n
etwo
r
k
tr
af
f
ic.
Ho
wev
e
r
,
f
o
r
i
n
s
tan
ce
ML
m
et
h
o
d
s
,
f
ea
tu
r
e
en
g
in
ee
r
in
g
is
o
f
ten
n
ee
d
ed
an
d
ad
a
p
tab
ilit
y
to
ev
o
lv
in
g
r
an
s
o
m
war
e
tactics is l
o
w.
“
T
h
e
b
est
to
o
ls
f
o
r
r
a
n
s
o
m
war
e
d
etec
tio
n
wer
e
DL
m
o
d
els,
in
clu
d
in
g
C
NNs
an
d
R
NNs.
A
s
m
ac
h
in
es,
th
e
y
ar
e
esp
ec
iall
y
g
o
o
d
at
lear
n
in
g
co
m
p
lex
p
atter
n
s
t
o
d
estro
y
s
o
p
h
is
ticated
r
an
s
o
m
wa
r
e
v
ar
ian
ts
.
I
n
ter
m
s
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
a
n
d
F1
-
s
co
r
e,
DL
m
o
d
els
o
u
t
p
er
f
o
r
m
ed
b
o
th
tr
ad
itio
n
al
a
n
d
ML
b
ased
m
eth
o
d
s
co
n
s
is
ten
tly
.
Ad
d
itio
n
ally
,
th
ey
a
r
e
ex
c
ellen
t
f
o
r
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
an
d
d
etec
tio
n
,
a
n
d
s
h
o
w
s
u
p
er
io
r
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
f
o
r
d
etec
tin
g
r
an
s
o
m
war
e.
DL
is
h
ig
h
lig
h
te
d
a
s
ce
n
tr
al
to
s
o
lv
in
g
to
d
ay
’
s
cy
b
e
r
s
ec
u
r
ity
p
r
o
b
le
m
s
,
in
clu
d
in
g
th
eir
u
s
e
in
r
ea
l
tim
e
m
o
n
ito
r
in
g
s
y
s
tem
s
f
o
r
r
ap
id
d
etec
tio
n
a
n
d
r
esp
o
n
s
e.
E
v
e
n
th
o
u
g
h
DL
m
o
d
els
p
r
o
v
i
d
e
a
l
o
t
o
f
ad
v
a
n
tag
es,
h
ig
h
c
o
m
p
u
tatio
n
al
co
s
t
an
d
r
elian
ce
o
n
la
r
g
e
lab
eled
d
atasets
m
ak
e
th
em
n
o
t su
itab
le
f
o
r
d
e
p
lo
y
m
e
n
t to
r
e
s
o
u
r
ce
co
n
s
tr
ain
e
d
en
v
ir
o
n
m
e
n
ts
.
T
o
o
v
e
r
co
m
e
s
u
c
h
lim
itatio
n
s
,
f
u
tu
r
e
wo
r
k
s
h
o
u
ld
in
v
est
o
n
th
e
d
ev
elo
p
m
en
t
o
f
lig
h
t
weig
h
t
an
d
s
ca
lab
le
DL
ar
ch
itectu
r
es,
en
h
an
cin
g
m
o
d
el
r
o
b
u
s
tn
ess
v
ia
ad
v
er
s
ar
ial
tr
ain
in
g
,
as
well
as
co
llab
o
r
ativ
e
wo
r
k
f
o
r
d
ev
elo
p
m
en
t
o
f
s
tan
d
ar
d
i
ze
d
an
d
d
iv
er
s
e
d
atasets
.
B
y
in
teg
r
atin
g
m
u
ltimo
d
al
d
etec
tio
n
ap
p
r
o
ac
h
es
th
at
co
m
b
in
e
DL
with
h
eu
r
is
tic
an
d
b
eh
a
v
io
r
al
an
aly
s
is
m
eth
o
d
s
,
we
ex
p
ec
t
to
im
p
r
o
v
e
d
et
ec
tio
n
ac
cu
r
ac
y
a
n
d
d
ec
r
ea
s
e
f
alse
p
o
s
itiv
es.
T
h
is
s
u
r
v
ey
h
ig
h
lig
h
ts
th
e
n
ee
d
f
o
r
AI
b
ased
ap
p
r
o
ac
h
es
to
ad
d
r
ess
r
an
s
o
m
war
e
th
r
ea
ts
,
an
d
s
er
v
es
as
a
b
asis
f
o
r
f
u
tu
r
e
w
o
r
k
in
th
is
ar
ea
.
R
esear
ch
an
d
p
r
ac
titi
o
n
e
r
s
ca
n
u
s
e
th
e
p
o
wer
o
f
ML
an
d
DL
m
o
d
els to
d
ev
elo
p
m
o
r
e
ac
cu
r
ate,
ef
f
ec
tiv
e,
an
d
ad
a
p
tiv
e
r
an
s
o
m
war
e
d
etec
tio
n
s
y
s
tem
s
to
m
ax
im
u
m
b
en
ef
it th
e
d
ata
ce
n
ter
an
d
clo
u
d
in
f
r
astru
ctu
r
es.
”
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
ac
k
n
o
wled
g
e
t
h
e
r
esear
ch
ev
alu
atio
n
m
em
b
er
s
f
o
r
th
eir
in
v
alu
a
b
le
s
u
p
p
o
r
t
an
d
d
is
cu
s
s
io
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
was r
ec
eiv
e
d
f
o
r
t
h
is
s
tu
d
y
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Go
teti Bad
r
in
at
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Dr
.
Ar
p
ita
Gu
p
ta
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
“
T
h
e
au
th
o
r
s
d
ec
lar
e
n
o
co
n
f
lict o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
“
I
n
f
o
r
m
ed
co
n
s
en
t
was
n
o
t
ap
p
licab
le
f
o
r
t
h
is
s
tu
d
y
as
it
d
id
n
o
t
in
v
o
lv
e
h
u
m
an
p
ar
ti
cip
an
ts
o
r
id
en
tifia
b
le
h
u
m
an
d
ata
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
s
u
r
ve
y
o
n
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
u
s
in
g
A
I
mo
d
els
(
Go
teti
B
a
d
r
in
a
th
)
1093
E
T
H
I
CAL AP
P
RO
V
AL
“
T
h
is
s
tu
d
y
d
id
n
o
t in
v
o
lv
e
h
u
m
an
o
r
a
n
im
al
s
u
b
jects,
s
o
eth
ical
ap
p
r
o
v
al
was n
o
t r
eq
u
ir
ed
DATA AV
AI
L
AB
I
L
I
T
Y
No
n
ew
d
atasets
wer
e
g
en
er
a
ted
o
r
an
aly
ze
d
f
o
r
t
h
is
s
u
r
v
e
y
.
All
in
f
o
r
m
atio
n
an
d
"
d
ata"
p
r
esen
te
d
wer
e
ex
tr
ac
ted
f
r
o
m
p
r
ev
io
u
s
ly
p
u
b
lis
h
ed
wo
r
k
s
,
wh
ic
h
ar
e
f
u
lly
cited
in
th
e
R
ef
er
en
ce
s
s
ec
t
io
n
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
A
z
m
o
o
d
e
h
,
A
.
D
e
h
g
h
a
n
t
a
n
h
a
,
M
.
C
o
n
t
i
,
a
n
d
K
.
-
K
.
R
.
C
h
o
o
,
“
D
e
t
e
c
t
i
n
g
c
r
y
p
t
o
-
r
a
n
so
mw
a
r
e
i
n
I
o
T
n
e
t
w
o
r
k
s
b
a
s
e
d
o
n
e
n
e
r
g
y
c
o
n
su
mp
t
i
o
n
f
o
o
t
p
r
i
n
t
,
”
J
o
u
r
n
a
l
o
f
A
m
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
ze
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
1
1
4
1
–
1
1
5
2
,
A
u
g
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
017
-
0
5
5
8
-
5.
[
2
]
J.
A
.
H
.
S
i
l
v
a
a
n
d
M
.
H
e
r
n
a
n
d
e
z
-
A
l
v
a
r
e
z
,
“
L
a
r
g
e
s
c
a
l
e
r
a
n
so
mw
a
r
e
d
e
t
e
c
t
i
o
n
b
y
c
o
g
n
i
t
i
v
e
se
c
u
r
i
t
y
,
”
2
0
1
7
I
E
EE
2
n
d
E
c
u
a
d
o
r
T
e
c
h
n
i
c
a
l
C
h
a
p
t
e
rs
Me
e
t
i
n
g
,
ETC
M
2
0
1
7
,
v
o
l
.
2
0
1
7
-
Ja
n
u
a
r
y
,
p
p
.
1
–
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
E
TC
M
.
2
0
1
7
.
8
2
4
7
4
8
4
.
[
3
]
I
.
A
.
C
h
e
st
i
,
M
.
H
u
ma
y
u
n
,
N
.
U
.
S
a
m
a
,
a
n
d
N
.
Z
.
J
h
a
n
j
h
i
,
“
E
v
o
l
u
t
i
o
n
,
mi
t
i
g
a
t
i
o
n
,
a
n
d
p
r
e
v
e
n
t
i
o
n
o
f
r
a
n
so
mw
a
r
e
,
”
2
0
2
0
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s,
I
C
C
I
S
2
0
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
S
4
9
2
4
0
.
2
0
2
0
.
9
2
5
7
7
0
8
.
[
4
]
P
.
P
.
K
u
l
k
a
r
n
i
,
T
.
N
a
f
i
s,
a
n
d
S
.
S
.
B
i
sw
a
s
,
“
P
r
e
v
e
n
t
i
v
e
me
a
s
u
r
e
s
a
n
d
i
n
c
i
d
e
n
t
r
e
sp
o
n
se
f
o
r
l
o
c
k
y
r
a
n
so
mw
a
r
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
R
e
se
a
rc
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
8
,
n
o
.
5
,
2
0
1
8
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
w
w
w
.
i
j
a
r
c
s.
i
n
f
o
.
[
5
]
A
.
Jeg
e
d
e
,
A
.
F
a
d
e
l
e
,
M
.
O
n
o
j
a
,
G
.
A
i
m
u
f
u
a
,
a
n
d
I
.
J.
M
a
z
a
d
u
,
“
Tr
e
n
d
s
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s
i
n
a
u
t
o
m
a
t
e
d
r
a
n
so
mw
a
r
e
d
e
t
e
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
S
o
c
i
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
1
7
–
4
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
7
3
6
/
j
c
s
i
.
4
9
3
2
.
2
0
2
2
.
[
6
]
R
.
B
r
e
w
e
r
,
“
R
a
n
s
o
mw
a
r
e
a
t
t
a
c
k
s
:
d
e
t
e
c
t
i
o
n
,
p
r
e
v
e
n
t
i
o
n
a
n
d
c
u
r
e
,
”
N
e
t
w
o
r
k
S
e
c
u
r
i
t
y
,
v
o
l
.
2
0
1
6
,
n
o
.
9
,
p
p
.
5
–
9
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
S
1
3
5
3
-
4
8
5
8
(
1
6
)
3
0
0
8
6
-
1.
[
7
]
A
.
H
.
C
e
l
d
r
á
n
,
P
.
M
.
S
.
S
á
n
c
h
e
z
,
M
.
A
.
C
a
s
t
i
l
l
o
,
G
.
B
o
v
e
t
,
G
.
M
.
P
é
r
e
z
,
a
n
d
B
.
S
t
i
l
l
e
r
,
“
I
n
t
e
l
l
i
g
e
n
t
a
n
d
b
e
h
a
v
i
o
r
a
l
-
b
a
s
e
d
d
e
t
e
c
t
i
o
n
o
f
mal
w
a
r
e
i
n
I
o
T
sp
e
c
t
r
u
m
se
n
s
o
r
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
r
m
a
t
i
o
n
S
e
c
u
ri
t
y
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
5
4
1
–
5
6
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
2
0
7
-
022
-
0
0
6
0
2
-
w.
[
8
]
S
.
H
.
K
o
k
,
A
.
A
b
d
u
l
l
a
h
,
N
.
Z.
Jh
a
n
j
h
i
,
a
n
d
M
.
S
u
p
r
a
m
a
n
i
a
m
,
“
R
a
n
s
o
mw
a
r
e
,
t
h
r
e
a
t
a
n
d
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
:
a
r
e
v
i
e
w
,
”
I
J
C
S
N
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
N
e
t
w
o
rk
S
e
c
u
ri
t
y
,
v
o
l
.
1
9
,
n
o
.
8
,
p
.
1
3
6
,
2
0
1
9
.
[
9
]
A
.
A
l
r
a
i
z
z
a
a
n
d
A
.
A
l
g
a
r
n
i
,
“
R
a
n
s
o
mw
a
r
e
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
:
a
s
u
r
v
e
y
,
”
Bi
g
D
a
t
a
a
n
d
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
,
n
o
.
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
b
d
c
c
7
0
3
0
1
4
3
.
[
1
0
]
P
.
O
’
K
a
n
e
,
S
.
S
e
z
e
r
,
a
n
d
D
.
C
a
r
l
i
n
,
“
Ev
o
l
u
t
i
o
n
o
f
r
a
n
so
mw
a
r
e
,
”
I
ET
N
e
t
w
o
rks
,
v
o
l
.
7
,
n
o
.
5
,
p
p
.
3
2
1
–
3
2
7
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
n
e
t
.
2
0
1
7
.
0
2
0
7
.
[
1
1
]
S
.
K
.
S
h
a
u
k
a
t
a
n
d
V
.
J.
R
i
b
e
i
r
o
,
“
R
a
n
so
m
W
a
l
l
:
a
l
a
y
e
r
e
d
d
e
f
e
n
se
sy
s
t
e
m
a
g
a
i
n
s
t
c
r
y
p
t
o
g
r
a
p
h
i
c
r
a
n
s
o
mw
a
r
e
a
t
t
a
c
k
s
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
2
0
1
8
1
0
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
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s
a
n
d
N
e
t
w
o
rks,
C
O
M
S
N
ETS
2
0
1
8
,
v
o
l
.
2
0
1
8
-
Jan
u
a
r
y
,
p
p
.
3
5
6
–
3
6
3
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
M
S
N
ETS.
2
0
1
8
.
8
3
2
8
2
1
9
.
[
1
2
]
H
.
S
.
T
a
l
a
b
a
n
i
a
n
d
H
.
M
.
T
.
A
b
d
u
l
h
a
d
i
,
“
B
i
t
c
o
i
n
r
a
n
so
mw
a
r
e
d
e
t
e
c
t
i
o
n
e
mp
l
o
y
i
n
g
r
u
l
e
-
b
a
se
d
a
l
g
o
r
i
t
h
ms
,
”
S
c
i
e
n
c
e
J
o
u
r
n
a
l
o
f
U
n
i
v
e
rsi
t
y
o
f
Z
a
k
h
o
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
5
–
1
0
,
2
0
2
2
,
d
o
i
:
1
0
.
2
5
2
7
1
/
s
j
u
o
z
.
2
0
2
2
.
1
0
.
1
.
8
6
5
.
[
1
3
]
I
.
B
e
l
l
o
e
t
a
l
.
,
“
D
e
t
e
c
t
i
n
g
r
a
n
s
o
mw
a
r
e
a
t
t
a
c
k
s
u
si
n
g
i
n
t
e
l
l
i
g
e
n
t
a
l
g
o
r
i
t
h
m
s:
r
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
a
n
d
n
e
x
t
d
i
r
e
c
t
i
o
n
f
r
o
m
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
b
i
g
d
a
t
a
p
e
r
sp
e
c
t
i
v
e
s
,
”
J
o
u
rn
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
z
e
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
,
n
o
.
9
,
p
p
.
8
6
9
9
–
8
7
1
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
6
5
2
-
0
2
0
-
0
2
6
3
0
-
7.
[
1
4
]
A
.
O
.
A
l
mas
h
h
a
d
a
n
i
,
M
.
K
a
i
i
a
l
i
,
S
.
S
e
z
e
r
,
a
n
d
P
.
O
’
K
a
n
e
,
“
A
mu
l
t
i
-
c
l
a
s
si
f
i
e
r
n
e
t
w
o
r
k
-
b
a
se
d
c
r
y
p
t
o
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
s
y
st
e
m:
a
c
a
se
s
t
u
d
y
o
f
l
o
c
k
y
r
a
n
s
o
mw
a
r
e
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
4
7
0
5
3
–
4
7
0
6
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
0
7
4
8
5
.
[
1
5
]
J.
H
w
a
n
g
,
J.
K
i
m,
S
.
Le
e
,
a
n
d
K
.
K
i
m,
“
Tw
o
-
st
a
g
e
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
y
n
a
mi
c
a
n
a
l
y
s
i
s
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
Wi
r
e
l
e
ss
Pe
rs
o
n
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
2
,
n
o
.
4
,
p
p
.
2
5
9
7
–
2
6
0
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
7
-
020
-
0
7
1
6
6
-
9.
[
1
6
]
O
.
M
a
k
i
n
d
e
,
A
.
S
a
n
g
o
d
o
y
i
n
,
B
.
M
o
h
a
mm
e
d
,
D
.
N
e
a
g
u
,
a
n
d
U
.
A
d
a
m
u
,
“
D
i
st
r
i
b
u
t
e
d
n
e
t
w
o
r
k
b
e
h
a
v
i
o
u
r
p
r
e
d
i
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
a
g
e
n
t
-
b
a
se
d
mi
c
r
o
s
i
m
u
l
a
t
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
-
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
F
u
t
u
re
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
a
n
d
C
l
o
u
d
,
Fi
C
l
o
u
d
2
0
1
9
,
p
p
.
1
8
2
–
188
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
F
i
C
l
o
u
d
.
2
0
1
9
.
0
0
0
3
3
.
[
1
7
]
M
.
P
a
q
u
e
t
-
C
l
o
u
s
t
o
n
,
B
.
H
a
sl
h
o
f
e
r
,
a
n
d
B
.
D
u
p
o
n
t
,
“
R
a
n
so
mw
a
r
e
p
a
y
m
e
n
t
s
i
n
t
h
e
B
i
t
c
o
i
n
e
c
o
s
y
st
e
m,
”
J
o
u
rn
a
l
o
f
C
y
b
e
rse
c
u
r
i
t
y
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
1
–
1
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
9
3
/
c
y
b
s
e
c
/
t
y
z
0
0
3
.
[
1
8
]
J.
M
o
d
i
,
“
D
e
t
e
c
t
i
n
g
r
a
n
s
o
mw
a
r
e
i
n
e
n
c
r
y
p
t
e
d
n
e
t
w
o
r
k
t
r
a
f
f
i
c
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
U
n
i
v
e
r
si
t
y
o
f
V
i
c
t
o
r
i
a
,
S
a
a
n
i
c
h
,
2
0
1
9
.
[
1
9
]
M
.
A
m
e
e
r
,
“
A
n
d
r
o
i
d
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
u
si
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
t
o
m
i
t
i
g
a
t
e
a
d
v
e
r
sari
a
l
e
v
a
s
i
o
n
a
t
t
a
c
k
s,
”
C
a
p
i
t
a
l
U
n
i
v
e
r
si
t
a
s S
a
i
n
s
d
a
n
Te
k
n
o
l
o
g
i
,
2
0
1
9
.
[
2
0
]
B
.
M
.
K
h
a
mm
a
s
,
“
R
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
r
a
n
d
o
m f
o
r
e
st
t
e
c
h
n
i
q
u
e
,
”
I
C
T
Ex
p
r
e
ss
,
v
o
l
.
6
,
2
0
2
0
.
[
2
1
]
U
.
A
d
a
m
u
a
n
d
I
.
A
w
a
n
,
“
R
a
n
so
mw
a
r
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
i
n
2
0
1
9
7
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
Fu
t
u
r
e
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
a
n
d
C
l
o
u
d
(
Fi
C
l
o
u
d
)
,
A
u
g
.
2
0
1
9
,
p
p
.
5
7
–
6
3
,
d
o
i
:
1
0
.
1
1
0
9
/
F
i
C
l
o
u
d
.
2
0
1
9
.
0
0
0
1
6
.
[
2
2
]
Y.
-
L.
W
a
n
,
J.
-
C
.
C
h
a
n
g
,
R
.
-
J
.
C
h
e
n
,
a
n
d
S
.
-
J.
W
a
n
g
,
“
F
e
a
t
u
r
e
-
se
l
e
c
t
i
o
n
-
b
a
s
e
d
r
a
n
s
o
mw
a
r
e
d
e
t
e
c
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
o
f
d
a
t
a
a
n
a
l
y
si
s
,
”
i
n
2
0
1
8
3
r
d
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
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s
(
I
C
C
C
S
)
,
A
p
r
.
2
0
1
8
,
p
p
.
8
5
–
8
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
O
M
S
.
2
0
1
8
.
8
4
6
3
3
0
0
.
[
2
3
]
A
.
A
l
z
a
h
r
a
n
i
e
t
a
l
.
,
“
R
a
n
D
r
o
i
d
:
s
t
r
u
c
t
u
r
a
l
s
i
mi
l
a
r
i
t
y
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
r
a
n
s
o
mw
a
r
e
a
p
p
l
i
c
a
t
i
o
n
s i
n
a
n
d
r
o
i
d
p
l
a
t
f
o
r
m,
”
i
n
2
0
1
8
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
r
o
/
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
EI
T
)
,
M
a
y
2
0
1
8
,
v
o
l
.
2
0
1
8
-
M
a
y
,
p
p
.
0
8
9
2
–
0
8
9
7
,
d
o
i
:
1
0
.
1
1
0
9
/
EI
T.
2
0
1
8
.
8
5
0
0
1
6
1
.
[
2
4
]
N
.
S
c
a
i
f
e
,
H
.
C
a
r
t
e
r
,
P
.
Tr
a
y
n
o
r
,
a
n
d
K
.
R
.
B
.
B
u
t
l
e
r
,
“
C
r
y
p
t
o
L
o
c
k
(
a
n
d
D
r
o
p
I
t
)
:
st
o
p
p
i
n
g
r
a
n
s
o
mw
a
r
e
a
t
t
a
c
k
s
o
n
u
ser
d
a
t
a
,
”
i
n
2
0
1
6
I
EEE
3
6
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
D
i
s
t
ri
b
u
t
e
d
C
o
m
p
u
t
i
n
g
S
y
st
e
m
s (I
C
D
C
S
)
,
J
u
n
.
2
0
1
6
,
v
o
l
.
2
0
1
6
-
A
u
g
u
s
,
p
p
.
3
0
3
–
3
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
C
S
.
2
0
1
6
.
4
6
.
[
2
5
]
D
.
S
g
a
n
d
u
r
r
a
,
L
.
M
u
ñ
o
z
-
G
o
n
z
á
l
e
z
,
R
.
M
o
h
s
e
n
,
a
n
d
E
.
C
.
L
u
p
u
,
“
A
u
t
o
m
a
t
e
d
d
y
n
a
m
i
c
a
n
a
l
y
si
s
o
f
r
a
n
s
o
mw
a
r
e
:
b
e
n
e
f
i
t
s,
l
i
m
i
t
a
t
i
o
n
s
a
n
d
u
se
f
o
r
d
e
t
e
c
t
i
o
n
,
”
a
rX
i
v
,
2
0
1
6
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
1
6
0
9
.
0
3
0
2
0
.
[
2
6
]
A
.
Za
h
r
a
a
n
d
M
.
A
.
S
h
a
h
,
“
I
o
T
b
a
se
d
r
a
n
s
o
mw
a
r
e
g
r
o
w
t
h
r
a
t
e
e
v
a
l
u
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
u
si
n
g
c
o
mm
a
n
d
a
n
d
c
o
n
t
r
o
l
b
l
a
c
k
l
i
st
i
n
g
,
”
I
C
AC
2
0
1
7
-
2
0
1
7
2
3
r
d
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
u
t
o
m
a
t
i
o
n
a
n
d
C
o
m
p
u
t
i
n
g
:
A
d
d
ress
i
n
g
G
l
o
b
a
l
C
h
a
l
l
e
n
g
e
s
t
h
r
o
u
g
h
Au
t
o
m
a
t
i
o
n
a
n
d
C
o
m
p
u
t
i
n
g
,
2
0
1
7
,
d
o
i
:
1
0
.
2
3
9
1
9
/
I
C
o
n
A
C
.
2
0
1
7
.
8
0
8
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
0
8
5
-
1
0
9
4
1094
[
27
]
L.
G
h
o
u
t
i
a
n
d
M
.
I
mam,
“
M
a
l
w
a
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
c
o
m
p
a
c
t
i
m
a
g
e
f
e
a
t
u
r
e
s
a
n
d
m
u
l
t
i
c
l
a
ss
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s,
”
I
ET I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
4
1
9
–
4
2
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
i
f
s.2
0
1
9
.
0
1
8
9
.
[2
8
]
E.
Th
a
k
r
a
n
a
n
d
A
.
K
u
m
a
r
i
,
“
I
mp
a
c
t
o
f
‘
R
a
n
s
o
mw
a
r
e
’
o
n
c
r
i
t
i
c
a
l
i
n
f
r
a
st
r
u
c
t
u
r
e
d
u
e
t
o
p
a
n
d
e
m
i
c
,
”
S
S
R
N
El
e
c
t
r
o
n
i
c
J
o
u
r
n
a
l
,
2
0
2
3
,
d
o
i
:
1
0
.
2
1
3
9
/
s
sr
n
.
4
3
6
1
1
1
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
G
o
te
ti
Ba
d
r
in
a
th
h
e
re
c
e
iv
e
d
h
is
first
M
a
ste
r
’
s
d
e
g
re
e
in
P
u
re
M
a
th
e
m
a
ti
c
s
fro
m
Na
g
a
rju
n
a
Un
iv
e
rsity
,
I
n
d
ia,
in
1
9
8
6
.
In
2
0
0
8
,
h
e
e
a
rn
e
d
a
M
a
ste
r
’
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
fr
o
m
An
d
h
ra
Un
i
v
e
rsity
,
In
d
ia.
He
se
rv
e
d
i
n
t
h
e
M
i
n
istr
y
o
f
El
e
c
tro
n
ics
a
n
d
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
G
o
v
e
rn
m
e
n
t
o
f
In
d
ia,
in
v
a
rio
u
s c
a
p
a
c
it
ies
fo
r
n
e
a
rly
3
0
y
e
a
rs
a
n
d
re
ti
re
d
a
s
S
c
ien
ti
st
-
F
.
C
u
rre
n
tl
y
,
h
e
is
p
u
rsu
in
g
h
is
P
h
.
D.
u
n
d
e
r
th
e
g
u
id
a
n
c
e
o
f
Dr.
Arp
it
a
G
u
p
ta,
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
n
d
HO
D,
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
KL
De
e
m
e
d
to
b
e
Un
iv
e
rsity
,
Ko
n
e
r
u
Lak
sh
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
a
ti
o
n
,
In
d
ia.
His res
e
a
rc
h
in
tere
sts in
c
l
u
d
e
c
y
b
e
rse
c
u
rit
y
,
d
e
e
p
lea
rn
in
g
,
a
n
d
g
e
n
e
ra
ti
v
e
AI.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
a
d
rin
a
t
h
.
g
o
te
ti
@g
m
a
il
.
c
o
m
.
Dr
.
Ar
p
ita
G
u
p
ta
s
h
e
re
c
e
iv
e
d
h
e
r
P
h
.
D
.
fr
o
m
Na
ti
o
n
a
l
In
st
it
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ti
ru
c
h
irap
a
ll
i,
In
d
ia i
n
Tran
sfe
r
L
e
a
rn
in
g
.
S
h
e
is wo
rk
i
n
g
a
s a
n
As
so
c
iate
P
ro
fe
rss
o
r
a
n
d
HO
D
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
.
,
K.L
De
e
m
e
d
to
b
e
Un
iv
e
rsit
y
,
Ko
n
e
ru
Lak
s
h
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
a
ti
o
n
H
y
d
e
ra
b
a
d
,
I
n
d
ia.
He
r
re
se
a
c
h
wo
r
k
s
h
a
v
e
b
e
e
n
p
u
b
lsih
e
d
in
n
u
m
e
ro
u
s
p
e
e
r
re
v
iew
e
d
jo
u
rn
a
ls.
S
h
e
a
lso
h
a
s
b
e
e
n
a
n
a
c
ti
v
e
re
v
iew
e
r
fo
r
m
a
n
y
p
e
e
r
re
v
iew
e
d
jo
u
rn
a
ls.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
rp
it
a
g
u
p
ta2
9
9
3
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.