I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
2
2
7
1
~
2
2
8
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
2
2
7
1
-
2
2
8
1
2271
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Adv
a
ncing
net
wo
rk securi
ty: a co
mpa
ra
tive resea
r
ch of
ma
chine learning
techniqu
es for
int
rusio
n det
e
ction
Sh
y
ng
g
y
s
Ry
s
bek
o
v
1
,
Aby
la
y
Ait
ba
no
v
1
,
Z
uk
hra
Abdi
a
kh
m
et
o
v
a
2
,
Am
a
nd
y
k
K
a
r
t
ba
y
ev
1
1
S
c
h
o
o
l
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
K
a
z
a
k
h
-
B
r
i
t
i
s
h
Te
c
h
n
i
c
a
l
U
n
i
v
e
r
si
t
y
,
A
l
m
a
t
y
,
K
a
z
a
k
h
s
t
a
n
2
I
n
f
o
r
mat
i
c
s
D
e
p
a
r
t
me
n
t
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
A
l
-
F
a
r
a
b
i
K
a
z
a
k
h
N
a
t
i
o
n
a
l
U
n
i
v
e
r
s
i
t
y
,
A
l
ma
t
y
,
K
a
z
a
k
h
s
t
a
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
1
,
2
0
2
4
R
ev
is
ed
No
v
5
,
2
0
2
4
Acc
ep
ted
No
v
2
0
,
2
0
2
4
In
th
e
c
u
rre
n
t
d
ig
i
tal
e
ra
,
th
e
a
d
v
a
n
c
e
m
e
n
t
o
f
n
e
two
rk
-
b
a
se
d
tec
h
n
o
lo
g
ies
h
a
s
b
ro
u
g
h
t
a
su
rg
e
in
se
c
u
rit
y
v
u
l
n
e
ra
b
il
it
ies
,
n
e
c
e
ss
it
a
ti
n
g
c
o
m
p
lex
a
n
d
d
y
n
a
m
ic
d
e
fe
n
se
m
e
c
h
a
n
ism
s.
Th
is
p
a
p
e
r
e
x
p
lo
re
s
t
h
e
in
te
g
ra
ti
o
n
o
f
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s
wi
th
in
in
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
s
(IDS)
to
tac
k
le
th
e
in
tri
c
a
c
ies
o
f
m
o
d
e
rn
n
e
two
r
k
th
re
a
ts.
A
d
e
tailed
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
o
f
v
a
rio
u
s
a
lg
o
rit
h
m
s,
in
c
l
u
d
i
n
g
k
-
n
e
a
re
st
n
e
i
g
h
b
o
rs
(KN
N)
,
lo
g
isti
c
re
g
re
ss
io
n
,
a
n
d
p
e
rc
e
p
tro
n
n
e
u
ra
l
n
e
two
r
k
s,
is
c
o
n
d
u
c
te
d
t
o
e
v
a
lu
a
te
th
e
i
r
e
fficie
n
c
y
i
n
d
e
tec
ti
n
g
a
n
d
c
las
sify
in
g
d
iffere
n
t
t
y
p
e
s
o
f
n
e
two
rk
in
tru
si
o
n
s
su
c
h
a
s
d
e
n
ial
o
f
se
rv
ice
(Do
S
),
p
r
o
b
e
,
u
se
r
to
ro
o
t
(
U2
R),
a
n
d
re
m
o
te
to
lo
c
a
l
(R2
L).
Util
izi
n
g
t
h
e
n
a
ti
o
n
a
l
so
ftwa
re
lab
o
ra
to
ry
k
n
o
wle
d
g
e
d
isc
o
v
e
ry
a
n
d
d
a
ta
m
in
i
n
g
(NSL
-
KD
D)
d
a
tas
e
t,
a
sta
n
d
a
rd
in
th
e
field
,
th
e
stu
d
y
e
x
a
m
in
e
s
th
e
a
l
g
o
ri
th
m
s’
a
b
il
it
y
to
id
e
n
ti
f
y
c
o
m
p
lex
p
a
tt
e
rn
s
a
n
d
a
n
o
m
a
li
e
s
in
d
ica
ti
v
e
o
f
se
c
u
rit
y
b
re
a
c
h
e
s.
P
rin
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
is
u
ti
li
z
e
d
t
o
stre
a
m
li
n
e
t
h
e
d
a
tas
e
t
in
to
2
0
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
s
fo
r
d
a
t
a
p
ro
c
e
ss
in
g
e
fficie
n
c
y
.
Re
su
l
ts
in
d
ica
te
th
a
t
th
e
n
e
u
ra
l
n
e
two
rk
m
o
d
e
l
is
p
a
rti
c
u
larly
e
ffe
c
ti
v
e
,
d
e
m
o
n
stra
ti
n
g
e
x
c
e
p
ti
o
n
a
l
p
e
rf
o
rm
a
n
c
e
m
e
tri
c
s
a
c
ro
ss
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
a
n
d
re
c
a
ll
in
b
o
t
h
trai
n
in
g
a
n
d
tes
ti
n
g
p
h
a
se
s,
a
ffir
m
in
g
it
s
re
li
a
b
il
i
ty
a
n
d
u
ti
li
t
y
in
IDS.
Th
e
p
o
ten
ti
a
l
f
o
r
h
y
b
rid
m
o
d
e
ls
c
o
m
b
in
i
n
g
d
iffere
n
t
m
a
c
h
in
e
lea
rn
in
g
(M
L)
stra
teg
ies
is
a
lso
d
isc
u
ss
e
d
,
h
ig
h
li
g
h
ti
n
g
a
p
a
th
t
o
wa
rd
s m
o
re
r
o
b
u
st an
d
a
d
a
p
tab
le IDS
s
o
lu
t
io
n
s.
K
ey
w
o
r
d
s
:
An
o
m
aly
d
etec
tio
n
Hy
b
r
id
m
o
d
el
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
Ma
ch
in
e
lear
n
in
g
Netwo
r
k
s
ec
u
r
ity
Neu
r
al
n
etwo
r
k
s
Ov
er
s
am
p
lin
g
m
eth
o
d
s
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
:
Am
an
d
y
k
Ka
r
tb
ay
ev
Sch
o
o
l o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
an
d
E
n
g
in
ee
r
in
g
,
Kaz
ak
h
-
B
r
itis
h
T
ec
h
n
ical
Un
iv
er
s
ity
T
o
le
B
i 5
9
,
Alm
aty
,
Kaz
ak
h
s
tan
E
m
ail: a
.
k
ar
tb
ay
e
v
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
e
n
t
y
ea
r
s
,
th
e
r
ap
id
ex
p
an
s
io
n
o
f
i
n
ter
n
et
o
f
t
h
in
g
s
(
I
o
T
)
tech
n
o
lo
g
ies
h
av
e
s
ig
n
if
ican
tly
in
cr
ea
s
ed
b
o
th
th
e
n
u
m
b
e
r
o
f
i
n
ter
n
et
u
s
er
s
an
d
th
e
v
a
r
iety
o
f
ap
p
licatio
n
s
,
co
n
s
eq
u
en
tly
h
eig
h
ten
in
g
n
etwo
r
k
co
n
n
ec
tiv
ity
.
T
h
is
d
ev
elo
p
m
en
t,
h
o
wev
e
r
,
h
as
in
tr
o
d
u
ce
d
n
u
m
e
r
o
u
s
s
ec
u
r
ity
v
u
ln
e
r
a
b
ilit
ies.
T
r
ad
itio
n
al
s
ec
u
r
ity
m
ea
s
u
r
es
lik
e
f
ir
ewa
lls
,
d
ata
en
cr
y
p
tio
n
,
an
d
u
s
er
au
th
en
ticatio
n
h
av
e
b
ee
n
d
ep
l
o
y
ed
t
o
co
u
n
ter
ac
t
th
ese
th
r
ea
ts
.
Alth
o
u
g
h
ef
f
ec
t
iv
e
ag
ain
s
t
m
a
n
y
ty
p
es
o
f
att
ac
k
s
,
th
ese
co
n
v
en
tio
n
al
m
et
h
o
d
s
o
f
ten
lac
k
th
e
ca
p
ac
ity
f
o
r
in
-
d
ep
th
p
ac
k
et
an
aly
s
is
,
leav
in
g
th
em
v
u
ln
er
ab
le
to
m
o
r
e
co
m
p
lex
attac
k
s
.
T
o
ad
d
r
ess
th
ese
lim
itatio
n
s
,
in
tr
u
s
io
n
p
r
e
v
e
n
tio
n
s
y
s
tem
s
(
I
PS
)
an
d
i
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
(
I
DS)
h
av
e
b
ee
n
im
p
lem
en
ted
.
T
h
ese
s
y
s
tem
s
,
u
tili
zin
g
s
o
p
h
is
ticated
alg
o
r
ith
m
s
f
r
o
m
m
ac
h
in
e
lear
n
i
n
g
,
d
ee
p
lear
n
in
g
,
a
n
d
ar
tific
ial
in
tellig
en
ce
,
p
r
o
v
id
e
a
d
ee
p
er
d
ata
an
aly
s
is
to
im
p
r
o
v
e
attac
k
d
etec
tio
n
.
W
h
ile
I
PS
u
n
its
co
m
b
in
e
d
etec
tio
n
an
d
p
r
ev
e
n
tio
n
f
u
n
ct
io
n
alities
,
I
DS u
n
its
f
o
cu
s
p
r
i
m
ar
ily
o
n
d
etec
tio
n
a
n
d
tr
af
f
ic
an
aly
s
is
.
T
h
e
s
u
r
g
e
in
in
ter
n
et
co
n
n
ec
tiv
ity
an
d
d
ata
tr
an
s
f
er
r
ates
h
as
also
led
to
an
in
cr
ea
s
e
i
n
n
etwo
r
k
an
o
m
alies
an
d
a
co
r
r
esp
o
n
d
in
g
r
is
e
in
cy
b
er
-
attac
k
s
.
Acc
o
r
d
in
g
to
a
r
ec
en
t
v
u
ln
er
a
b
ilit
y
an
d
th
r
ea
t
r
ep
o
r
t
b
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
7
1
-
2
2
8
1
2272
Sk
y
b
o
x
Secu
r
ity
,
th
er
e
wer
e
1
7
th
o
u
s
an
d
n
ew
v
u
ln
er
ab
ilit
i
es
r
ec
o
r
d
ed
in
2
0
1
9
,
r
ef
lectin
g
a
3
.
8
%
in
cr
ea
s
e
f
r
o
m
th
e
p
r
ev
i
o
u
s
y
ea
r
.
I
n
r
esp
o
n
s
e
to
th
ese
g
r
o
win
g
t
h
r
ea
ts
,
b
o
th
th
e
p
u
b
lic
an
d
p
r
iv
ate
s
ec
to
r
s
ar
e
s
ig
n
if
ican
tly
in
cr
ea
s
in
g
th
eir
i
n
v
estme
n
t
in
cy
b
e
r
s
ec
u
r
ity
te
ch
n
o
lo
g
ies.
A
r
ep
o
r
t
b
y
C
r
y
s
tal
Ma
r
k
et
R
esear
ch
in
d
icate
s
th
at
th
e
cy
b
er
s
ec
u
r
i
ty
m
ar
k
et,
wh
ich
was
v
alu
e
d
at
ap
p
r
o
x
im
ately
USD
5
8
b
illi
o
n
in
2
0
1
2
,
is
ex
p
ec
ted
to
s
o
ar
to
USD
1
7
3
b
illi
o
n
b
y
2
0
2
2
.
As
in
ter
n
et
u
s
ag
e
co
n
tin
u
es
to
clim
b
,
cy
b
e
r
s
ec
u
r
ity
f
ir
m
s
ar
e
ch
allen
g
ed
t
o
d
e
v
elo
p
m
o
r
e
s
o
p
h
is
ticated
tech
n
o
lo
g
ies
an
d
m
eth
o
d
s
b
ey
o
n
d
tr
ad
itio
n
al
s
ec
u
r
ity
m
ea
s
u
r
es.
T
h
is
in
n
o
v
atio
n
h
as
led
to
th
e
ad
v
en
t
o
f
p
r
o
ac
tiv
e
s
ec
u
r
ity
tech
n
o
lo
g
ies
s
u
ch
as
n
etwo
r
k
b
eh
av
i
o
r
an
al
y
s
is
,
m
ac
h
in
e
lear
n
in
g
,
an
d
th
r
ea
t
i
n
tellig
en
ce
,
with
I
DS
s
y
s
tem
s
in
cr
ea
s
in
g
ly
ce
n
tr
al
to
en
h
an
cin
g
r
esp
o
n
s
iv
en
ess
to
cy
b
er
t
h
r
ea
ts
.
R
ec
en
t
r
esear
ch
h
as
f
o
cu
s
ed
o
n
th
e
a
p
p
licatio
n
o
f
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
al
g
o
r
ith
m
s
f
o
r
a
n
o
m
aly
d
etec
tio
n
in
n
etwo
r
k
s
ec
u
r
ity
[
1
]
.
T
h
ese
alg
o
r
ith
m
s
,
tr
ain
e
d
o
n
ex
te
n
s
iv
e
d
atasets
,
ar
e
ev
alu
ated
f
o
r
th
eir
ab
ilit
y
to
id
e
n
tify
p
o
ten
tial
attac
k
s
.
His
to
r
ical
s
tu
d
ies
h
av
e
p
r
e
d
o
m
in
a
n
tly
ex
a
m
in
ed
alg
o
r
ith
m
s
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M)
an
d
ar
tific
ial
n
e
u
r
al
n
etw
o
r
k
(
ANN)
f
o
r
th
ei
r
ef
f
icien
c
y
in
h
a
n
d
lin
g
la
r
g
e
d
atasets
f
o
r
n
etwo
r
k
i
n
tr
u
s
io
n
d
etec
tio
n
[
2
]
.
Am
o
n
g
th
e
v
ar
io
u
s
s
ec
u
r
ity
te
ch
n
o
lo
g
ies
av
ailab
le,
I
DS
s
tan
d
s
o
u
t
as
a
d
y
n
am
ic
a
n
d
r
o
b
u
s
t
s
o
lu
tio
n
s
p
ec
if
ically
d
esig
n
ed
to
d
etec
t
p
ar
ticu
lar
n
etwo
r
k
th
r
ea
ts
.
An
I
DS
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
s
n
etwo
r
k
ac
tiv
ities
,
s
cr
u
tin
izin
g
th
em
f
o
r
an
y
d
ev
iatio
n
s
f
r
o
m
s
tan
d
ar
d
o
p
e
r
atio
n
s
o
r
ab
n
o
r
m
alities
.
I
DS
u
tili
ze
two
m
ain
d
etec
tio
n
m
eth
o
d
o
lo
g
ies:
s
ig
n
atu
r
e
-
b
ased
a
n
d
r
u
le
-
b
ased
(
an
o
m
aly
-
b
ased
)
.
Sig
n
atu
r
e
-
b
ased
I
DS
s
y
s
tem
s
wo
r
k
b
y
co
m
p
ar
in
g
n
etwo
r
k
d
ata
to
k
n
o
wn
p
atter
n
s
o
f
attac
k
s
s
to
r
ed
in
d
atab
ases
,
tr
ig
g
er
in
g
aler
ts
wh
en
m
atch
es
ar
e
f
o
u
n
d
[
3
]
.
T
h
e
m
ain
lim
itatio
n
o
f
th
is
ap
p
r
o
ac
h
is
its
f
ailu
r
e
to
i
d
en
tify
n
ew
,
u
n
k
n
o
wn
th
r
ea
ts
,
wh
er
ea
s
r
u
le
-
b
ased
I
DS
s
y
s
tem
s
,
u
s
in
g
an
o
m
alies,
cr
ea
te
a
b
aselin
e
o
f
ty
p
ical
n
etwo
r
k
ac
tiv
ity
an
d
d
etec
t
an
o
m
alies,
en
ab
lin
g
th
em
to
i
d
en
tify
n
o
v
el
attac
k
s
th
r
o
u
g
h
ad
ap
tiv
e
ca
p
ab
ilit
ies
[
4
]
,
[
5
]
.
As a
s
o
f
twar
e
to
o
l,
it
is
ad
ep
t
at
id
en
tify
in
g
s
u
s
p
icio
u
s
b
eh
av
io
r
s
an
d
p
o
licy
v
io
l
atio
n
s
with
in
a
n
etwo
r
k
.
I
DS
ca
n
b
e
class
if
ied
in
to
s
ev
er
al
ty
p
es:
n
etwo
r
k
,
h
o
s
t,
p
r
o
t
o
co
l
-
b
ased
,
ap
p
licatio
n
p
r
o
to
co
l
-
b
ased
,
an
d
h
y
b
r
id
I
DS
[
6
]
,
[
7
]
.
T
h
e
p
r
im
ar
y
d
etec
tio
n
s
tr
ateg
ies
em
p
lo
y
ed
b
y
I
DS
ar
e
m
is
u
s
e
d
etec
tio
n
(
s
ig
n
atu
r
e
-
b
ased
)
an
d
an
o
m
aly
d
etec
tio
n
[
8
]
.
T
h
e
lan
d
s
ca
p
e
o
f
n
etwo
r
k
s
e
cu
r
ity
r
esear
ch
h
as
b
ee
n
s
ig
n
if
ican
tly
s
h
ap
ed
b
y
s
tu
d
ies
th
at
em
p
lo
y
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
t
o
en
h
an
ce
I
DS
ca
p
ab
ilit
ies.
No
tab
ly
,
r
esear
ch
r
ef
e
r
en
ce
d
in
[
9
]
em
p
lo
y
ed
n
aiv
e
B
ay
es,
r
an
d
o
m
f
o
r
est
,
an
d
S
VM
to
id
en
tif
y
th
e
ty
p
es
o
f
attac
k
s
s
u
ch
as
d
en
ial
o
f
s
er
v
ice
.
T
h
is
s
tu
d
y
h
ig
h
lig
h
ted
th
e
s
u
p
er
i
o
r
e
f
f
ic
ac
y
o
f
th
e
r
a
n
d
o
m
f
o
r
est
class
if
ier
an
d
s
u
g
g
ested
th
at
i
n
teg
r
atin
g
h
ier
ar
c
h
ical
clu
s
ter
in
g
co
u
ld
f
u
r
t
h
er
im
p
r
o
v
e
p
e
r
f
o
r
m
an
ce
.
C
o
n
c
u
r
r
e
n
tly
,
an
o
t
h
er
in
v
esti
g
atio
n
in
[
1
0
]
u
n
d
er
to
o
k
a
co
m
p
ar
ativ
e
an
aly
s
is
o
f
s
u
p
e
r
v
is
ed
ML
class
if
ier
s
in
clu
d
i
n
g
r
an
d
o
m
f
o
r
est
,
SVM,
g
a
u
s
s
ian
n
aiv
e
B
ay
es,
a
n
d
lo
g
is
tic
r
eg
r
ess
io
n
,
f
o
cu
s
in
g
o
n
k
ey
p
er
f
o
r
m
a
n
ce
m
et
r
ics
as
th
e
F1
-
Sco
r
e
an
d
ac
cu
r
ac
y
.
T
h
is
an
aly
s
is
r
ea
f
f
ir
m
ed
th
e
d
o
m
in
an
ce
o
f
th
e
r
an
d
o
m
f
o
r
est
class
if
ier
a
cr
o
s
s
v
ar
io
u
s
d
atasets
an
d
p
ar
am
eter
s
.
A
n
o
tab
le
ap
p
r
o
ac
h
in
[
1
1
]
em
p
h
asized
t
h
e
im
p
o
r
tan
ce
o
f
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
f
o
r
a
lig
h
tweig
h
t
I
DS,
ad
v
o
ca
tin
g
f
o
r
th
e
elim
in
atio
n
o
f
r
ed
u
n
d
an
t
d
ata
to
en
s
u
r
e
th
e
r
eliab
ilit
y
an
d
ac
cu
r
ac
y
o
f
ML
alg
o
r
ith
m
s
.
Similar
ly
,
th
e
r
esear
ch
in
[
1
2
]
in
tr
o
d
u
ce
d
a
s
u
p
er
v
is
ed
ML
-
b
ased
I
DS
to
ca
te
g
o
r
i
ze
o
n
lin
e
n
etwo
r
k
d
ata
as
n
o
r
m
al
o
r
a
n
o
m
alo
u
s
,
alth
o
u
g
h
it wa
s
r
estricte
d
to
d
etec
tin
g
o
n
ly
d
en
ial
o
f
s
er
v
ice
(
Do
S)
an
d
p
r
o
b
e
attac
k
s
.
No
tab
le
in
n
o
v
atio
n
s
in
t
h
e
f
i
eld
wer
e
d
is
cu
s
s
ed
in
[
1
3
]
,
wh
er
e
a
f
ea
t
u
r
e
r
e
m
o
v
al
tec
h
n
iq
u
e
was
ap
p
lied
with
in
an
SVM
-
b
ase
d
in
tr
u
s
io
n
d
etec
tio
n
m
eth
o
d
,
s
elec
tin
g
th
e
to
p
n
in
etee
n
f
ea
tu
r
es
f
r
o
m
th
e
k
n
o
wled
g
e
d
is
co
v
er
y
an
d
d
a
ta
m
in
in
g
cu
p
1
9
9
9
(
KDD
-
C
UP9
9
)
d
ataset
to
b
o
o
s
t
al
g
o
r
ith
m
e
f
f
icien
cy
.
Ad
d
itio
n
al
s
tu
d
ies,
s
u
ch
as
s
tu
d
y
[
1
4
]
,
ex
p
lo
r
ed
a
n
en
h
a
n
c
ed
s
elf
-
ad
ap
tiv
e
B
ay
esian
a
lg
o
r
ith
m
f
o
r
an
o
m
aly
d
etec
tio
n
,
ca
p
ab
le
o
f
p
r
o
ce
s
s
in
g
lar
g
e
d
atasets
ef
f
ec
tiv
ely
.
Me
an
wh
ile,
s
tu
d
y
[
1
5
]
p
r
esen
ted
an
in
n
o
v
ativ
e
tr
ian
g
le
-
b
ased
k
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN)
m
eth
o
d
aim
e
d
at
r
ed
u
cin
g
d
ata
d
im
en
s
io
n
al
ity
,
an
d
s
tu
d
y
[
1
6
]
test
ed
an
I
DS
em
p
lo
y
i
n
g
f
u
zz
y
lo
g
ic
to
d
er
iv
e
f
u
zz
y
r
u
les
f
r
o
m
d
ef
i
n
ite
r
u
les
u
s
in
g
f
r
eq
u
e
n
t
item
s
,
ac
h
iev
in
g
o
v
er
9
0
%
class
if
icatio
n
ac
cu
r
ac
y
ac
r
o
s
s
all
attac
k
ty
p
es.
T
h
ese
ad
v
an
ce
m
en
ts
u
n
d
er
s
c
o
r
e
a
tr
en
d
to
war
d
m
o
r
e
p
r
ec
is
e
an
d
ef
f
icien
t
m
et
h
o
d
s
f
o
r
n
etwo
r
k
in
tr
u
s
io
n
d
et
ec
tio
n
.
Pan
ig
r
ah
i
et
a
l.
[
1
7
]
ass
ess
ed
f
o
u
r
s
u
p
er
v
is
ed
alg
o
r
ith
m
s
f
o
r
id
en
tif
y
in
g
attac
k
s
s
u
ch
as
a
p
r
o
b
e,
Do
S,
r
em
o
te
to
lo
ca
l
(
R
2
L
)
,
an
d
u
s
er
to
r
o
o
t
(
U2
R
)
.
T
h
ey
d
is
co
v
er
e
d
th
at
th
e
d
ec
i
s
io
n
tr
ee
class
if
ier
o
u
tp
er
f
o
r
m
ed
n
aiv
e
B
ay
es
in
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Similar
ly
,
th
e
r
esear
ch
in
[
1
8
]
co
m
p
a
r
ed
th
e
ef
f
icac
y
o
f
n
eu
r
al
n
etwo
r
k
s
,
an
d
d
ec
is
io
n
tr
ee
s
ac
r
o
s
s
f
alse
alar
m
r
ate,
ac
cu
r
ac
y
,
a
n
d
d
etec
tio
n
r
ate.
T
h
ey
r
ev
ea
le
d
th
at
th
e
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
s
u
r
p
ass
ed
its
co
u
n
ter
p
ar
ts
in
ef
f
icien
cy
.
Fu
r
th
er
ex
p
l
o
r
in
g
th
e
in
teg
r
ati
o
n
o
f
m
ac
h
in
e
lear
n
in
g
s
tr
ateg
ies,
Ak
ash
d
ee
p
et
a
l.
[
1
9
]
a
d
v
o
ca
ted
f
o
r
a
co
m
b
in
atio
n
o
f
SVMs,
m
u
ltiv
ar
iate
ad
ap
tiv
e
r
eg
r
ess
io
n
s
p
lin
es
(
MA
R
S),
an
d
ANNs
to
im
p
r
o
v
e
in
tr
u
s
io
n
d
etec
tio
n
ca
p
ab
ilit
ies.
A
n
o
v
el
h
y
b
r
id
ap
p
r
o
ac
h
u
s
in
g
SVM
an
d
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
was
p
r
o
p
o
s
ed
in
[
2
0
]
.
T
h
e
s
ig
n
if
ica
n
ce
o
f
f
ea
t
u
r
e
s
elec
tio
n
was
ad
d
r
ess
ed
in
[
2
1
]
,
wh
e
r
e
a
s
eq
u
e
n
tial
s
ea
r
ch
s
tr
ateg
y
was
em
p
lo
y
ed
to
ev
alu
ate
th
e
im
p
o
r
tan
ce
o
f
attr
ib
u
tes
b
y
th
ei
r
r
em
o
v
al,
en
h
a
n
cin
g
alg
o
r
ith
m
p
er
f
o
r
m
a
n
ce
b
y
elim
in
atin
g
n
o
n
-
ess
en
tial
f
ea
t
u
r
es.
B
u
ild
in
g
o
n
th
is
,
s
tu
d
y
[
2
2
]
u
n
d
e
r
s
co
r
ed
th
at
n
o
t
all
d
ataset
attr
ib
u
tes
ar
e
cr
u
cial,
h
ig
h
lig
h
tin
g
t
h
at
th
e
s
im
p
le
ca
r
t
alg
o
r
ith
m
y
ield
e
d
s
u
p
er
io
r
r
esu
lts
co
m
p
ar
ed
t
o
o
th
er
m
o
d
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
d
va
n
cin
g
n
etw
o
r
k
s
ec
u
r
ity:
a
co
mp
a
r
a
tive
r
esea
r
ch
o
f m
a
c
h
in
e
lea
r
n
in
g
…
(
S
h
y
n
g
g
ys R
y
s
b
ek
o
v
)
2273
I
n
th
e
co
n
tex
t
o
f
v
eh
ic
u
lar
ad
h
o
c
n
etwo
r
k
s
(
VANE
T
s
)
,
Me
n
g
et
a
l.
[
2
3
]
d
is
cu
s
s
es
th
e
u
s
e
o
f
SVM
o
p
tim
ized
with
th
r
ee
in
tellig
e
n
t
alg
o
r
ith
m
s
-
p
ar
ticle
s
war
m
o
p
tim
izatio
n
,
an
t
c
o
lo
n
y
o
p
ti
m
izatio
n
,
a
n
d
g
en
etic
alg
o
r
ith
m
,
with
latter
s
h
o
win
g
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
.
Fin
ally
,
Kwo
n
et
a
l.
[
2
4
]
ex
am
i
n
ed
th
e
s
ec
u
r
ity
o
f
I
o
T
n
etwo
r
k
s
th
r
o
u
g
h
q
u
ality
o
f
s
er
v
ice
in
d
icato
r
s
,
p
r
o
p
o
s
in
g
an
I
DS
s
y
s
tem
b
ased
o
n
class
if
icatio
n
u
s
in
g
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs).
T
h
is
ap
p
r
o
ac
h
was
s
u
b
s
tan
tially
b
etter
in
th
e
ac
cu
r
ac
y
o
f
d
etec
tin
g
Do
S a
ttack
s
wh
ile
r
ed
u
cin
g
f
a
ls
e
p
o
s
itiv
es,
m
ar
k
in
g
a
s
ig
n
if
i
ca
n
t a
d
v
an
ce
m
en
t in
th
e
f
ield
.
Ou
r
p
ap
er
aim
s
to
id
en
tify
t
h
e
m
o
s
t
ef
f
ec
tiv
e
ML
alg
o
r
i
th
m
f
o
r
an
o
m
aly
d
etec
tio
n
i
n
n
etwo
r
k
en
v
ir
o
n
m
en
ts
,
a
v
ital
ad
v
an
ce
m
en
t
f
o
r
n
etwo
r
k
s
ec
u
r
ity
s
o
lu
tio
n
s
.
I
t
co
n
d
u
cts
a
co
m
p
r
eh
en
s
iv
e
ev
alu
atio
n
o
f
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
u
s
in
g
th
e
n
atio
n
al
s
o
f
twar
e
lab
o
r
ato
r
y
k
n
o
wled
g
e
d
is
co
v
er
y
an
d
d
ata
m
in
in
g
(
NSL
-
KDD)
d
ataset
d
u
r
in
g
th
e
m
o
d
elin
g
p
h
ases
.
T
h
e
NSL
-
KDD
d
atase
t
[
2
5
]
,
an
im
p
r
o
v
e
d
v
er
s
io
n
o
f
th
e
ea
r
lier
KDD
-
C
UP9
9
d
atas
et
[
2
6
]
,
was
ch
o
s
en
d
u
e
to
its
m
o
r
e
ch
allen
g
in
g
s
et
o
f
d
ata
f
ea
tu
r
es,
m
ak
in
g
it
a
s
u
itab
le
ch
o
ice
f
o
r
r
i
g
o
r
o
u
s
test
in
g
o
f
in
tr
u
s
io
n
d
etec
tio
n
al
g
o
r
ith
m
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
ese
alg
o
r
ith
m
s
is
test
ed
ac
r
o
s
s
v
ar
io
u
s
ty
p
es
o
f
n
etwo
r
k
in
tr
u
s
io
n
s
,
p
r
o
v
id
in
g
a
d
etailed
co
m
p
ar
is
o
n
o
f
th
eir
ef
f
ec
tiv
en
ess
in
id
en
tify
in
g
d
if
f
er
e
n
t
th
r
ea
t
v
ec
to
r
s
.
T
h
er
ef
o
r
e,
t
h
e
g
o
al
o
f
th
is
s
tu
d
y
is
to
id
en
tif
y
th
e
b
est
alg
o
r
ith
m
f
o
r
d
ev
elo
p
in
g
m
o
r
e
e
f
f
icien
t
s
ec
u
r
ity
m
ec
h
an
is
m
s
f
o
r
n
etwo
r
k
p
r
o
tectio
n
.
T
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws:
Sectio
n
2
o
u
tlin
es
th
e
m
eth
o
d
o
lo
g
y
f
o
r
d
ata
an
aly
s
is
,
s
ec
tio
n
3
d
is
cu
s
s
es
th
e
s
tu
d
y
's
f
in
d
in
g
s
with
tab
les
an
d
illu
s
tr
atio
n
s
,
an
d
s
ec
tio
n
4
c
o
n
clu
d
es with
a
s
u
m
m
ar
y
o
f
k
ey
r
esu
lts
.
2.
M
E
T
H
O
D
2
.
1
.
O
v
er
v
iew
o
f
a
lg
o
rit
h
m
s
Ma
ch
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
ar
e
g
ettin
g
p
iv
o
tal
in
e
n
h
a
n
cin
g
c
y
b
er
s
ec
u
r
it
y
b
y
d
etec
tin
g
an
d
n
eu
tr
alizin
g
c
y
b
er
a
n
o
m
alie
s
.
An
o
m
aly
d
etec
tio
n
f
o
c
u
s
es
o
n
id
en
tify
in
g
d
ata
ele
m
en
ts
,
ev
en
ts
,
o
r
o
b
s
er
v
atio
n
s
th
at
d
ev
iate
s
ig
n
if
ican
tly
f
r
o
m
ex
p
ec
te
d
p
att
er
n
s
,
wh
ich
co
u
l
d
in
d
icate
p
o
ten
tial
th
r
ea
ts
o
r
m
alicio
u
s
ac
tiv
ity
.
Key
alg
o
r
ith
m
s
th
at
p
lay
a
c
r
u
cial
r
o
le
i
n
th
is
d
o
m
ain
in
clu
d
e:
−
K
-
m
ea
n
s
clu
s
ter
in
g
:
t
h
is
alg
o
r
ith
m
o
r
g
a
n
izes
d
ata
in
to
d
is
tin
ct
g
r
o
u
p
s
.
I
t
ef
f
ec
ti
v
ely
id
en
tifie
s
an
o
m
alies
b
y
is
o
latin
g
o
u
tlier
s
th
at
d
o
n
o
t
f
it
in
to
an
y
estab
lis
h
ed
clu
s
te
r
.
Du
r
in
g
clu
s
ter
in
g
,
ty
p
ical
d
ata
p
o
in
ts
f
o
r
m
co
h
esiv
e
g
r
o
u
p
s
,
wh
ile
a
n
o
m
alies,
wh
ich
d
if
f
er
s
ig
n
if
ican
tly
in
f
ea
tu
r
e
s
p
ac
e,
r
e
m
ain
u
n
-
clu
s
ter
ed
o
r
lo
o
s
ely
co
n
n
ec
te
d
to
clu
s
ter
s
.
T
h
is
ch
ar
ac
ter
is
tic
allo
ws
th
e
alg
o
r
ith
m
to
f
lag
p
o
te
n
tial
o
u
tlier
s
b
y
ass
es
s
in
g
th
eir
d
is
tan
ce
to
co
r
e
clu
s
ter
s
.
−
I
s
o
lated
f
o
r
ests
:
b
ased
o
n
a
c
o
llectio
n
o
f
d
ec
is
io
n
tr
ee
s
,
th
is
u
n
s
u
p
er
v
is
ed
al
g
o
r
ith
m
is
o
lates
an
o
m
alies
ef
f
icien
tly
b
y
q
u
ick
ly
s
eg
r
e
g
atin
g
aty
p
ical
d
ata
p
o
in
ts
.
B
y
co
n
s
tr
u
ctin
g
r
a
n
d
o
m
d
ec
is
io
n
tr
ee
s
th
at
p
ar
titi
o
n
d
ata
p
o
i
n
ts
b
ased
o
n
s
p
ec
if
ic
attr
ib
u
tes,
th
e
alg
o
r
ith
m
ca
n
s
wif
tly
id
en
tify
o
u
tlier
s
,
wh
ich
m
ak
es
th
is
m
eth
o
d
ef
f
ec
tiv
e
in
h
i
g
h
-
d
im
en
s
io
n
al
d
atasets
an
d
is
co
m
p
u
tatio
n
ally
ef
f
icien
t
.
−
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
:
a
s
a
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
iq
u
e
,
SVMs
class
if
y
d
ata
b
y
cr
e
atin
g
a
m
o
d
el
t
h
at
s
ep
ar
ates
d
ata
p
o
i
n
ts
u
s
in
g
a
h
y
p
er
p
lan
e.
T
h
is
m
et
h
o
d
is
p
ar
ticu
lar
ly
ef
f
ec
tiv
e
in
an
o
m
aly
d
etec
tio
n
b
ec
au
s
e
it id
en
tifie
s
d
ata
p
o
i
n
ts
th
at
ar
e
m
ar
k
ed
l
y
d
is
tan
t f
r
o
m
th
e
r
est o
f
th
e
d
ataset
.
−
Naiv
e
B
ay
es
:
clas
s
if
ier
s
co
m
p
r
is
e
a
g
r
o
u
p
o
f
class
if
icatio
n
m
eth
o
d
s
b
ased
o
n
B
ay
es'
th
eo
r
em
.
Usu
ally
,
th
is
co
llectio
n
in
clu
d
es
v
ar
io
u
s
alg
o
r
ith
m
s
th
at
o
p
er
ate
u
n
d
e
r
a
co
m
m
o
n
p
r
i
n
cip
le.
E
ac
h
m
eth
o
d
o
p
e
r
ates
u
n
d
er
th
e
ass
u
m
p
tio
n
th
at
th
e
o
cc
u
r
r
en
ce
o
f
a
s
p
ec
if
ic
f
e
atu
r
e
with
in
a
class
is
in
d
ep
en
d
en
t
o
f
o
th
er
f
ea
tu
r
es.
T
h
is
ass
u
m
p
tio
n
s
ig
n
if
ican
tly
s
im
p
lifie
s
th
e
ca
lcu
latio
n
o
f
p
r
o
b
a
b
ilit
ies,
f
ac
ilit
atin
g
m
o
r
e
ef
f
icien
t a
n
d
s
tr
ea
m
lin
e
d
class
if
icatio
n
.
−
Neu
r
al
n
etwo
r
k
s
:
e
m
p
lo
y
in
g
a
s
er
ies
o
f
in
ter
co
n
n
ec
ted
n
o
d
e
s
,
th
ese
s
u
p
er
v
is
ed
lear
n
in
g
al
g
o
r
ith
m
s
ex
ce
l
in
d
etec
tin
g
an
o
m
alies
b
y
lea
r
n
in
g
an
d
r
ec
o
g
n
izin
g
p
atter
n
s
an
d
co
r
r
elatio
n
s
th
at
d
ev
iat
e
f
r
o
m
t
y
p
ical
b
eh
av
io
r
s
.
W
e
u
s
ed
a
p
er
ce
p
t
r
o
n
,
wh
ich
is
a
ty
p
e
o
f
n
eu
r
al
n
etwo
r
k
ar
c
h
itectu
r
e
t
h
at
co
n
s
is
t
s
o
f
s
ev
er
al
lin
ea
r
lay
er
s
i
n
ter
co
n
n
ec
ted
b
y
n
o
n
lin
ea
r
lay
e
r
s
.
I
t
r
ep
r
e
s
en
ts
a
f
o
u
n
d
atio
n
al
ar
ch
itec
tu
r
e
in
n
eu
r
al
n
etwo
r
k
d
esig
n
a
n
d
is
v
er
s
atile
en
o
u
g
h
to
a
d
d
r
ess
v
ar
i
o
u
s
p
r
o
b
lem
s
,
in
clu
d
in
g
m
u
lticlas
s
class
if
icatio
n
task
s
.
Fo
r
th
e
n
o
n
lin
ea
r
lay
er
s
,
d
if
f
er
en
t
f
u
n
cti
o
n
s
ca
n
b
e
u
s
ed
;
th
e
m
o
s
t
co
m
m
o
n
ly
em
p
lo
y
ed
e
x
am
p
les
in
clu
d
e
r
ec
tifie
d
lin
ea
r
u
n
it (
R
eL
U)
,
s
ig
m
o
id
,
a
n
d
th
eir
d
er
iv
ativ
es
.
−
Sy
n
th
etic
m
in
o
r
ity
o
v
er
s
am
p
lin
g
tech
n
iq
u
e
(
SMOT
E
)
:
is
an
u
p
s
am
p
lin
g
alg
o
r
ith
m
th
at
g
en
er
ates
n
ew
s
y
n
th
etic
s
am
p
les
f
r
o
m
th
e
m
in
o
r
ity
class
.
I
t
id
en
tifie
s
s
ev
e
r
al
n
ea
r
est
n
eig
h
b
o
r
s
f
o
r
ea
ch
m
in
o
r
ity
class
s
am
p
le,
s
elec
ts
a
r
an
d
o
m
s
u
b
s
et
b
ased
o
n
t
h
e
d
esire
d
s
am
p
l
e
r
atio
,
an
d
th
en
cr
ea
tes
s
y
n
th
etic
s
am
p
les
b
y
ch
o
o
s
in
g
r
an
d
o
m
p
o
in
ts
alo
n
g
lin
e
s
eg
m
en
ts
b
etwe
en
n
eig
h
b
o
r
s
an
d
th
e
o
r
ig
in
al
s
am
p
le.
No
tab
ly
,
SMOT
E
is
tailo
r
ed
f
o
r
n
u
m
er
i
ca
l f
ea
tu
r
es a
n
d
d
o
es n
o
t su
p
p
o
r
t c
ateg
o
r
ical
f
ea
tu
r
es
[
2
7
]
.
I
n
teg
r
atin
g
t
h
ese
alg
o
r
ith
m
s
ca
n
s
ig
n
if
ican
tly
im
p
r
o
v
e
th
e
p
r
ec
is
io
n
o
f
th
ese
s
y
s
tem
s
.
As
d
ig
ital
lan
d
s
ca
p
es
co
n
tin
u
e
to
ev
o
lv
e
,
th
e
n
ee
d
f
o
r
r
o
b
u
s
t
m
ac
h
in
e
lear
n
in
g
ap
p
licatio
n
s
in
cy
b
e
r
s
ec
u
r
ity
b
ec
o
m
es
m
o
r
e
cr
u
cial.
T
h
ese
alg
o
r
ith
m
s
ar
e
n
o
t
o
n
ly
ca
p
a
b
le
o
f
i
d
en
tify
in
g
u
n
u
s
u
al
p
atter
n
s
i
n
n
etwo
r
k
tr
af
f
ic
o
r
p
o
ten
tial
ze
r
o
-
d
ay
e
x
p
lo
its
b
y
co
n
tr
asti
n
g
th
em
ag
ain
s
t
h
is
to
r
ical
d
ata
b
u
t
ar
e
also
ef
f
ec
t
iv
e
in
r
ec
o
g
n
izin
g
in
ter
n
al
th
r
ea
ts
th
r
o
u
g
h
b
eh
a
v
io
r
al
an
aly
s
is
co
m
p
ar
e
d
to
esta
b
lis
h
ed
n
o
r
m
s
[
2
8
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
7
1
-
2
2
8
1
2274
T
h
e
E
u
r
o
p
ea
n
Un
i
o
n
Ag
en
cy
f
o
r
C
y
b
er
s
ec
u
r
ity
(
E
NI
SA)
d
o
cu
m
en
t
"
C
lo
u
d
co
m
p
u
tin
g
s
ec
u
r
ity
r
is
k
ass
es
s
m
en
t
(
C
C
SK)
"
p
r
o
v
id
es
an
o
v
er
v
iew
o
f
ex
is
tin
g
v
u
l
n
er
ab
ilit
ies
in
m
o
d
er
n
in
f
o
r
m
at
io
n
tech
n
o
lo
g
y
(
I
T
)
in
f
r
astru
ctu
r
e
.
Am
o
n
g
th
ese
v
u
ln
er
ab
ilit
ies,
th
e
d
o
c
u
m
en
t h
i
g
h
lig
h
ts
s
ev
er
al
cr
itical
ar
ea
s
:
−
AAA
v
u
ln
er
ab
ilit
ies:
t
h
ese
r
elate
to
au
th
en
ticatio
n
,
au
th
o
r
iz
atio
n
,
an
d
ac
co
u
n
tin
g
,
p
o
s
in
g
s
ig
n
if
ican
t
r
is
k
s
in
m
an
ag
in
g
ac
ce
s
s
an
d
tr
ac
k
i
n
g
u
s
er
ac
tiv
ities
.
−
User
p
r
o
v
is
io
n
in
g
v
u
ln
er
ab
ilit
ies:
i
s
s
u
es
h
er
e
in
v
o
lv
e
th
e
m
an
ag
em
en
t
o
f
u
s
er
ac
co
u
n
ts
,
s
p
ec
if
ically
th
e
s
ec
u
r
e
ad
d
itio
n
a
n
d
r
e
m
o
v
al
o
f
u
s
er
ac
ce
s
s
.
−
R
em
o
te
ac
ce
s
s
:
th
is
r
ef
er
s
to
th
e
v
u
ln
er
ab
ilit
ies
th
at
ca
n
ar
is
e
wh
en
ex
ter
n
al
en
titi
es
g
ai
n
ac
ce
s
s
to
th
e
clo
u
d
’
s
m
an
a
g
em
en
t in
ter
f
ac
e
s
.
−
Hy
p
er
v
is
o
r
v
u
ln
er
a
b
ilit
ies:
as
a
k
ey
c
o
m
p
o
n
en
t
in
v
ir
tu
al
en
v
ir
o
n
m
en
ts
,
h
y
p
er
v
is
o
r
s
p
r
esen
t
a
p
r
im
e
tar
g
et
f
o
r
attac
k
s
if
n
o
t p
r
o
p
e
r
ly
s
ec
u
r
ed
.
−
L
ac
k
o
f
r
eso
u
r
ce
is
o
latio
n
:
t
h
ese
v
u
ln
er
ab
ilit
ies
lead
to
p
o
ten
tial
cr
o
s
s
-
ten
an
t
attac
k
s
an
d
r
ep
u
tatio
n
al
d
am
ag
e
d
u
e
to
s
h
ar
e
d
r
eso
u
r
c
es.
−
E
n
cr
y
p
tio
n
v
u
l
n
er
ab
ilit
ies:
th
ese
in
clu
d
e
wea
k
en
cr
y
p
tio
n
o
f
d
ata
in
tr
an
s
it
an
d
at
r
est,
an
d
is
s
u
es
wi
th
th
e
en
cr
y
p
tio
n
p
r
o
ce
s
s
es
th
em
s
elv
es,
s
u
ch
as
in
ad
e
q
u
ate
k
e
y
m
an
a
g
em
en
t
o
r
th
e
in
ab
il
ity
to
p
r
o
ce
s
s
en
cr
y
p
ted
d
ata.
C
o
n
s
eq
u
en
tly
,
th
e
p
r
im
ar
y
th
r
ea
ts
to
in
f
o
r
m
atio
n
s
ec
u
r
ity
in
clo
u
d
s
er
v
ices
f
o
cu
s
o
n
cr
itic
al
co
m
p
o
n
en
ts
s
u
ch
as
th
e
h
y
p
er
v
is
o
r
,
v
ir
tu
al
m
a
ch
in
es,
n
etwo
r
k
in
te
r
ac
tio
n
s
,
an
d
au
d
it
m
ec
h
an
is
m
s
.
E
ac
h
o
f
th
ese
elem
en
ts
r
eq
u
ir
es
r
o
b
u
s
t
s
ec
u
r
ity
m
ea
s
u
r
es
to
m
itig
ate
th
e
r
is
k
o
f
co
m
p
r
o
m
is
e
an
d
en
s
u
r
e
th
e
in
teg
r
i
ty
an
d
av
ailab
ilit
y
o
f
clo
u
d
s
er
v
ices.
2
.
2
.
Da
t
a
s
et
s
T
h
e
KDD9
9
C
u
p
d
ataset
is
t
h
e
m
o
s
t
wid
ely
cited
d
atase
t
f
o
r
class
if
y
in
g
c
o
m
p
u
ter
a
ttack
s
,
as
ev
id
en
ce
d
b
y
n
u
m
er
o
u
s
p
u
b
l
icatio
n
s
.
Ho
wev
er
,
s
in
ce
it
was
cr
ea
ted
in
1
9
9
9
,
its
r
elev
an
ce
f
o
r
tr
ain
i
n
g
m
o
d
er
n
tr
af
f
ic
d
etec
tio
n
s
y
s
tem
s
is
in
cr
ea
s
in
g
ly
q
u
esti
o
n
ab
le.
Ma
n
y
n
ew
ty
p
es
o
f
cy
b
er
-
attac
k
s
h
a
v
e
em
er
g
ed
s
in
ce
th
e
n
th
at
ar
e
n
o
t
r
ep
r
esen
ted
in
th
is
d
ataset,
lim
itin
g
its
ef
f
ec
tiv
en
ess
in
cu
r
r
en
t
ap
p
licatio
n
s
.
An
o
th
er
c
o
m
m
o
n
ly
r
e
f
er
en
ce
d
d
ataset
in
th
e
f
ield
o
f
co
m
p
u
ter
attac
k
d
etec
tio
n
is
th
e
Un
iv
er
s
ity
o
f
Ne
w
So
u
th
W
ales
n
etwo
r
k
-
b
ased
2
0
1
5
(
UNSW
-
NB
1
5
)
d
ataset,
wh
ich
was
co
m
p
iled
in
2
0
1
5
a
n
d
in
clu
d
es
a
b
r
o
ad
e
r
r
an
g
e
o
f
co
n
tem
p
o
r
ar
y
cy
b
er
th
r
ea
ts
[
2
9
]
.
Desp
ite
its
r
elev
an
ce
,
we
ch
o
s
e
n
o
t
to
u
s
e
it
f
o
r
s
ev
e
r
al
r
ea
s
o
n
s
.
Firstl
y
,
th
e
d
ataset
f
ea
tu
r
es
a
v
e
r
y
s
m
all
n
u
m
b
er
o
f
in
s
tan
ce
s
f
o
r
ea
ch
ty
p
e
o
f
attac
k
,
wh
i
ch
ca
n
lead
t
o
is
s
u
es
with
m
o
d
el
tr
ain
in
g
an
d
g
en
er
aliza
tio
n
.
Seco
n
d
ly
,
th
e
d
ataset
we
s
elec
ted
was
g
ath
er
ed
m
o
r
e
r
ec
en
tly
,
en
s
u
r
in
g
th
at
it
r
e
f
lects
th
e
cu
r
r
en
t
t
h
r
ea
t
lan
d
s
ca
p
e
m
o
r
e
ac
cu
r
ately
.
Am
o
n
g
m
o
r
e
r
ec
en
t
d
atasets
,
th
e
a
d
ap
tiv
e
wir
eless
in
tr
u
s
io
n
d
etec
tio
n
(
AW
I
D)
d
atasets
an
d
th
e
I
o
T
d
ataset,
co
llected
in
2
0
2
0
,
r
esp
ec
tiv
ely
,
ar
e
n
o
tewo
r
th
y
[
3
0
]
.
Ho
wev
er
,
we
o
p
te
d
n
o
t
to
u
til
ize
th
ese
d
atasets
as
well.
T
h
e
y
co
n
tain
less
co
m
m
o
n
attac
k
ty
p
es
th
at
m
a
y
n
o
t
b
e
r
elev
an
t
f
o
r
b
r
o
ad
er
ap
p
lic
atio
n
s
,
an
d
t
h
ey
also
h
av
e
a
less
u
s
er
-
f
r
ien
d
ly
d
ata
f
o
r
m
at.
I
n
co
r
p
o
r
atin
g
th
ese
d
atasets
wo
u
ld
r
eq
u
ir
e
u
s
er
s
to
co
n
v
e
r
t
th
eir
d
ata
in
to
a
m
o
r
e
co
m
p
lex
f
o
r
m
at,
wh
ich
c
o
u
ld
d
eter
p
o
ten
tial
u
s
er
s
f
r
o
m
a
d
o
p
tin
g
th
e
s
y
s
tem
we
d
ev
el
o
p
ed
.
Ou
r
g
o
al
is
to
en
s
u
r
e
th
at
th
e
d
ataset
we
u
s
e
is
ac
ce
s
s
ib
le,
en
h
an
cin
g
u
s
er
en
g
ag
em
e
n
t in
d
etec
tin
g
cy
b
er
th
r
ea
ts
.
T
h
is
s
tu
d
y
u
s
es
th
e
NSL
-
K
DD
d
ataset,
an
u
p
g
r
ad
e
d
v
e
r
s
io
n
o
f
th
e
KDD
-
C
UP9
9
d
ataset
th
at
ad
d
r
ess
es
s
o
m
e
o
f
its
l
im
itati
o
n
s
.
T
h
e
im
p
r
o
v
em
en
ts
r
eso
lv
e
s
ev
er
al
in
h
er
en
t
is
s
u
es
th
at
af
f
ec
ted
p
r
ev
io
u
s
r
esear
ch
o
u
tco
m
es.
T
h
e
KD
D
d
ataset
was
f
ir
s
t
in
tr
o
d
u
c
ed
d
u
r
in
g
"
T
h
e
th
ir
d
in
ter
n
atio
n
al
k
n
o
wled
g
e
d
is
co
v
er
y
a
n
d
d
ata
m
in
in
g
to
o
ls
co
m
p
etitio
n
,
"
aim
in
g
to
d
ev
elo
p
an
in
tr
u
s
io
n
d
etec
ti
o
n
s
y
s
tem
th
at
ca
n
d
if
f
er
en
tiate
with
in
"
g
o
o
d
"
a
n
d
"b
a
d
"
n
etwo
r
k
tr
af
f
ic.
Sin
ce
th
en
,
th
e
d
ataset
h
as
b
ee
n
wid
ely
u
tili
ze
d
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
,
tr
ain
in
g
,
test
in
g
,
an
d
im
p
lem
en
tin
g
m
ac
h
in
e
lear
n
in
g
tec
h
n
o
lo
g
ies
in
th
e
cy
b
er
s
ec
u
r
ity
d
o
m
ain
.
Ov
er
tim
e,
h
o
wev
e
r
,
r
esear
ch
er
s
h
av
e
id
en
tifie
d
v
ar
io
u
s
p
r
o
b
lem
s
with
in
th
e
d
ataset
th
at
ca
n
im
p
ac
t
th
e
r
esu
lts
o
f
s
tu
d
ies
an
d
s
u
b
s
eq
u
en
t
ap
p
licatio
n
s
.
As
a
r
esp
o
n
s
e,
th
e
NSL
-
KDD
d
at
aset
was
p
r
o
p
o
s
ed
,
in
co
r
p
o
r
atin
g
n
ec
ess
ar
y
co
r
r
e
ctio
n
s
an
d
u
p
d
ates.
T
h
e
d
ataset,
as
s
h
o
wn
in
T
ab
le
1
,
co
n
tain
s
4
2
f
ea
tu
r
es
th
a
t
th
o
r
o
u
g
h
ly
d
escr
ib
e
in
co
m
i
n
g
tr
af
f
ic.
Fo
r
o
u
r
an
al
y
s
is
,
we
will
f
o
cu
s
o
n
th
e
n
o
r
m
al,
R
2
L
,
an
d
U2
R
class
es,
as th
ese
ar
e
m
o
s
t r
elev
an
t f
o
r
o
u
r
lear
n
in
g
o
b
jectiv
es.
I
t in
cl
u
d
es a
v
ar
iety
o
f
attac
k
class
es,
s
p
ec
if
ically
:
−
Do
S:
a
ttack
s
s
u
ch
as B
ac
k
,
L
an
d
,
Nep
tu
n
e,
Po
d
,
Sm
u
r
f
,
an
d
T
ea
r
Dr
o
p
.
−
Pro
b
e:
i
n
clu
d
es a
ttack
s
lik
e
Sa
tan
,
I
p
s
wee
p
,
Nm
ap
,
an
d
Po
r
ts
wee
p
.
−
R
2
L
:
a
ttack
s
s
u
ch
as
g
u
ess
p
ass
wo
r
d
,
Ftp
r
f
ak
e,
I
m
ap
,
Ph
f
,
Mu
ltih
o
p
,
W
ar
ez
m
aster
,
W
ar
ez
clien
t,
an
d
Sp
y
.
−
U2
R
:
i
n
clu
d
es
b
u
f
f
er
o
v
er
f
lo
w
,
L
o
ad
m
o
d
u
le,
R
o
o
t
k
it,
an
d
Per
l a
ttack
s
.
Fo
r
d
ata
p
r
ep
a
r
atio
n
,
we
u
s
e
p
r
in
cip
al
c
o
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
,
a
s
tatis
tical
m
eth
o
d
th
at
r
ed
u
ce
s
h
ig
h
-
d
im
e
n
s
io
n
al
d
ata
b
y
i
d
en
tify
in
g
k
ey
f
ea
tu
r
es,
r
etain
in
g
th
e
m
o
s
t
in
f
o
r
m
ativ
e
asp
ec
ts
o
f
th
e
d
ataset
wh
ile
r
ed
u
cin
g
d
im
en
s
io
n
ality
.
W
h
en
ad
d
r
ess
in
g
class
im
b
alan
ce
,
if
th
e
d
is
p
ar
ity
is
n
o
t
e
x
ce
s
s
iv
e
an
d
s
u
f
f
icien
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
d
va
n
cin
g
n
etw
o
r
k
s
ec
u
r
ity:
a
co
mp
a
r
a
tive
r
esea
r
ch
o
f m
a
c
h
in
e
lea
r
n
in
g
…
(
S
h
y
n
g
g
ys R
y
s
b
ek
o
v
)
2275
d
ata
is
av
ailab
le,
we
m
ay
r
e
m
o
v
e
in
s
tan
ce
s
f
r
o
m
th
e
o
v
er
r
ep
r
esen
ted
class
.
Ho
wev
er
,
i
t
is
cr
u
cial
to
r
etain
en
o
u
g
h
in
f
o
r
m
atio
n
to
av
o
id
s
ig
n
if
ican
tly
im
p
ac
tin
g
cl
ass
if
icatio
n
ac
cu
r
ac
y
.
Var
io
u
s
m
eth
o
d
s
ca
n
b
e
em
p
lo
y
ed
f
o
r
d
ata
r
ed
u
ctio
n
,
s
u
ch
as
r
an
d
o
m
s
am
p
lin
g
f
r
o
m
th
e
lar
g
er
class
o
r
clu
s
ter
i
n
g
to
s
elec
t
a
f
ix
ed
n
u
m
b
er
o
f
e
x
am
p
les
f
r
o
m
ea
c
h
clu
s
ter
.
T
h
e
latter
ap
p
r
o
ac
h
p
r
eser
v
es
m
o
r
e
in
f
o
r
m
atio
n
b
y
en
s
u
r
i
n
g
th
at
n
o
clu
s
ter
is
en
tire
ly
lo
s
t.
T
ab
le
1
.
Attr
ib
u
tes o
f
th
e
d
ata
s
et
u
s
ed
in
th
is
s
tu
d
y
#
F
e
a
t
u
r
e
#
F
e
a
t
u
r
e
#
F
e
a
t
u
r
e
1
D
u
r
a
t
i
o
n
15
C
o
u
n
t
29
S
r
v
d
i
f
f
h
o
s
t
r
a
t
e
2
P
r
o
t
o
c
o
l
t
y
p
e
16
N
u
m
f
i
l
e
c
r
e
a
t
i
o
n
s
30
C
l
a
s
s l
a
b
e
l
s
3
F
l
a
g
s
17
N
u
m ro
o
t
31
S
a
me
sr
v
r
a
t
e
4
S
e
r
v
i
c
e
s
18
N
u
m a
c
c
e
ss fi
l
e
s
32
D
st
h
o
s
t
c
o
u
n
t
5
S
o
u
r
c
e
b
y
t
e
s
19
N
u
m s
h
e
l
l
s
33
D
st
h
o
s
t
sa
me
sr
v
r
a
t
e
6
D
e
st
i
n
a
t
i
o
n
b
y
t
e
s
20
N
u
m
o
u
t
b
o
u
n
d
c
m
d
s
34
D
st
h
o
s
t
sr
v
c
o
u
n
t
7
W
r
o
n
g
f
r
a
g
me
n
t
s
21
I
s h
o
st
l
o
g
i
n
35
D
st
h
o
s
t
sr
v
d
i
f
f
h
o
s
t
r
a
t
e
8
La
n
d
22
I
s g
u
e
st
l
o
g
i
n
36
D
st
h
o
s
t
sa
me
sr
c
p
o
r
t
r
a
t
e
9
H
o
t
23
S
u
a
t
t
e
mp
t
e
d
37
D
st
h
o
s
t
d
i
f
f
sr
v
r
a
t
e
10
U
r
g
e
n
t
24
S
r
v
e
r
r
o
r
r
a
t
e
38
D
st
h
o
s
t
r
e
r
r
o
r
r
a
t
e
11
Lo
g
g
e
d
i
n
25
S
r
v
c
o
u
n
t
39
D
st
h
o
s
t
sr
v
r
e
r
r
o
r
r
a
t
e
12
N
u
mb
e
r
o
f
f
a
i
l
e
d
l
o
g
i
n
s
26
S
r
v
r
e
r
r
o
r
r
a
t
e
40
D
st
h
o
s
t
serr
o
r
r
a
t
e
13
R
o
o
t
sh
e
l
l
27
R
e
r
r
o
r
r
a
t
e
41
D
st
h
o
s
t
sr
v
serr
o
r
r
a
t
e
14
N
u
m c
o
m
p
r
o
m
i
se
d
28
S
r
v
serr
o
r
r
a
t
e
42
D
i
f
f
sr
v
r
a
t
e
I
n
o
u
r
a
p
p
r
o
ac
h
,
we
in
itiate
PC
A
to
r
ed
u
ce
t
h
e
d
ataset
to
2
0
f
ea
tu
r
es,
s
elec
tin
g
co
m
p
o
n
en
ts
th
at
ca
p
tu
r
e
th
e
m
o
s
t
v
ar
ian
ce
wh
ile
s
im
p
lify
in
g
th
e
d
ata.
T
h
e
PC
A
m
o
d
el
is
th
en
f
itted
to
t
h
e
f
ea
tu
r
e
m
atr
ix
,
tr
an
s
f
o
r
m
in
g
th
e
f
ea
tu
r
es
in
to
a
r
e
d
u
ce
d
s
p
ac
e
c
o
n
tain
in
g
t
h
ese
2
0
p
r
in
ci
p
al
co
m
p
o
n
e
n
ts
.
Su
b
s
eq
u
e
n
tly
,
we
s
p
lit
th
e
d
ataset
in
to
tr
ain
in
g
an
d
test
in
g
s
ets,
r
eser
v
in
g
2
0
%
o
f
th
e
d
ata
f
o
r
test
in
g
p
u
r
p
o
s
e,
a
s
tan
d
ar
d
p
r
ac
tice
f
o
r
e
v
alu
atin
g
m
o
d
el
p
er
f
o
r
m
an
ce
.
2
.
3
.
Sy
s
t
em
des
ig
n
T
h
e
d
ev
elo
p
ed
s
y
s
tem
u
s
es
v
ar
io
u
s
m
eth
o
d
s
f
o
r
wo
r
k
in
g
with
d
atasets
to
en
h
an
ce
th
e
p
er
f
o
r
m
an
ce
o
f
m
o
d
els
in
th
e
task
o
f
cl
ass
if
y
in
g
co
m
p
u
ter
attac
k
s
,
f
o
llo
win
g
wh
ich
we
d
escr
ib
e
th
e
im
p
lem
en
ted
m
eth
o
d
s
.
T
h
e
p
r
im
ar
y
tr
ain
i
n
g
p
ip
elin
e
ca
n
o
p
er
ate
in
two
m
o
d
es:
t
h
e
s
tan
d
a
r
d
m
o
d
e,
wh
er
e
th
e
m
o
d
el
is
tr
ain
ed
with
tech
n
iq
u
es
f
o
r
h
an
d
lin
g
s
m
all
class
es,
an
d
th
e
co
m
p
ar
is
o
n
m
o
d
e,
w
h
er
e
a
m
o
d
el
is
in
itially
tr
ain
ed
with
o
u
t
th
ese
tech
n
iq
u
es
an
d
th
en
with
th
e
m
.
T
h
e
a
cc
u
r
ac
ies
o
f
b
o
th
m
o
d
els
ac
r
o
s
s
d
if
f
er
en
t
class
es
ar
e
ca
lcu
lated
to
c
o
m
p
ar
e
t
h
eir
p
er
f
o
r
m
an
ce
[
3
1
]
.
T
h
e
p
r
o
ce
s
s
,
as
s
h
o
wn
in
Fig
u
r
e
1
,
b
e
g
in
s
with
t
h
e
cr
ea
ti
o
n
o
f
a
m
o
d
el,
wh
ic
h
is
th
e
n
tr
ai
n
ed
o
n
p
r
e
-
p
r
o
ce
s
s
ed
tr
ain
in
g
d
ata.
Fo
r
e
ac
h
s
am
p
le
in
th
e
m
in
o
r
ity
cla
s
s
,
s
ev
er
al
n
ea
r
est
n
eig
h
b
o
r
s
f
r
o
m
th
e
s
am
e
class
ar
e
id
en
tifie
d
.
Fr
o
m
th
ese
n
ei
g
h
b
o
r
s
,
a
r
an
d
o
m
s
u
b
s
et
o
f
th
e
r
eq
u
ir
e
d
s
ize
is
s
elec
ted
,
wh
er
e
th
e
s
ize
d
ep
e
n
d
s
o
n
th
e
r
atio
o
f
th
e
c
u
r
r
en
t
n
u
m
b
er
o
f
s
am
p
les
in
th
e
m
in
o
r
ity
class
to
th
e
d
esire
d
n
u
m
b
e
r
o
f
s
am
p
les
af
ter
th
e
alg
o
r
ith
m
'
s
ap
p
licatio
n
.
Af
te
r
tr
ain
in
g
,
t
h
e
m
o
d
el
u
n
d
e
r
g
o
es
in
f
er
e
n
ce
o
n
test
d
ata,
f
o
llo
w
ed
b
y
ca
lcu
latio
n
s
o
f
class
-
s
p
ec
if
ic
an
d
o
v
er
all
ac
cu
r
ac
ies
o
n
th
is
d
ata,
an
d
th
e
co
n
s
tr
u
ctio
n
o
f
a
co
n
f
u
s
io
n
m
atr
ix
.
Su
b
s
eq
u
en
tly
,
v
is
u
aliza
tio
n
o
f
th
e
co
n
f
u
s
io
n
m
atr
ix
is
in
v
o
k
ed
,
a
n
d
th
e
co
n
s
tr
u
cte
d
m
a
tr
ix
alo
n
g
with
th
e
tr
ain
ed
m
o
d
el'
s
weig
h
ts
ar
e
s
av
ed
.
Fo
r
ea
ch
m
o
d
el
tr
ain
i
n
g
s
ess
io
n
,
two
v
er
s
io
n
s
o
f
th
e
co
n
f
u
s
io
n
m
atr
ix
ar
e
s
av
ed
-
o
n
e
i
n
ab
s
o
lu
te
n
u
m
b
e
r
s
an
d
th
e
o
th
e
r
in
r
elativ
e
v
alu
es.
Fig
u
r
e
1
.
T
h
e
g
e
n
er
al
s
y
s
tem
’
s
d
esig
n
an
d
p
i
p
elin
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
7
1
-
2
2
8
1
2276
T
h
e
m
ain
f
ile
co
n
tain
s
all
th
e
co
d
e
r
elate
d
to
m
eth
o
d
s
f
o
r
h
an
d
lin
g
s
m
all
class
es.
I
t
i
n
clu
d
es
an
ab
s
tr
ac
t c
lass
B
a
s
eS
a
mp
lin
g
with
an
ab
s
tr
ac
t m
eth
o
d
fit_
mo
d
el
,
as we
ll a
s
d
er
iv
ed
class
e
s
N
o
Up
S
a
mp
lin
g
an
d
B
a
s
eS
mo
te
th
at
im
p
lem
en
t
th
i
s
m
eth
o
d
.
Ad
d
itio
n
ally
,
t
h
is
f
ile
co
n
tain
s
th
e
crea
te_
s
a
mp
lin
g
f
u
n
ctio
n
,
wh
ich
in
v
o
k
es
t
h
e
c
o
n
s
tr
u
cto
r
f
o
r
t
h
e
d
esire
d
m
o
d
el
with
t
h
e
a
p
p
r
o
p
r
iate
p
ar
am
eter
s
a
n
d
r
etu
r
n
s
an
in
s
tan
ce
o
f
t
h
is
m
o
d
el
class
.
T
h
e
b
eh
av
io
r
o
f
th
is
f
u
n
ctio
n
is
d
eter
m
in
ed
b
y
p
ar
am
eter
s
s
p
ec
if
ied
in
th
e
co
n
f
ig
u
r
atio
n
f
ile.
T
h
er
e
ar
e
also
s
ev
er
al
s
m
all
a
u
x
iliar
y
s
cr
ip
ts
ass
o
ciate
d
with
th
is
f
u
n
ctio
n
ality
.
T
h
e
d
ev
el
o
p
ed
s
y
s
tem
o
f
f
er
s
m
u
ltip
le
ap
p
licatio
n
s
,
as
s
h
o
w
n
in
Fig
u
r
e
2
.
Firstl
y
,
it
ca
n
b
e
u
tili
ze
d
f
o
r
in
f
er
en
ce
o
n
u
s
er
d
ata
,
p
r
o
v
id
ed
th
at
th
e
c
h
o
s
en
co
m
b
in
atio
n
o
f
m
o
d
el
an
d
tech
n
iq
u
es
f
o
r
h
an
d
lin
g
s
m
all
class
es
h
a
s
b
ee
n
p
r
e
-
tr
ain
e
d
.
T
h
e
s
ec
o
n
d
ap
p
licatio
n
in
v
o
lv
es
th
e
p
o
ten
tial
to
r
eiter
ate
t
h
e
tr
ain
in
g
p
r
o
ce
s
s
u
s
in
g
o
n
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
els
an
d
m
et
h
o
d
s
f
o
r
s
m
all
class
es,
b
u
t
with
m
o
d
if
icati
o
n
s
to
th
e
tr
ai
n
in
g
d
ataset
o
r
th
e
m
o
d
el'
s
h
y
p
er
p
ar
am
eter
s
.
Fo
r
in
s
tan
ce
,
wh
en
d
ep
lo
y
in
g
th
e
p
e
r
ce
p
tr
o
n
m
o
d
el
alo
n
g
s
id
e
m
eth
o
d
s
f
o
r
m
a
n
ag
in
g
s
m
all
class
es,
th
er
e
is
an
im
p
r
o
v
e
m
en
t
in
th
e
ac
cu
r
ac
y
o
f
d
ete
ctin
g
m
o
s
t
ty
p
es
o
f
attac
k
s
.
Ho
wev
er
,
an
ex
ce
p
tio
n
o
cc
u
r
s
with
r
ar
e
attac
k
ty
p
e
s
,
wh
er
e
ac
cu
r
ac
y
r
em
ain
s
lo
w,
an
d
m
an
y
attac
k
s
ar
e
m
is
tak
en
ly
class
if
ied
as
b
en
ig
n
tr
af
f
ic
.
T
h
is
ap
p
r
o
ac
h
h
i
g
h
lig
h
ts
th
e
s
y
s
tem
's
ad
ap
tab
ilit
y
an
d
its
p
o
ten
tial
to
r
ef
in
e
d
etec
tio
n
ca
p
ab
ilit
ies
u
n
d
er
v
ar
ied
co
n
d
itio
n
s
.
T
h
e
p
r
im
ar
y
d
is
tin
ctio
n
o
f
o
u
r
wo
r
k
f
r
o
m
o
t
h
er
s
in
th
e
f
ield
is
o
u
r
f
o
c
u
s
o
n
i
m
p
r
o
v
i
n
g
class
if
icatio
n
ac
c
u
r
ac
y
s
p
ec
if
ically
f
o
r
r
ar
e
cl
ass
es,
r
ath
er
th
an
m
ax
im
izin
g
o
v
er
all
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
W
h
ile
o
th
er
s
tu
d
ies
p
r
im
ar
ily
tr
ac
k
m
et
r
ics
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
o
u
r
in
te
r
est
lies
in
u
n
d
er
s
tan
d
i
n
g
h
o
w
class
if
icatio
n
ac
cu
r
ac
y
f
o
r
in
f
r
eq
u
en
t
class
es
ch
an
g
es with
d
if
f
e
r
en
t u
p
s
am
p
lin
g
an
d
d
o
wn
s
am
p
lin
g
tech
n
iq
u
es.
Fig
u
r
e
2
.
Ov
e
r
v
iew
o
f
ap
p
lica
tio
n
s
o
f
th
e
d
ev
elo
p
e
d
s
y
s
tem
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
d
va
n
cin
g
n
etw
o
r
k
s
ec
u
r
ity:
a
co
mp
a
r
a
tive
r
esea
r
ch
o
f m
a
c
h
in
e
lea
r
n
in
g
…
(
S
h
y
n
g
g
ys R
y
s
b
ek
o
v
)
2277
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
W
e
s
e
t u
p
m
ac
h
in
e
lear
n
in
g
m
o
d
els th
at
ca
n
s
p
o
t tr
af
f
ic
an
o
m
alies,
ex
p
er
im
en
ted
with
th
ese
m
o
d
els,
an
d
c
o
m
p
ar
e
d
th
em
b
ased
o
n
ch
o
s
en
m
etr
ics.
Un
lik
e
lin
ea
r
r
eg
r
ess
io
n
,
lo
g
is
tic
r
e
g
r
ess
io
n
p
er
f
o
r
m
s
well
in
s
ce
n
ar
io
s
wh
er
e
th
e
class
es
a
r
e
lin
ea
r
ly
s
ep
ar
ab
le
o
r
n
ea
r
l
y
s
ep
ar
ab
le,
as
it
p
r
ed
icts
th
e
p
r
o
b
a
b
ilit
y
th
at
an
o
b
ject
b
elo
n
g
s
to
a
p
ar
ticu
lar
class
.
I
n
it
s
b
asic
f
o
r
m
,
th
e
m
o
d
el,
lik
e
th
e
o
th
er
test
ed
m
o
d
els,
ac
h
iev
es
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
f
o
r
p
o
p
u
lar
attac
k
s
.
Fo
r
all
th
e
p
o
p
u
lar
a
n
d
m
a
n
y
m
o
d
er
ate
t
y
p
es
o
f
attac
k
s
,
th
e
ac
cu
r
ac
y
ex
ce
ed
s
9
5
%.
Ho
wev
er
,
f
o
r
r
a
r
e
attac
k
class
es,
th
e
ac
cu
r
ac
y
d
r
o
p
s
to
0
%
-
th
e
m
o
d
el
s
tr
u
g
g
les
to
class
if
y
th
is
ty
p
e
o
f
attac
k
,
o
f
ten
m
is
class
if
y
in
g
th
ese
attac
k
s
as
b
en
ig
n
.
T
h
e
p
er
f
o
r
m
a
n
c
e
m
etr
ics
f
r
o
m
th
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
a
r
e
d
is
p
lay
ed
in
T
ab
le
2
.
T
ab
le
2
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
et
r
ics f
o
r
th
e
m
o
d
el
M
e
t
r
i
c
s
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
Tr
a
i
n
i
n
g
a
c
c
u
r
a
c
y
8
7
.
9
7
%
Te
st
a
c
c
u
r
a
c
y
8
7
.
6
2
%
Tr
a
i
n
i
n
g
p
r
e
c
i
si
o
n
8
3
.
8
1
%
Te
st
p
r
e
c
i
s
i
o
n
8
3
.
5
6
%
Tr
a
i
n
i
n
g
r
e
c
a
l
l
9
1
.
8
5
%
T
h
e
co
n
f
u
s
io
n
m
atr
ix
as
s
h
o
wn
in
Fig
u
r
e
3
is
u
s
ed
to
ass
ess
th
e
p
er
f
o
r
m
a
n
ce
o
f
a
cl
ass
if
icatio
n
m
o
d
el
in
th
is
s
ce
n
ar
io
,
lik
ely
ap
p
lied
in
ev
alu
atin
g
an
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
th
at
class
if
ies
o
u
tco
m
es
a
s
“
n
o
r
m
al
”
o
r
“
attac
k
”
.
T
h
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
d
e
m
o
n
s
tr
ates
s
tr
o
n
g
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
th
r
e
e
m
etr
ics
-
p
r
ec
is
io
n
,
r
ec
all,
an
d
ac
cu
r
ac
y
.
T
h
e
co
n
s
is
ten
cy
o
b
s
er
v
ed
f
r
o
m
tr
ain
in
g
to
test
in
g
p
h
ases
s
u
g
g
est
s
th
at
th
e
m
o
d
el
is
r
o
b
u
s
t,
p
o
t
en
tially
p
er
f
o
r
m
in
g
well
o
n
n
ew,
u
n
s
ee
n
d
ata.
Alth
o
u
g
h
th
e
m
o
d
el
ap
p
ea
r
s
b
alan
ce
d
b
etwe
en
p
r
ec
is
io
n
a
n
d
r
ec
all,
f
u
r
th
er
ex
a
m
in
atio
n
o
f
th
e
s
p
ec
if
ic
b
u
s
in
ess
co
n
tex
t
is
r
eq
u
ir
ed
to
d
ec
id
e
if
th
e
tr
a
d
e
-
o
f
f
b
etwe
en
th
ese
m
etr
ics is
ac
ce
p
tab
le.
Fig
u
r
e
3
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
t
h
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
I
n
th
e
co
n
tex
t
o
f
an
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
,
a
h
ig
h
er
r
e
ca
ll
m
ay
b
e
m
o
r
e
cr
itical
th
an
p
r
ec
is
io
n
to
en
s
u
r
e
as
m
an
y
tr
u
e
th
r
ea
t
s
as
p
o
s
s
ib
le
ar
e
d
etec
ted
,
ev
en
if
it
r
esu
lts
in
s
o
m
e
f
alse
alar
m
s
.
Ho
wev
er
,
if
f
alse
p
o
s
itiv
es
ar
e
p
ar
ticu
lar
ly
co
s
tly
o
r
d
is
r
u
p
tiv
e,
en
h
a
n
cin
g
p
r
ec
is
io
n
b
ec
o
m
es
cr
u
c
ial.
E
s
p
ec
ially
,
th
e
k
-
n
ea
r
est
n
eig
h
b
o
r
alg
o
r
ith
m
,
a
n
o
n
-
p
a
r
am
etr
ic,
s
u
p
e
r
v
is
ed
lear
n
in
g
class
if
ier
th
at
r
elie
s
o
n
p
r
o
x
im
ity
f
o
r
class
if
icatio
n
,
is
also
ev
alu
at
ed
.
T
h
e
p
e
r
f
o
r
m
an
ce
r
esu
lts
f
o
r
t
h
e
k
-
n
ea
r
est
n
eig
h
b
o
r
m
o
d
el
ar
e
s
h
o
wn
in
T
ab
le
3
.
T
h
is
m
eth
o
d
'
s
ef
f
ec
ti
v
en
ess
h
in
g
es
o
n
its
ab
ilit
y
to
class
if
y
d
ata
p
o
in
ts
b
a
s
ed
o
n
th
e
clo
s
est
tr
ain
in
g
ex
am
p
les in
th
e
f
ea
t
u
r
e
s
p
ac
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
7
1
-
2
2
8
1
2278
T
ab
le
3
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
et
r
ics f
o
r
th
e
m
o
d
el
M
e
t
r
i
c
s
K
N
N
Tr
a
i
n
i
n
g
a
c
c
u
r
a
c
y
9
9
.
0
5
%
Te
st
a
c
c
u
r
a
c
y
9
8
.
9
4
%
Tr
a
i
n
i
n
g
p
r
e
c
i
si
o
n
9
9
.
2
3
%
Te
st
p
r
e
c
i
s
i
o
n
9
9
.
0
6
%
Tr
a
i
n
i
n
g
r
e
c
a
l
l
9
8
.
7
3
%
Ov
er
all,
th
e
r
esu
lts
s
h
o
w
th
at
t
h
e
KNN
ex
ce
ls
,
ac
h
iev
in
g
h
ig
h
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
in
b
o
t
h
tr
ain
in
g
an
d
test
in
g
p
h
ases
.
T
h
is
p
er
f
o
r
m
an
ce
s
u
g
g
ests
th
at
th
e
m
o
d
el
h
as e
f
f
ec
tiv
ely
lear
n
ed
th
e
d
ata
p
atter
n
s
an
d
ca
n
g
en
er
alize
well
to
n
ew
d
ata,
in
d
icatin
g
a
g
o
o
d
f
it
with
n
o
s
ig
n
if
ican
t
s
ig
n
s
o
f
o
v
er
f
itti
n
g
o
r
u
n
d
er
f
itti
n
g
.
I
n
th
e
c
o
n
f
u
s
io
n
m
atr
ix
,
as
s
h
o
wn
in
Fig
u
r
e
4
,
th
e
to
p
lef
t
q
u
ad
r
a
n
t
(
1
3
,
2
7
5
)
in
d
icate
s
tr
u
e
p
o
s
itiv
es,
wh
er
e
th
e
m
o
d
el
ac
cu
r
ately
p
r
e
d
icted
th
e
p
o
s
itiv
e
class
.
T
h
e
to
p
r
ig
h
t
q
u
a
d
r
an
t (
1
1
1
)
ca
p
tu
r
es
f
alse
n
eg
ativ
es,
wh
er
e
p
o
s
itiv
e
ca
s
es
wer
e
in
co
r
r
ec
tly
p
r
ed
icted
a
s
n
eg
ativ
e.
T
h
e
b
o
tto
m
lef
t
q
u
ad
r
an
t
(
1
5
7
)
s
h
o
ws
f
alse
p
o
s
itiv
es,
in
s
tan
ce
s
wh
er
e
th
e
m
o
d
el
m
is
tak
en
ly
p
r
ed
icted
n
eg
ativ
e
ca
s
es
as
p
o
s
itiv
e.
Fin
ally
,
th
e
b
o
tto
m
r
ig
h
t
q
u
a
d
r
an
t
(
1
1
,
6
5
2
)
r
e
p
r
esen
ts
tr
u
e
n
e
g
ativ
es,
co
r
r
ec
tly
id
en
tifie
d
n
e
g
ativ
e
ca
s
es,
to
d
is
tin
g
u
is
h
ef
f
ec
tiv
ely
b
etwe
en
class
lab
el
s
.
Fig
u
r
e
4
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
t
h
e
KNN
m
o
d
el
Naiv
e
B
ay
es
cla
s
s
if
ier
s
co
m
p
r
is
e
a
f
am
ily
o
f
clas
s
if
icatio
n
m
eth
o
d
s
b
ased
o
n
B
ay
es'
th
eo
r
em
.
T
h
ese
ar
e
n
o
t
s
in
g
u
lar
alg
o
r
ith
m
s
b
u
t
a
s
u
ite
th
at
o
p
er
ates
u
n
d
er
a
co
m
m
o
n
p
r
i
n
cip
le.
T
h
e
m
ai
n
d
r
awb
ac
k
o
f
th
is
m
eth
o
d
is
th
e
h
ig
h
n
u
m
b
er
o
f
f
alse
p
o
s
itiv
es,
wh
ic
h
co
n
s
eq
u
en
tly
r
ed
u
ce
s
its
u
s
ef
u
ln
ess
f
o
r
co
m
p
lex
tr
af
f
ic
s
ce
n
ar
io
s
.
T
h
e
d
ec
is
io
n
tr
ee
is
co
n
s
id
er
ed
o
n
e
o
f
th
e
m
o
s
t
p
o
wer
f
u
l
an
d
co
m
m
o
n
ly
u
s
ed
to
o
ls
f
o
r
ca
teg
o
r
izatio
n
an
d
p
r
ed
ictio
n
[
3
2
]
.
I
t c
o
n
s
is
ts
o
f
a
h
ier
ar
ch
ic
al
s
tr
u
ctu
r
e
wh
er
e
ea
ch
in
ter
n
al
n
o
d
e
r
ep
r
esen
ts
a
test
o
n
a
n
attr
ib
u
te,
ea
c
h
b
r
an
ch
d
e
p
icts
th
e
p
o
ten
tial
o
u
tco
m
es
o
f
th
ese
test
s
,
an
d
ea
ch
l
ea
f
n
o
d
e
ass
ig
n
s
a
class
lab
el.
T
h
e
p
er
f
o
r
m
an
ce
r
esu
lts
f
o
r
th
e
n
aiv
e
B
ay
es a
n
d
d
ec
is
io
n
tr
ee
m
o
d
els ar
e
d
etailed
in
T
ab
le
4
.
T
ab
le
4
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
et
r
ics f
o
r
th
e
m
o
d
els
M
e
t
r
i
c
s
N
a
ï
v
e
B
a
y
e
s
D
e
c
i
s
i
o
n
t
r
e
e
Tr
a
i
n
i
n
g
a
c
c
u
r
a
c
y
9
1
.
8
0
%
9
9
.
9
9
%
Te
st
a
c
c
u
r
a
c
y
9
1
.
6
0
%
9
9
.
8
6
%
Tr
a
i
n
i
n
g
p
r
e
c
i
si
o
n
9
2
.
6
2
%
1
0
0
%
Te
st
p
r
e
c
i
s
i
o
n
9
2
.
5
3
%
9
9
.
8
4
%
Tr
a
i
n
i
n
g
r
e
c
a
l
l
8
9
.
4
7
%
9
9
.
9
8
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
d
va
n
cin
g
n
etw
o
r
k
s
ec
u
r
ity:
a
co
mp
a
r
a
tive
r
esea
r
ch
o
f m
a
c
h
in
e
lea
r
n
in
g
…
(
S
h
y
n
g
g
ys R
y
s
b
ek
o
v
)
2279
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
AN
N
m
o
d
el
with
in
t
h
e
co
n
te
x
t
o
f
an
I
DS
is
ex
ce
p
tio
n
ally
p
r
o
m
is
in
g
,
as
d
em
o
n
s
tr
ated
b
y
th
e
r
esu
lts
.
T
h
e
m
o
d
el
ac
h
iev
es
a
n
ea
r
-
p
er
f
ec
t
tr
ain
in
g
ac
cu
r
a
cy
o
f
9
9
.
9
9
4
%,
clo
s
ely
m
ir
r
o
r
ed
b
y
a
test
ac
cu
r
ac
y
.
T
h
is
s
lig
h
t
d
is
cr
ep
an
cy
s
h
o
ws
h
ig
h
ef
f
ec
tiv
en
ess
an
d
th
e
m
o
d
el
is
n
o
t
o
v
er
f
itted
,
a
co
m
m
o
n
is
s
u
e
in
m
ac
h
in
e
lear
n
in
g
.
A
h
ig
h
r
ec
all
r
ate
is
cr
u
cial
in
an
I
DS
as
it
r
ed
u
ce
s
th
e
lik
elih
o
o
d
o
f
m
is
s
in
g
tr
u
e
attac
k
s
,
a
k
ey
f
ac
to
r
in
m
ain
tain
in
g
r
o
b
u
s
t
n
et
wo
r
k
s
ec
u
r
ity
.
T
h
e
d
etailed
r
esu
lts
f
o
r
th
e
ANN
m
o
d
el
ar
e
d
is
p
lay
ed
in
T
a
b
le
5
.
I
t
was
d
is
co
v
er
ed
th
at
r
ed
u
cin
g
th
e
f
ea
tu
r
e
s
et
ad
v
er
s
ely
im
p
ac
ted
th
e
p
er
f
o
r
m
an
ce
o
f
m
o
d
els
wh
en
ap
p
lied
to
r
ea
l
n
etwo
r
k
tr
af
f
i
c
[
3
3
]
.
B
ased
o
n
th
is
,
th
e
f
u
ll
f
ea
tu
r
e
s
et
was
u
s
ed
f
o
r
d
ete
ctio
n
an
d
tr
ain
in
g
,
with
th
e
ex
ce
p
tio
n
o
f
in
ter
n
e
t
p
r
o
to
co
l
(
I
P)
ad
d
r
ess
es,
p
o
r
ts
,
an
d
s
o
m
e
o
th
er
s
p
ec
if
ic
d
ata.
Ho
wev
er
,
it
is
wo
r
th
n
o
tin
g
th
at
in
r
ea
l
in
f
r
a
s
tr
u
ctu
r
e
s
etu
p
s
,
k
ee
p
in
g
p
o
r
t
in
f
o
r
m
atio
n
ca
n
b
e
b
en
ef
icia
l.
Netwo
r
k
"n
o
is
e"
ca
n
s
ig
n
if
ican
tly
r
ed
u
ce
th
e
ef
f
ec
tiv
en
ess
o
f
ex
p
er
im
en
ts
,
wh
ich
co
u
ld
in
clu
d
e
co
r
r
u
p
ted
p
ac
k
ets
d
u
e
to
s
o
f
twar
e
er
r
o
r
s
.
Sin
ce
we
k
n
o
w
wh
ich
s
er
v
ices
ar
e
r
u
n
n
in
g
o
n
s
p
ec
if
ic
p
o
r
ts
,
r
etain
in
g
th
i
s
d
ata
ca
n
in
cr
ea
s
e
th
e
d
etec
tio
n
ac
cu
r
ac
y
.
T
ab
le
5
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
et
r
ics f
o
r
th
e
m
o
d
el
M
e
t
r
i
c
s
ANN
Tr
a
i
n
i
n
g
a
c
c
u
r
a
c
y
9
9
.
9
9
4
%
Te
st
a
c
c
u
r
a
c
y
9
9
.
8
7
7
%
Tr
a
i
n
i
n
g
p
r
e
c
i
si
o
n
9
9
,
8
7
%
Te
st
p
r
e
c
i
s
i
o
n
9
9
.
9
9
%
Tr
a
i
n
i
n
g
r
e
c
a
l
l
9
9
.
9
8
8
%
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
ev
alu
ates
th
e
ef
f
e
ctiv
en
ess
o
f
v
ar
io
u
s
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
in
I
DS,
em
p
lo
y
in
g
tech
n
iq
u
es
s
u
ch
as
lo
g
is
tic
r
eg
r
ess
io
n
,
KNN,
n
aiv
e
B
ay
es,
d
ec
is
io
n
tr
ee
,
an
d
n
eu
r
al
n
et
wo
r
k
s
.
Utilizin
g
th
e
NSL
-
KDD
d
ataset,
th
e
s
tu
d
y
o
f
f
er
s
in
s
ig
h
ts
in
to
ea
ch
alg
o
r
ith
m
'
s
m
etr
ics,
h
ig
h
lig
h
tin
g
th
e
n
ee
d
to
s
elec
t
th
e
ap
p
r
o
p
r
iate
alg
o
r
ith
m
b
ased
o
n
its
ca
p
ab
ilit
y
to
i
d
en
tify
v
ar
io
u
s
ty
p
es
o
f
n
etwo
r
k
attac
k
s
.
No
tab
ly
,
th
e
ANN
m
o
d
el
s
h
o
ws
ex
ce
p
tio
n
al
p
er
f
o
r
m
an
ce
,
d
em
o
n
s
tr
atin
g
n
ea
r
-
p
er
f
ec
t
m
etr
ics,
wh
ich
u
n
d
e
r
s
co
r
es
th
e
p
o
ten
tial
o
f
n
eu
r
al
n
etwo
r
k
s
in
co
m
b
atin
g
s
o
p
h
is
ticated
cy
b
er
th
r
ea
ts
.
L
o
o
k
in
g
f
o
r
war
d
,
th
e
p
ap
er
s
u
g
g
ests
s
ev
er
al
r
esear
ch
d
ir
ec
tio
n
s
to
en
h
an
ce
I
DS
ca
p
ab
ilit
ies:
in
teg
r
atin
g
o
p
tim
izatio
n
tech
n
iq
u
es
to
b
o
o
s
t
r
ea
l
-
tim
e
d
et
ec
tio
n
ef
f
icien
cy
,
d
ev
elo
p
i
n
g
h
y
b
r
id
m
o
d
els
th
at
lev
er
ag
e
th
e
s
tr
en
g
th
s
o
f
v
a
r
i
o
u
s
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
,
ex
p
lo
r
in
g
ad
v
an
ce
d
d
ee
p
le
ar
n
in
g
ar
c
h
itectu
r
es
to
d
etec
t
n
u
an
ce
d
p
atter
n
s
in
n
etwo
r
k
tr
af
f
ic,
an
d
ap
p
ly
in
g
th
ese
m
o
d
els
in
d
iv
er
s
e
r
ea
l
-
wo
r
ld
s
ettin
g
s
to
ass
es
s
p
r
ac
tical
ef
f
ec
tiv
en
ess
.
Ad
d
itio
n
ally
,
f
u
r
th
er
in
v
esti
g
atio
n
in
t
o
f
ea
t
u
r
e
s
elec
tio
n
an
d
e
n
g
in
ee
r
i
n
g
is
r
ec
o
m
m
en
d
ed
to
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
.
W
ith
th
e
g
r
o
wth
o
f
I
o
T
d
e
v
ices
an
d
ed
g
e
co
m
p
u
tin
g
,
ex
p
lo
r
in
g
a
n
o
m
aly
d
etec
tio
n
i
n
th
ese
n
ew
c
o
n
tex
ts
is
also
p
er
tin
en
t.
T
h
ese
ef
f
o
r
ts
will
s
ig
n
if
ican
tly
a
d
v
an
ce
th
e
cy
b
e
r
s
ec
u
r
ity
f
ield
,
p
ar
tic
u
lar
ly
in
d
e
v
elo
p
in
g
m
o
r
e
a
d
v
an
ce
d
,
r
eliab
le,
an
d
ef
f
icien
t
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
L
i
u
,
J.
S
h
i
,
X
.
C
h
e
n
,
a
n
d
C
.
Lu
,
“
N
e
t
w
o
r
k
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
a
n
d
s
e
c
u
r
i
t
y
d
e
f
e
n
s
e
t
e
c
h
n
o
l
o
g
y
b
a
se
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
9
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
4
.
1
0
9
5
8
1
.
[
2
]
T.
S
o
w
m
y
a
a
n
d
E.
A
.
M
a
r
y
A
n
i
t
a
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
A
I
b
a
s
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
M
e
a
s
u
remen
t
:
S
e
n
so
rs
,
v
o
l
.
2
8
,
p
p
.
1
–
1
3
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
se
n
.
2
0
2
3
.
1
0
0
8
2
7
.
[
3
]
A
.
K
h
r
a
i
sa
t
,
I
.
G
o
n
d
a
l
,
P
.
V
a
mp
l
e
w
,
a
n
d
J.
K
a
mr
u
z
z
a
ma
n
,
“
S
u
r
v
e
y
o
f
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
ms
:
t
e
c
h
n
i
q
u
e
s,
d
a
t
a
se
t
s
a
n
d
c
h
a
l
l
e
n
g
e
s,”
C
y
b
e
rse
c
u
r
i
t
y
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
–
2
2
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
2
4
0
0
-
0
1
9
-
0
0
3
8
-
7.
[
4
]
Q
.
Li
u
,
V
.
H
a
g
e
n
me
y
e
r
,
a
n
d
H
.
B
.
K
e
l
l
e
r
,
“
A
r
e
v
i
e
w
o
f
r
u
l
e
l
e
a
r
n
i
n
g
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
ms
a
n
d
t
h
e
i
r
p
r
o
s
p
e
c
t
s
i
n
smar
t
g
r
i
d
s,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
5
7
5
4
2
–
5
7
5
6
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
7
1
2
6
3
.
[
5
]
R
.
V
i
n
a
y
a
k
u
m
a
r
,
M
.
A
l
a
z
a
b
,
K
.
P
.
S
o
ma
n
,
P
.
P
o
o
r
n
a
c
h
a
n
d
r
a
n
,
A
.
A
l
-
N
e
mr
a
t
,
a
n
d
S
.
V
e
n
k
a
t
r
a
m
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
i
n
t
e
l
l
i
g
e
n
t
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
4
1
5
2
5
–
4
1
5
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
8
9
5
3
3
4
.
[
6
]
K
.
S
i
v
a
r
a
ma
n
,
R
.
M
.
V
.
K
r
i
s
h
n
a
n
,
B
.
S
u
n
d
a
r
r
a
j
,
a
n
d
S
.
S
r
i
G
o
w
t
h
e
m,
“
N
e
t
w
o
r
k
f
a
i
l
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
s
i
s
b
y
a
n
a
l
y
z
i
n
g
sy
sl
o
g
a
n
d
S
N
S
d
a
t
a
:
a
p
p
l
y
i
n
g
b
i
g
d
a
t
a
a
n
a
l
y
s
i
s
t
o
n
e
t
w
o
r
k
o
p
e
r
a
t
i
o
n
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
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Ex
p
l
o
ri
n
g
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
8
,
n
o
.
9
S
3
,
p
p
.
8
8
3
–
8
8
7
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
3
5
9
4
0
/
i
j
i
t
e
e
.
I
3
1
8
7
.
0
7
8
9
S
3
1
9
.
[
7
]
A
.
D
.
D
w
i
v
e
d
i
,
G
.
S
r
i
v
a
s
t
a
v
a
,
S
.
D
h
a
r
,
a
n
d
R
.
S
i
n
g
h
,
“
A
d
e
c
e
n
t
r
a
l
i
z
e
d
p
r
i
v
a
c
y
-
p
r
e
ser
v
i
n
g
h
e
a
l
t
h
c
a
r
e
b
l
o
c
k
c
h
a
i
n
f
o
r
I
o
T,
”
S
e
n
so
rs
,
v
o
l
.
1
9
,
n
o
.
2
,
p
p
.
1
–
1
7
,
J
a
n
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s1
9
0
2
0
3
2
6
.
[
8
]
Z.
A
z
a
m,
M
.
M
.
I
sl
a
m,
a
n
d
M
.
N
.
H
u
d
a
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
ms a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
m
o
d
e
l
a
n
a
l
y
si
s
t
h
r
o
u
g
h
d
e
c
i
s
i
o
n
t
r
e
e
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
8
0
3
4
8
–
8
0
3
9
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
6
4
4
4
.
[
9
]
H
.
W
u
,
“
F
e
a
t
u
r
e
-
w
e
i
g
h
t
e
d
n
a
i
v
e
B
a
y
e
s
i
a
n
c
l
a
ssi
f
i
e
r
f
o
r
w
i
r
e
l
e
ss
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
,
”
S
e
c
u
r
i
t
y
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rks
,
n
o
.
1
,
p
p
.
1
–
1
3
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
4
/
7
0
6
5
4
8
2
.
[
1
0
]
W
.
Li
,
P
.
Y
i
,
Y
.
W
u
,
L.
P
a
n
,
a
n
d
J
.
Li
,
“
A
n
e
w
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
b
a
s
e
d
o
n
K
N
N
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
i
n
w
i
r
e
l
e
ss
sen
s
o
r
n
e
t
w
o
r
k
,
”
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
r
i
n
g
,
n
o
.
1
,
p
p
.
1
–
8
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
4
/
2
4
0
2
1
7
.
[
1
1
]
F
.
S
.
D
.
P
r
a
n
o
t
o
a
n
d
Y
.
A
s
n
a
r
,
“
D
e
v
e
l
o
p
me
n
t
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
s
u
b
s
y
st
e
m
i
n
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
c
y
b
e
r
p
h
y
s
i
c
a
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
7
1
-
2
2
8
1
2280
sy
st
e
m,
”
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
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
I
C
EEI)
,
O
c
t
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EEI
5
9
4
2
6
.
2
0
2
3
.
1
0
3
4
6
6
4
9
.
[
1
2
]
S
.
B
.
S
a
i
d
i
n
a
n
d
S
.
B
.
I
.
H
i
sh
a
m
,
“
A
s
u
r
v
e
y
o
n
su
p
e
r
v
i
s
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
i
n
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
ms f
o
r
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s,
”
i
n
2
0
2
3
I
EEE
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
on
S
o
f
t
w
a
re
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
y
st
e
m
s
(
I
C
S
EC
S
)
,
A
u
g
.
2
0
2
3
,
p
p
.
4
1
9
–
4
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
EC
S
5
8
4
5
7
.
2
0
2
3
.
1
0
2
5
6
2
7
5
.
[
1
3
]
A
.
P
o
n
m
a
l
a
r
a
n
d
V
.
D
h
a
n
a
k
o
t
i
,
“
A
n
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
u
s
i
n
g
e
n
s
e
mb
l
e
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
b
a
sed
c
h
a
o
s
g
a
m
e
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
i
n
b
i
g
d
a
t
a
p
l
a
t
f
o
r
m,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
1
6
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
1
.
1
0
8
2
9
5
.
[
1
4
]
M
.
A
mr
u
e
t
a
l
.
,
“
N
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
b
y
a
p
p
l
y
i
n
g
e
n
se
m
b
l
e
mo
d
e
l
f
o
r
smar
t
h
o
me
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
3
4
8
5
–
3
4
9
4
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
3
4
8
5
-
3
4
9
4
.
[
1
5
]
M
.
C
.
T
h
r
u
n
,
J
.
M
ä
r
t
e
,
a
n
d
Q
.
S
t
i
e
r
,
“
A
n
a
l
y
z
i
n
g
q
u
a
l
i
t
y
mea
s
u
r
e
m
e
n
t
s
f
o
r
d
i
m
e
n
s
i
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
,
”
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
Ex
t
ra
c
t
i
o
n
,
v
o
l
.
5
,
n
o
.
3
,
p
p
.
1
0
7
6
–
1
1
1
8
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
k
e
5
0
3
0
0
5
6
.
[
1
6
]
P
.
S
.
B
h
a
t
t
a
c
h
a
r
j
e
e
,
A
.
K
.
M
d
F
u
j
a
i
l
,
a
n
d
S
.
A
.
B
e
g
u
m,
“
A
c
o
mp
a
r
i
s
o
n
o
f
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
b
y
k
-
me
a
n
s
a
n
d
f
u
z
z
y
c
-
me
a
n
s
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
o
v
e
r
t
h
e
N
S
L
-
K
D
D
d
a
t
a
s
e
t
,
”
i
n
2
0
1
7
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
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
p
u
t
i
n
g
R
e
se
a
rc
h
(
I
C
C
I
C
)
,
D
e
c
.
2
0
1
7
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
C
.
2
0
1
7
.
8
5
2
4
4
0
1
.
[
1
7
]
R
.
P
a
n
i
g
r
a
h
i
e
t
a
l
.
,
“
A
c
o
n
s
o
l
i
d
a
t
e
d
d
e
c
i
s
i
o
n
t
r
e
e
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
f
o
r
b
i
n
a
r
y
a
n
d
m
u
l
t
i
c
l
a
ss i
m
b
a
l
a
n
c
e
d
d
a
t
a
se
t
s,”
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
9
,
n
o
.
7
,
p
p
.
1
–
3
5
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
t
h
9
0
7
0
7
5
1
.
[
1
8
]
M
.
A
l
-
Ze
w
a
i
r
i
,
S
.
A
l
ma
j
a
l
i
,
a
n
d
A
.
A
w
a
j
a
n
,
“
E
x
p
e
r
i
m
e
n
t
a
l
e
v
a
l
u
a
t
i
o
n
o
f
a
m
u
l
t
i
-
l
a
y
e
r
f
e
e
d
-
f
o
r
w
a
r
d
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
c
l
a
ss
i
f
i
e
r
f
o
r
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
i
n
2
0
1
7
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
N
e
w
T
re
n
d
s
i
n
C
o
m
p
u
t
i
n
g
S
c
i
e
n
c
e
s
(
I
C
T
C
S
)
,
O
c
t
.
2
0
1
7
,
p
p
.
1
6
7
–
1
7
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
TC
S
.
2
0
1
7
.
2
9
.
[
1
9
]
A
k
a
s
h
d
e
e
p
,
I
.
M
a
n
z
o
o
r
,
a
n
d
N
.
K
u
m
a
r
,
“
A
f
e
a
t
u
r
e
r
e
d
u
c
e
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
u
s
i
n
g
A
N
N
c
l
a
ssi
f
i
e
r
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
8
,
p
p
.
2
4
9
–
2
5
7
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
7
.
0
7
.
0
0
5
.
[
2
0
]
K
.
W
a
n
g
,
A
.
Z
h
a
n
g
,
H
.
S
u
n
,
a
n
d
B
.
W
a
n
g
,
“
A
n
a
l
y
s
i
s
o
f
r
e
c
e
n
t
d
e
e
p
-
l
e
a
r
n
i
n
g
-
b
a
s
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
met
h
o
d
s
f
o
r
i
n
-
v
e
h
i
c
l
e
n
e
t
w
o
r
k
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
t
T
r
a
n
sp
o
rt
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
1
8
4
3
–
1
8
5
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
TS.2
0
2
2
.
3
2
2
2
4
8
6
.
[
2
1
]
A
.
K
a
n
a
d
e
e
t
a
l
.
,
“
A
n
a
l
y
s
i
s o
f
w
i
r
e
l
e
s
s
n
e
t
w
o
r
k
s
e
c
u
r
i
t
y
i
n
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s,”
I
n
d
i
a
n
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
1
,
n
o
.
5
5
,
p
p
.
1
–
1
2
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
5
4
9
0
5
/
d
i
sssi
.
v
2
1
i
5
5
.
e
1
i
j
e
1
6
7
5
.
[
2
2
]
F
.
u
r
R
e
h
m
a
n
a
n
d
C
.
I
z
u
r
i
e
t
a
,
“
S
t
a
t
i
s
t
i
c
a
l
m
e
t
a
m
o
r
p
h
i
c
t
e
s
t
i
n
g
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
s
,
”
i
n
2
0
2
1
I
E
E
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
C
y
b
e
r
S
e
c
u
r
i
t
y
a
n
d
R
e
s
i
l
i
e
n
c
e
(
C
S
R
)
,
J
u
l
.
2
0
2
1
,
p
p
.
2
0
–
26
,
d
o
i
:
1
0
.
1
1
0
9
/
C
S
R
5
1
1
8
6
.
2
0
2
1
.
9
5
2
7
9
9
3
.
[
2
3
]
S
.
T
h
i
a
n
M
e
n
g
,
S
.
Y
o
g
a
r
a
y
a
n
,
S
.
F
a
t
i
mah
A
b
d
u
l
R
a
z
a
k
,
S
.
K
a
n
n
a
n
,
a
n
d
A
.
A
z
ma
n
,
“
A
d
v
a
n
c
e
s
o
f
v
e
h
i
c
u
l
a
r
a
d
h
o
c
n
e
t
w
o
r
k
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
2
,
n
o
.
3
,
p
p
.
1
4
2
6
–
1
4
3
3
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
2
.
i
3
.
p
p
1
4
2
6
-
1
4
3
3
.
[
2
4
]
D
.
K
w
o
n
,
K
.
N
a
t
a
r
a
j
a
n
,
S
.
C
.
S
u
h
,
H
.
K
i
m
,
a
n
d
J.
K
i
m
,
“
A
n
e
mp
i
r
i
c
a
l
st
u
d
y
o
n
n
e
t
w
o
r
k
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
u
si
n
g
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
s,
”
i
n
2
0
1
8
I
EE
E
3
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
D
i
st
r
i
b
u
t
e
d
C
o
m
p
u
t
i
n
g
S
y
s
t
e
m
s
(
I
C
D
C
S
)
,
Ju
l
.
2
0
1
8
,
p
p
.
1
5
9
5
–
1
5
9
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
C
S
.
2
0
1
8
.
0
0
1
7
8
.
[
2
5
]
M
.
T
a
v
a
l
l
a
e
e
,
E
.
B
a
g
h
e
r
i
,
W
.
L
u
,
a
n
d
A
.
A
.
G
h
o
r
b
a
n
i
,
“
A
d
e
t
a
i
l
e
d
a
n
a
l
y
s
i
s
o
f
t
h
e
K
D
D
C
U
P
9
9
d
a
t
a
s
e
t
,
”
i
n
2
0
0
9
I
EEE
S
y
m
p
o
s
i
u
m
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
S
e
c
u
ri
t
y
a
n
d
D
e
f
e
n
se
Ap
p
l
i
c
a
t
i
o
n
s
,
J
u
l
.
2
0
0
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
S
D
A
.
2
0
0
9
.
5
3
5
6
5
2
8
.
[
2
6
]
S
.
C
h
o
u
d
h
a
r
y
a
n
d
N
.
K
e
ssw
a
n
i
,
“
A
n
a
l
y
si
s
o
f
K
D
D
-
C
u
p
’
9
9
,
N
S
L
-
K
D
D
a
n
d
U
N
S
W
-
N
B
1
5
d
a
t
a
se
t
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
i
n
I
o
T,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
7
,
p
p
.
1
5
6
1
–
1
5
7
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
0
.
0
3
.
3
6
7
.
[
2
7
]
N
.
V
.
C
h
a
w
l
a
,
K
.
W
.
B
o
w
y
e
r
,
L.
O
.
H
a
l
l
,
a
n
d
W
.
P
.
K
e
g
e
l
me
y
e
r
,
“
S
M
O
TE
:
s
y
n
t
h
e
t
i
c
mi
n
o
r
i
t
y
o
v
e
r
-
s
a
m
p
l
i
n
g
t
e
c
h
n
i
q
u
e
,
”
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
s
e
a
rc
h
,
v
o
l
.
1
6
,
p
p
.
3
2
1
–
3
5
7
,
J
u
n
.
2
0
0
2
.
[
2
8
]
M
.
H
e
i
g
l
,
E.
W
e
i
g
e
l
t
,
D
.
F
i
a
l
a
,
a
n
d
M
.
S
c
h
r
a
mm
,
“
U
n
su
p
e
r
v
i
s
e
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
f
o
r
o
u
t
l
i
e
r
d
e
t
e
c
t
i
o
n
o
n
s
t
r
e
a
m
i
n
g
d
a
t
a
t
o
e
n
h
a
n
c
e
n
e
t
w
o
r
k
se
c
u
r
i
t
y
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
2
4
,
p
p
.
1
–
3
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
2
4
1
2
0
7
3
.
[
2
9
]
N
.
M
o
u
st
a
f
a
a
n
d
J.
S
l
a
y
,
“
U
N
S
W
-
N
B
1
5
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
d
a
t
a
s
e
t
f
o
r
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
ms
(
U
N
S
W
-
N
B
1
5
n
e
t
w
o
r
k
d
a
t
a
se
t
)
,
”
i
n
2
0
1
5
M
i
l
i
t
a
ry
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
C
o
n
f
e
re
n
c
e
(
M
i
l
C
I
S
)
,
N
o
v
.
2
0
1
5
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
M
i
l
C
I
S
.
2
0
1
5
.
7
3
4
8
9
4
2
.
[
3
0
]
E.
C
h
a
t
z
o
g
l
o
u
,
G
.
K
a
m
b
o
u
r
a
k
i
s,
a
n
d
C
.
K
o
l
i
a
s,
“
Em
p
i
r
i
c
a
l
e
v
a
l
u
a
t
i
o
n
o
f
a
t
t
a
c
k
s
a
g
a
i
n
s
t
I
EEE
8
0
2
.
1
1
e
n
t
e
r
p
r
i
se
n
e
t
w
o
r
k
s:
T
h
e
A
W
I
D
3
d
a
t
a
set
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
3
4
1
8
8
–
3
4
2
0
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
6
1
6
0
9
.
[
3
1
]
F
.
N
u
ss
i
p
o
v
a
,
S
.
R
y
sb
e
k
o
v
,
Z.
A
b
d
i
a
k
h
me
t
o
v
a
,
a
n
d
A
.
K
a
r
t
b
a
y
e
v
,
“
O
p
t
i
mi
z
i
n
g
l
o
ss
f
u
n
c
t
i
o
n
s
f
o
r
i
m
p
r
o
v
e
d
e
n
e
r
g
y
d
e
ma
n
d
p
r
e
d
i
c
t
i
o
n
i
n
sm
a
r
t
p
o
w
e
r
g
r
i
d
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
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
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
3
4
1
5
–
3
4
2
6
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
3
4
1
5
-
3
4
2
6
.
[
3
2
]
N
.
A
ss
y
mk
h
a
n
a
n
d
A
.
K
a
r
t
b
a
y
e
v
,
“
A
d
v
a
n
c
e
d
I
o
T
-
e
n
a
b
l
e
d
i
n
d
o
o
r
t
h
e
r
m
a
l
c
o
mf
o
r
t
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
S
V
M
a
n
d
r
a
n
d
o
m
f
o
r
e
s
t
mo
d
e
l
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
8
,
p
p
.
1
0
4
0
–
1
0
5
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
4
.
0
1
5
0
8
1
0
2
.
[
3
3
]
D
.
P
r
e
u
v
e
n
e
e
r
s
a
n
d
W
.
Jo
o
se
n
,
“
S
h
a
r
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
a
s
i
n
d
i
c
a
t
o
r
s
o
f
c
o
m
p
r
o
m
i
se
f
o
r
c
y
b
e
r
t
h
r
e
a
t
i
n
t
e
l
l
i
g
e
n
c
e
,
”
J
o
u
rn
a
l
o
f
C
y
b
e
r
sec
u
r
i
t
y
a
n
d
Pr
i
v
a
c
y
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
1
4
0
–
1
6
3
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
j
c
p
1
0
1
0
0
0
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
h
y
n
g
g
y
s
Ry
sbek
o
v
is
a
m
o
ti
v
a
ted
st
u
d
e
n
t
p
u
rs
u
in
g
a
b
a
c
h
e
lo
r'
s
d
e
g
re
e
in
in
fo
rm
a
ti
o
n
sy
ste
m
s
a
t
th
e
I
n
tern
a
ti
o
n
a
l
U
n
iv
e
rsit
y
o
f
In
f
o
r
m
a
ti
o
n
Tec
h
n
o
l
o
g
ies
a
n
d
c
o
n
ti
n
u
i
n
g
h
is
e
d
u
c
a
ti
o
n
wi
th
a
m
a
ste
r'
s
in
d
a
ta
sc
ien
c
e
a
t
t
h
e
Ka
z
a
k
h
-
Brit
ish
Tec
h
n
ica
l
Un
iv
e
rsity
.
He
sh
o
ws
in
i
ti
a
ti
v
e
in
h
is
stu
d
ies
a
n
d
h
a
s
i
n
d
e
p
e
n
d
e
n
tl
y
lea
rn
e
d
p
ro
g
ra
m
m
in
g
lan
g
u
a
g
e
s,
i
n
c
lu
d
in
g
HT
M
L,
CS
S
,
Ja
v
a
S
c
ri
p
t,
a
n
d
P
y
t
h
o
n
.
S
h
y
n
g
g
y
s
is
a
c
ti
v
e
in
t
h
e
e
d
u
c
a
ti
o
n
a
l
p
ro
c
e
ss
,
p
a
rt
icip
a
tes
i
n
o
n
l
in
e
c
o
u
rse
s,
a
n
d
is
c
o
m
m
it
ted
t
o
se
lf
-
imp
ro
v
e
m
e
n
t.
Hi
s
p
a
ss
io
n
f
o
r
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
a
n
d
c
o
n
ti
n
u
o
u
s
q
u
e
st
fo
r
k
n
o
wle
d
g
e
h
i
g
h
li
g
h
t
h
is
p
o
te
n
ti
a
l
fo
r
fu
tu
re
p
ro
fe
ss
io
n
a
l
g
ro
wt
h
in
th
e
field
o
f
IT.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
o
b
e
rsh
y
n
g
y
s@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.