I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
2
,
A
p
r
il
2
0
2
0
,
p
p
.
1
5
9
9
~1
6
1
1
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1/
ij
ec
e
.
v
1
0
i
2
.
p
p
1
5
9
9
-
1
6
1
1
1599
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Pree
m
p
tive
m
o
de
lling
tow
a
rds
c
la
ss
ifying
v
ulnera
bil
ity
o
f
DDo
S
a
tt
a
ck
in
SDN
e
n
v
iro
n
m
en
t
Na
re
nd
er
M
.
,
Yuv
a
ra
j
u B
.
N.
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
T
h
e
Na
ti
o
n
a
l
I
n
stit
u
te
o
f
En
g
in
e
e
rin
g
M
y
su
ru
,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
tic
le
his
to
r
y:
R
ec
eiv
ed
Ma
y
3
0
,
2
0
1
9
R
ev
i
s
ed
Oct
1
2
,
2
0
1
9
A
cc
ep
ted
Oct
2
2
,
2
0
1
9
S
o
f
tw
a
r
e
-
De
f
in
e
d
Ne
t
w
o
rk
in
g
(
S
DN
)
h
a
s
b
e
c
o
m
e
a
n
e
ss
e
n
ti
a
l
n
e
tw
o
rk
in
g
c
o
n
c
e
p
t
t
o
w
a
rd
s
e
sc
a
l
a
ti
n
g
th
e
n
e
tw
o
rk
in
g
c
a
p
a
b
il
it
ies
th
a
t
a
re
h
ig
h
ly
d
e
m
a
n
d
e
d
f
u
tu
re
in
tern
e
t
sy
ste
m
,
w
h
ich
is
imm
e
n
se
l
y
d
istri
b
u
ted
in
n
a
tu
re
.
Ow
in
g
to
th
e
n
o
v
e
l
c
o
n
c
e
p
t
in
t
h
e
f
ield
o
f
n
e
t
w
o
rk
,
it
is
stil
l
sh
ro
u
d
e
d
w
it
h
se
c
u
rit
y
p
ro
b
lem
s.
It
is
a
lso
f
o
u
n
d
t
h
a
t
th
e
Distrib
u
ted
De
n
ial
-
of
-
S
e
rv
ice
(DD
o
S
)
a
tt
a
c
k
is
o
n
e
o
f
th
e
p
r
o
m
in
e
n
t
p
ro
b
lem
s
in
th
e
S
DN
e
n
v
iro
n
m
e
n
t.
Af
ter
r
e
v
ie
w
in
g
e
x
isti
n
g
re
s
e
a
rc
h
so
lu
ti
o
n
s
t
o
w
a
rd
s
re
sistin
g
DD
o
S
a
tt
a
c
k
in
S
DN
,
it
is
f
o
u
n
d
th
a
t
stil
l
th
e
re
a
re
m
a
n
y
o
p
e
n
-
e
n
d
issu
e
s.
T
h
e
re
f
o
re
,
th
e
se
issu
e
s
a
re
id
e
n
ti
f
ied
a
n
d
a
re
a
d
d
re
ss
e
d
in
t
h
is
p
a
p
e
r
in
t
h
e
f
o
r
m
o
f
a
p
re
e
m
p
ti
v
e
m
o
d
e
l
o
f
se
c
u
rit
y
.
Diff
e
re
n
t
f
ro
m
e
x
isti
n
g
a
p
p
ro
a
c
h
e
s,
th
is
m
o
d
e
l
is
c
a
p
a
b
le
o
f
id
e
n
ti
fy
in
g
a
n
y
m
a
li
c
io
u
s
a
c
ti
v
it
y
th
a
t
le
a
d
s
to
a
DD
o
S
a
tt
a
c
k
b
y
p
e
rf
o
r
m
in
g
a
c
o
rre
c
t
c
las
si
f
ica
ti
o
n
o
f
a
tt
a
c
k
str
a
teg
y
u
sin
g
a
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
.
T
h
e
p
a
p
e
r
a
lso
d
isc
u
ss
e
s
th
e
a
p
p
li
c
a
b
il
it
y
o
f
b
e
st cla
ss
if
ier
s u
sin
g
m
a
c
h
in
e
lea
rn
in
g
t
h
a
t
is ef
fe
c
ti
v
e
a
g
a
in
st DD
o
S
a
tt
a
c
k
.
K
ey
w
o
r
d
s
:
A
t
tack
Dis
tr
ib
u
ted
d
en
ia
l o
f
s
er
v
ice
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
Ma
ch
i
n
e
lear
n
i
n
g
So
f
t
w
ar
e
d
ef
i
n
e
n
e
t
w
o
r
k
Co
p
y
rig
h
t
©
2
0
2
0
I
n
stit
u
te o
f
Ad
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Nar
en
d
er
M
.
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
T
h
e
Natio
n
al
I
n
s
ti
tu
te
o
f
E
n
g
i
n
ee
r
in
g
,
M
y
s
u
r
u
,
I
n
d
ia
.
E
m
ail:
n
ar
en
d
er
@
n
ie.
ac
.
i
n
1.
I
NT
RO
D
UCT
I
O
N
So
f
t
w
ar
e
-
De
f
in
ed
Net
w
o
r
k
i
n
g
(
SD
N)
h
a
s
b
ee
n
e
v
o
lv
ed
to
ca
ter
u
p
to
th
e
e
x
p
o
n
en
t
i
all
y
in
cr
ea
s
in
g
d
e
m
an
d
s
o
f
th
e
c
lie
n
ts
[
1
,
2
]
.
T
h
ese
r
is
es
o
f
t
h
e
d
e
m
an
d
s
ar
e
ar
is
i
n
g
f
r
o
m
t
h
e
u
s
ag
e
o
f
f
u
tu
r
e
in
ter
n
et
ar
ch
itect
u
r
e,
w
h
ic
h
i
s
v
er
y
d
i
f
f
er
en
t
f
r
o
m
ex
is
ti
n
g
n
e
t
w
o
r
k
i
n
g
s
c
h
e
m
e
s
[
3
]
.
T
h
e
ca
p
ab
ilit
y
o
f
th
e
ce
n
tr
alize
d
ar
ch
itect
u
r
e
u
s
ed
in
t
h
e
n
et
w
o
r
k
i
s
f
u
r
th
er
m
o
r
e
e
n
h
a
n
ce
d
as
it
ca
n
n
o
w
s
e
g
r
e
g
ate
t
h
e
co
n
tr
o
l
p
lan
e
to
f
o
r
w
ar
d
i
n
g
p
lan
e
a
n
d
ca
n
f
u
r
th
er
o
f
f
er
m
o
r
e
ex
te
n
s
i
v
e
p
r
o
g
r
am
m
i
n
g
ca
p
ab
ilit
y
to
th
e
n
et
w
o
r
k
[
4
,
5
]
.
I
r
r
esp
ec
tiv
e
o
f
i
m
m
en
s
e
ad
v
a
n
ta
g
e,
t
h
er
e
ar
e
v
ar
io
u
s
s
ec
u
r
it
y
is
s
u
e
s
as
s
o
ciate
d
w
i
th
t
h
e
SDN
[
6
-
1
0
]
.
A
p
ar
t
f
r
o
m
th
e
p
r
o
b
le
m
ass
o
ciate
d
w
i
th
t
h
e
f
ail
u
r
e
o
f
a
ce
n
tr
ali
ze
d
p
o
in
t
in
th
e
leg
ac
y
ce
n
tr
alize
d
ar
ch
itectu
r
e,
th
e
SD
N
o
f
f
er
s
a
m
ec
h
a
n
is
m
u
s
i
n
g
it
s
co
n
tr
o
ller
s
y
s
te
m
i
n
o
r
d
er
to
s
tu
d
y
th
e
s
ec
u
r
it
y
.
Ho
w
e
v
er
,
th
er
e
i
s
a
lo
n
g
w
a
y
to
g
o
as
SDN
i
s
c
o
m
p
ar
ativ
el
y
a
n
e
w
n
et
w
o
r
k
i
n
g
co
n
ce
p
t
w
h
ic
h
w
ill
r
eq
u
ir
e
m
o
r
e
p
r
o
to
ty
p
in
g
,
m
o
r
e
ex
h
au
s
ti
v
e
i
n
v
esti
g
atio
n
,
an
d
m
o
r
e
v
a
lid
atio
n
i
n
o
r
d
er
to
clai
m
it
s
s
u
cc
e
s
s
f
ac
t
o
r
.
T
h
er
e
is
v
ar
io
u
s
r
ev
ie
w
w
o
r
k
o
n
S
DN
en
v
ir
o
n
m
en
t
to
clai
m
t
h
at
it
i
s
in
f
l
icted
w
it
h
p
o
ten
tia
l
s
ec
u
r
it
y
p
r
o
b
lem
s
[
1
1
-
1
3
]
.
As
SDN
u
s
e
s
th
e
s
o
f
t
w
ar
e
as
th
e
co
r
e
p
ar
t;
th
er
ef
o
r
e,
th
e
r
is
k
o
f
in
tr
u
s
io
n
is
q
u
ite
m
o
r
e
o
v
er
th
e
n
et
w
o
r
k
,
an
d
v
ar
io
u
s
c
h
a
n
g
e
s
o
f
s
ec
u
r
it
y
b
r
ea
ch
es
ca
n
b
e
ex
p
ec
ted
.
I
n
t
h
is
r
e
g
ar
d
,
Dis
tr
ib
u
ted
Den
ia
l
-
of
-
Ser
v
ice
(
DDo
S)
ac
ts
as
a
s
i
n
g
le
p
o
in
t
o
f
atta
ck
w
h
ic
h
al
s
o
in
v
ite
s
v
ar
io
u
s
o
th
er
s
ec
u
r
it
y
b
r
ea
ch
es
to
o
.
T
h
is
is
p
o
s
s
ib
le
as
a
DDo
S
a
ttac
k
p
ar
al
y
ze
t
h
e
en
tire
s
y
s
te
m
o
n
th
e
tar
g
et
n
et
w
o
r
k
b
y
i
lle
g
iti
m
atel
y
ca
p
t
u
r
in
g
t
h
e
co
m
p
lete
av
ailab
ilit
y
o
f
s
u
c
h
a
s
y
s
te
m
.
Su
c
h
attac
k
s
ar
e
q
u
ite
ea
s
ier
t
o
b
e
lau
n
ch
ed
in
SD
N
o
w
i
n
g
to
th
e
p
r
esen
ce
o
f
a
ce
n
tr
alize
d
co
n
tr
o
ller
s
y
s
te
m
t
h
at
co
n
tr
o
ls
t
h
e
e
n
tire
n
et
w
o
r
k
an
d
f
o
r
m
u
la
tes
a
d
ec
is
i
o
n
o
f
a
s
er
v
er
to
b
e
v
icti
m
ized
.
No
r
m
al
l
y
,
w
h
e
n
a
s
w
itc
h
r
ec
eiv
e
s
a
d
ata
p
ac
k
e
t
f
r
o
m
v
ar
io
u
s
tr
a
f
f
ic
f
lo
w
th
a
t
i
s
f
o
u
n
d
to
b
e
q
u
i
te
u
n
m
atc
h
ed
w
it
h
ea
c
h
o
th
er
t
h
an
t
h
e
d
ata
p
ac
k
et
i
s
f
o
r
w
ar
d
e
d
to
th
e
SDN
co
n
tr
o
ller
.
A
tr
a
f
f
ic
f
lo
w
r
u
le
is
t
h
e
n
f
o
r
w
ar
d
ed
b
y
th
e
SDN
co
n
tr
o
ller
th
at
is
co
n
s
tr
u
cted
o
n
t
h
e
b
asis
o
f
t
h
e
ap
p
l
icatio
n
r
u
n
n
i
n
g
o
n
t
h
e
n
et
w
o
r
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
2
,
A
p
r
il 2
0
2
0
:
1
5
9
9
-
1611
1600
I
n
t
h
e
ca
s
e
o
f
DDo
S
attac
k
,
at
tack
er
s
u
s
e
m
u
ltip
le
co
m
p
r
o
m
is
ed
s
y
s
te
m
s
f
o
r
g
e
n
er
ati
n
g
m
ass
i
v
e
s
izes
o
f
d
ata
p
ac
k
ets.
T
h
ese
m
a
s
s
i
v
e
d
ata
p
ac
k
ets
ar
e
f
o
r
w
ar
d
ed
to
th
e
SDN
co
n
tr
o
ller
.
T
h
e
n
u
m
b
er
o
f
in
co
m
i
n
g
r
eq
u
ests
to
th
e
s
er
v
er
w
ill
in
cr
ea
s
e
ex
p
o
n
en
tiall
y
e
n
o
u
g
h
to
co
n
s
u
m
e
t
h
e
co
m
p
lete
r
eso
u
r
ce
s
th
at
ar
e
allo
ca
ted
f
o
r
a
d
ef
in
ed
co
m
m
u
n
icatio
n
c
h
a
n
n
e
l.
T
h
ese
r
eso
u
r
ce
s
ar
e
in
t
er
m
s
o
f
t
h
e
ch
a
n
n
el
ca
p
ac
it
y
,
s
to
r
ag
e,
m
e
m
o
r
y
,
etc.
o
f
t
h
e
r
eg
u
lar
u
s
er
.
O
n
e
o
f
th
e
v
u
l
n
er
ab
le
r
eso
u
r
ce
s
with
i
n
t
h
e
s
w
itc
h
i
s
t
h
e
f
o
r
w
ar
d
in
g
tab
le
ca
p
ac
it
y
.
T
h
is
in
f
o
r
m
a
tio
n
ca
n
b
e
co
m
p
r
o
m
i
s
ed
b
y
t
h
e
a
ttack
er
in
DDo
S.
A
ll
s
o
r
ts
o
f
ille
g
it
i
m
a
te
r
eso
u
r
ce
s
in
itia
te
to
w
ar
d
s
s
atu
r
at
in
g
t
h
e
tab
lesp
ac
e
w
h
e
n
a
m
a
s
s
i
v
e
q
u
an
tit
y
o
f
t
h
e
s
p
o
o
f
ed
p
ac
k
et
s
is
ac
c
u
m
u
lated
in
th
e
n
et
w
o
r
k
s
w
i
tch
.
Fi
n
all
y
,
t
h
e
DDo
S
attac
k
co
m
p
letel
y
c
r
ip
p
les
th
e
co
m
m
u
n
ica
tio
n
lin
k
e
x
is
tin
g
b
et
w
ee
n
th
e
SDN
co
n
tr
o
ller
an
d
th
e
n
et
w
o
r
k
s
w
i
tch
.
T
h
is
c
au
s
es
th
e
f
i
n
al
s
tep
o
f
DDo
S
att
ac
k
d
u
e
to
h
ea
v
ier
co
n
g
es
tio
n
o
f
s
u
c
h
ille
g
iti
m
at
e
tr
af
f
ic.
A
l
th
o
u
g
h
t
h
er
e
is
v
ar
io
u
s
e
x
i
s
tin
g
r
esear
ch
w
o
r
k
,
t
h
e
y
all
h
av
e
it
s
b
en
e
f
it
s
a
s
w
el
l
a
s
a
co
n
s
tr
ai
n
t
w
h
ic
h
let
th
e
DDo
S
p
r
o
b
le
m
s
till
u
n
s
o
l
v
ed
in
p
r
ese
n
t
t
i
m
e.
T
h
e
r
ef
o
r
e,
th
is
p
a
p
er
p
r
esen
t
s
a
s
o
l
u
tio
n
to
s
u
ch
a
p
r
o
b
lem
b
y
d
ev
elo
p
in
g
a
m
at
h
e
m
atica
l
m
o
d
el
to
w
ar
d
s
r
esis
ti
n
g
DDo
S
p
r
o
b
le
m
i
n
SDN.
T
h
e
p
ap
e
r
illu
s
tr
ates
t
h
e
m
o
d
el
w
i
th
a
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
to
o
f
f
er
m
o
r
e
g
ai
n
in
p
r
ev
e
n
ti
v
e
m
ea
s
u
r
es
to
w
ar
d
s
DDo
S.
T
h
e
o
r
g
an
izat
io
n
o
f
th
e
p
ap
er
is
a
s
f
o
llo
w
s
:
Sec
tio
n
1
.
1
d
is
cu
s
s
es
th
e
r
elate
d
w
o
r
k
o
f
ex
i
s
ti
n
g
ap
p
r
o
ac
h
es
to
w
ar
d
r
esis
ti
n
g
DDo
S
attac
k
o
n
SDN
en
v
ir
o
n
m
en
t.
Sec
tio
n
1
.
2
b
r
ief
s
th
e
r
esear
ch
p
r
o
b
lem
s
ad
d
r
ess
ed
in
c
u
r
r
en
t
w
o
r
k
w
h
ile
d
is
c
u
s
s
io
n
o
f
t
h
e
ad
o
p
ted
r
esear
ch
m
et
h
o
d
o
l
o
g
y
is
ca
r
r
ie
d
o
u
t
i
n
Sec
tio
n
2.
A
l
g
o
r
ith
m
d
is
c
u
s
s
io
n
i
s
ca
r
r
ied
o
u
t
in
Sectio
n
3
w
h
ile
r
esu
l
t
d
is
cu
s
s
io
n
i
s
ca
r
r
ied
o
u
t
in
Sectio
n
4
.
Fin
al
l
y
,
th
e
co
n
cl
u
s
i
v
e
r
e
m
ar
k
s
ar
e
m
a
d
e
in
Sectio
n
5
.
T
h
is
s
ec
tio
n
p
r
esen
t
s
a
b
r
ief
i
n
g
o
f
r
esear
c
h
ap
p
r
o
ac
h
es
to
w
ar
d
s
r
esis
ti
n
g
DDo
S
att
ac
k
.
Mo
s
t
r
ec
en
tl
y
,
P
h
a
n
an
d
P
ar
k
[
1
4
]
h
av
e
u
s
ed
a
s
elf
-
o
r
g
a
n
iz
in
g
ma
p
an
d
s
u
p
p
o
r
t
ve
cto
r
ma
ch
in
e
in
o
r
d
er
t
o
in
tr
o
d
u
ce
a
n
o
d
e
clas
s
i
f
icatio
n
co
n
ce
p
t
f
o
r
en
h
a
n
ci
n
g
th
e
r
ate
o
f
DDo
S
attac
k
d
etec
tio
n
o
v
er
SDN
c
lo
u
d
.
An
o
th
er
r
ec
e
n
t
w
o
r
k
o
f
Z
h
u
et
a
l
.
,
[
1
5
]
h
as
s
h
o
w
ca
s
ed
th
e
u
s
a
g
e
o
f
en
cryp
tio
n
ap
p
r
o
a
ch
f
o
r
s
af
e
g
u
ar
d
in
g
p
r
iv
ac
y
w
h
ile
th
e
K
N
N
ap
p
r
o
ac
h
is
u
s
ed
f
o
r
en
h
an
ci
n
g
th
e
ef
f
ic
ien
c
y
o
f
d
etec
tio
n
o
v
er
SDN.
T
h
e
w
o
r
k
o
f
Yu
et
a
l
.
,
[
1
6
]
h
as
p
r
esen
ted
d
etec
tio
n
a
s
w
ell
as
p
r
ev
e
n
t
io
n
m
ec
h
a
n
i
s
m
b
y
co
n
s
tr
u
cti
n
g
a
n
et
w
o
r
k
tab
le
u
s
i
n
g
Op
en
F
lo
w
p
r
o
to
co
l
.
T
h
e
s
t
u
d
y
h
a
s
also
u
s
ed
a
s
u
p
p
o
r
t
ve
cto
r
ma
ch
in
e
f
o
r
t
r
ain
in
g
.
A
co
r
r
e
la
tio
n
-
b
a
s
ed
a
p
p
r
o
a
ch
h
as
b
ee
n
p
r
esen
ted
b
y
Z
h
e
n
g
et
a
l
.
,
[
1
7
]
b
y
u
s
i
n
g
n
et
w
o
r
k
s
w
itc
h
es
d
esi
g
n
ed
u
s
i
n
g
a
co
mme
r
cia
l
o
ff
-
th
e
-
s
h
elf
.
E
x
is
t
in
g
s
y
s
te
m
al
s
o
r
ep
o
r
ts
o
f
u
s
i
n
g
en
tr
o
p
y
-
b
ased
ap
p
r
o
ac
h
es
to
w
ar
d
s
DDo
S
d
etec
tio
n
s
c
h
e
m
e.
T
h
e
w
o
r
k
o
f
Kal
k
a
n
et
a
l
.
,
[
1
8
]
h
as
u
s
ed
a
s
ta
tis
tica
l
s
o
lu
tio
n
th
at
e
n
ab
l
es
th
e
co
n
tr
o
ller
to
g
en
er
ate
a
d
y
n
a
m
ic
r
u
le.
Si
m
p
s
o
n
et
a
l
.
,
[
1
9
]
h
a
v
e
u
s
e
d
a
lo
ca
l
filt
e
r
in
g
s
ch
eme
with
a
m
o
r
e
p
r
ec
is
e
s
p
ec
if
icat
io
n
o
f
co
o
k
ies
as
well
as
p
r
o
o
f
s
.
Dif
f
er
e
n
t
tech
n
o
lo
g
ies
ass
o
ciate
d
w
it
h
m
ac
h
i
n
e
lear
n
i
n
g
ar
e
also
f
o
u
n
d
in
e
x
is
tin
g
ap
p
r
o
ac
h
es.
Ass
i
s
et
a
l
.
[
2
0
]
h
av
e
j
o
in
tly
u
s
ed
g
a
me
th
eo
r
y,
d
ig
ita
l
s
ig
n
a
tu
r
e,
an
d
fu
z
z
y
lo
g
ic
f
o
r
d
ev
elo
p
in
g
an
a
u
to
n
o
m
o
u
s
DDo
S
attac
k
d
etec
ti
o
n
.
A
u
n
iq
u
e
i
m
p
le
m
e
n
tat
io
n
s
c
h
e
m
e
h
as
b
ee
n
p
r
esen
ted
b
y
Yan
et
al
.
,
[
2
1
]
w
h
er
e
a
s
ch
ed
u
lin
g
ap
p
r
o
ac
h
h
as
u
s
ed
as
s
ec
u
r
it
y
ap
p
r
o
ac
h
.
T
h
e
ap
p
r
o
ac
h
ex
tr
ac
ts
d
i
f
f
er
en
t
ti
m
e
v
ar
ia
n
t
in
f
o
r
m
atio
n
o
f
th
e
s
ch
ed
u
les
allo
ca
ted
o
n
th
e
b
asis
o
f
t
h
e
attac
k
s
o
f
D
Do
S
in
te
n
s
it
y
.
Si
m
ilar
w
o
r
k
is
al
s
o
ca
r
r
ied
o
u
t
b
y
L
i
m
et
a
l
.
,
[
2
2
]
w
h
e
r
e
th
e
s
c
h
ed
u
lin
g
ap
p
r
o
ac
h
h
as
b
ee
n
p
r
o
m
o
ted
b
y
t
h
e
a
u
t
h
o
r
as
a
s
ec
u
r
it
y
s
o
l
u
tio
n
.
T
h
e
ap
p
r
o
a
ch
is
ca
p
ab
le
o
f
co
n
f
i
n
i
n
g
th
e
DDo
S
attac
k
f
r
o
m
in
f
ec
ti
n
g
t
h
e
SDN
co
n
tr
o
ller
.
L
a
w
al
a
n
d
Nu
r
a
y
[
2
3
]
h
av
e
p
r
esen
ted
a
tech
n
iq
u
e
w
h
er
e
th
e
p
ac
k
et
f
lo
w
s
ar
e
in
v
esti
g
at
ed
,
an
d
it
lead
s
to
th
e
g
e
n
er
atio
n
o
f
t
h
e
r
u
le
s
e
t
to
th
e
SDN
co
n
tr
o
ller
o
v
er
a
v
ir
tu
al
m
ac
h
in
e.
T
h
e
w
o
r
k
o
f
L
i
m
a
a
n
d
Fer
n
a
n
d
ez
[
2
4
]
h
as
p
r
ese
n
ted
a
s
ta
t
is
tica
l
tec
h
n
iq
u
e
a
s
w
el
l
as
th
e
en
tr
o
p
y
f
ac
to
r
o
f
tr
af
f
ic.
Usa
g
e
o
f
n
etw
o
r
k
fu
n
ctio
n
virt
u
a
liz
a
tio
n
h
a
s
also
b
e
en
p
r
o
v
en
to
as
s
is
t
s
i
n
b
o
o
s
ti
n
g
s
ec
u
r
it
y
s
y
s
te
m
ag
ai
n
s
t
D
Do
S
attac
k
.
T
h
e
wo
r
k
o
f
Z
h
o
u
a
n
d
Gu
o
[
2
5
]
h
as
in
tr
o
d
u
ce
d
a
f
r
a
m
e
w
o
r
k
f
o
r
m
iti
g
ati
n
g
DDo
S
attac
k
b
y
m
o
n
ito
r
i
n
g
t
h
e
n
et
w
o
r
k
tr
a
f
f
ic
to
f
ilter
o
u
t
a
n
y
a
n
o
ma
ly
-
b
a
s
ed
b
eh
a
vio
r
.
A
p
r
ev
e
n
tio
n
-
b
ased
m
ec
h
an
i
s
m
w
a
s
ca
r
r
ied
o
u
t
b
y
Do
n
g
et
a
l
.
,
[
2
6
]
w
h
er
e
th
e
tr
af
f
ic
f
lo
w
i
s
class
i
f
ied
f
o
r
th
e
p
u
r
p
o
s
e
o
f
s
eq
u
en
tia
l
p
r
o
b
a
b
ilit
y
d
ec
is
io
n
m
a
k
i
n
g
.
A
n
o
t
h
er
s
t
u
d
y
c
ar
r
ied
o
u
t
b
y
Ho
n
g
et
a
l
.
,
[
2
7
]
h
av
e
ad
d
r
ess
ed
th
e
p
r
o
b
lem
o
f
s
lo
w
DDo
S,
w
h
ic
h
in
v
ite
s
all
f
o
r
m
o
f
let
h
al
th
r
ea
ts
to
w
ar
d
s
th
e
w
eb
s
er
v
er
.
T
h
e
s
o
lu
tio
n
p
r
esen
ted
b
y
t
h
e
au
t
h
o
r
is
m
ain
l
y
a
d
ef
e
n
s
e
s
y
s
te
m
to
id
e
n
ti
f
y
a
n
d
r
esis
t
th
e
s
lo
w
m
o
d
e
attac
k
p
atter
n
o
f
DDo
S.
Usa
g
e
o
f
n
et
w
o
r
k
f
u
n
ctio
n
v
ir
tu
a
lizatio
n
is
a
ls
o
s
e
en
i
n
t
h
e
w
o
r
k
o
f
H
y
u
n
et
a
l
.
,
[
2
8
]
f
o
r
r
esis
tin
g
s
ec
u
r
it
y
b
r
ea
c
h
es.
T
h
e
au
th
o
r
s
h
av
e
d
ev
elo
p
ed
a
th
r
esh
o
ld
-
b
a
s
ed
mec
h
a
n
is
m
w
h
ic
h
u
n
b
lo
c
k
s
t
h
e
r
eg
u
lar
d
ata
p
ac
k
ets
an
d
b
lo
ck
th
e
s
u
s
p
i
cio
u
s
d
ata
p
ac
k
ets
f
o
r
b
ein
g
cir
cu
lated
in
th
e
n
et
w
o
r
k
.
T
h
e
s
tu
d
y
to
w
ar
d
s
th
e
r
esis
ta
n
ce
m
ea
s
u
r
es
ag
ai
n
s
t
D
Do
S
attac
k
s
o
n
t
h
e
SD
N
s
y
s
te
m
i
s
ca
r
r
ied
o
u
t
b
y
Kalk
a
n
et
a
l
.
,
[
2
9
]
.
A
cc
o
r
d
in
g
to
th
e
s
t
u
d
y
,
it
ca
n
b
e
s
aid
t
h
at
r
e
s
ea
r
ch
w
o
r
k
ca
r
r
ied
o
u
t
o
n
o
r
b
ef
o
r
e
t
h
e
y
ea
r
2
0
1
7
h
as
b
ee
n
ass
o
ciate
d
w
it
h
d
i
v
er
s
i
f
ied
f
e
atu
r
es
w
h
er
e
v
er
y
les
s
n
u
m
b
e
r
o
f
w
o
r
k
i
s
f
o
cu
s
s
ed
co
m
b
i
n
ed
o
n
d
etec
tio
n
a
n
d
m
iti
g
atio
n
.
T
h
e
s
t
u
d
y
ca
r
r
ied
o
u
t
b
y
K
u
er
b
an
et
a
l
.
,
[
3
0
]
h
as
e
m
p
h
asized
o
n
F
lo
w
S
ec
,
wh
ic
h
is
an
ap
p
r
o
ac
h
f
o
r
r
esis
ti
n
g
Do
S
t
h
r
e
at
o
n
t
h
e
co
n
tr
o
ller
.
Stu
d
y
co
n
s
id
er
in
g
r
eso
u
r
ce
as
th
e
f
ac
to
r
to
id
en
tify
DDo
S
th
r
ea
t
i
s
ca
r
r
ied
o
u
t
b
y
Xu
an
d
L
iu
[
3
1
]
th
at
is
ca
r
r
ied
o
u
t
w
h
ile
m
o
n
ito
r
in
g
th
e
n
e
ig
h
b
o
r
in
g
n
o
d
es.
Dao
et
a
l
.
,
[
3
2
]
h
av
e
p
r
ese
n
ted
a
m
ec
h
an
i
s
m
t
o
s
u
r
v
eil
t
h
e
d
ata
p
ac
k
ets
g
en
er
ated
f
r
o
m
t
h
e
s
w
i
tch
e
s
f
o
llo
w
ed
b
y
co
n
d
itio
n
al
ch
ec
k
in
g
i
f
t
h
e
p
ac
k
e
ts
m
atc
h
w
it
h
t
h
e
s
ec
u
r
it
y
lo
g
ic
p
r
esen
ted
.
B
lo
ck
i
n
g
an
d
u
n
b
lo
c
k
i
n
g
o
f
p
ac
k
et
s
ar
e
f
o
llo
w
ed
b
y
th
i
s
as
a
s
o
l
u
ti
o
n
to
w
ar
d
s
DDo
S
at
tack
.
Sa
r
av
an
a
n
et
a
l
.
,
[
3
3
]
h
av
e
d
em
o
n
s
tr
ated
a
n
o
v
e
l
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:
2
0
8
8
-
8708
P
r
ee
mp
tive
mo
d
ellin
g
to
w
a
r
d
s
cla
s
s
ifyin
g
vu
ln
era
b
ilit
y
o
f D
Do
S
a
tta
ck
in
S
DN
en
viro
n
men
t
(
N
a
r
en
d
er M
.
)
1601
s
tr
u
ct
u
r
e
to
r
ed
u
ce
DDo
S
v
u
ln
er
ab
itie
s
i
n
to
t
h
e
clo
u
d
en
v
ir
o
n
m
en
t.So
f
ia
e
t
a
l
.
,
[
3
4
]
h
av
e
p
r
ese
n
ted
co
n
s
tr
u
c
t
iv
e
r
o
u
ter
h
elp
ed
co
n
g
esti
o
n
co
n
tr
o
l
f
o
r
th
e
So
f
t
w
a
r
e
d
ef
in
ed
n
e
t
w
o
r
k
i
n
g
(
S
DN)
.
A
l
i
et
a
l
.
,
[
3
5
]
h
av
e
f
o
cu
s
ed
o
n
L
o
ad
b
alan
ci
n
g
in
to
th
e
d
ata
ce
n
ter
f
o
r
So
f
t
w
ar
e
d
ef
in
ed
n
et
w
o
r
k
in
g
.
T
h
er
ef
o
r
e,
th
er
e
ar
e
v
ar
io
u
s
s
tu
d
ie
s
ca
r
r
ied
o
u
t
to
w
ar
d
s
r
esis
ti
n
g
DDo
S
at
tac
k
o
v
er
th
e
SDN
en
v
ir
o
n
m
e
n
t.
Var
io
u
s
a
p
p
r
o
ac
h
es
p
r
esen
ted
b
y
t
h
e
r
esear
ch
er
s
d
o
h
av
e
th
eir
ad
v
an
tag
e
s
as
w
e
ll
as
li
m
itatio
n
.
T
h
e
n
ex
t
s
ec
tio
n
h
i
g
h
lig
h
ts
t
h
e
r
esear
c
h
p
r
o
b
lem
s
t
h
at
ar
e
co
n
s
tr
u
cted
af
ter
r
ev
ie
w
i
n
g
th
e
e
x
i
s
ti
n
g
s
y
s
te
m
.
Fo
llo
w
i
n
g
ar
e
th
e
r
es
ea
r
ch
g
a
p
s
th
at
h
a
v
e
b
ee
n
ev
o
l
v
ed
w
h
ile
s
t
u
d
y
i
n
g
ex
i
s
ti
n
g
m
et
h
o
d
o
lo
g
ies
as
w
el
l a
s
r
esu
lts
o
b
tain
ed
b
y
t
h
e
m
:
a.
F
ew
S
ta
n
d
a
r
d
R
esea
r
ch
W
o
r
k
:
T
h
er
e
is
n
o
d
o
u
b
t
o
f
th
e
p
r
esen
ce
o
f
r
esear
ch
-
b
ased
s
o
lu
tio
n
to
w
ar
d
s
DDo
S
attac
k
i
n
th
e
co
n
te
x
t
o
f
SDN
[
3
6
,
3
7
]
.
Ho
w
e
v
er
,
a
clo
s
er
lo
o
k
w
ill
s
h
o
w
t
h
at
t
h
er
e
i
s
n
o
s
ig
n
i
f
ica
n
t n
o
v
elt
y
in
t
h
e
ap
p
r
o
ac
h
es.
b.
Defin
ed
E
xe
cu
tio
n
:
E
x
is
tin
g
s
o
lu
tio
n
s
to
w
ar
d
s
r
esis
ti
n
g
DDo
S
is
o
n
l
y
s
u
cc
e
s
s
f
u
l
in
th
e
p
r
ed
ef
in
ed
in
f
o
r
m
atio
n
ab
o
u
t
th
e
attac
k
s
tr
ateg
y
i
s
k
n
o
w
n
to
th
e
co
n
tr
o
ller
.
Su
c
h
ap
p
r
o
ac
h
es
ar
e
n
o
t
ap
p
licab
le
in
o
r
d
er
to
s
to
p
th
e
d
y
n
a
m
ic
atta
ck
s
ce
n
ar
io
,
w
h
ic
h
is
co
m
p
le
x
in
a
d
is
tr
ib
u
ted
s
y
s
te
m
.
c.
Les
s
s
co
p
e
o
f
Ma
ch
in
e
Lea
r
n
in
g
:
Ma
ch
i
n
e
lear
n
i
n
g
is
tr
e
m
e
n
d
o
u
s
l
y
g
ai
n
i
n
g
s
u
cc
ess
i
n
s
o
lv
in
g
a
co
m
p
le
x
p
r
o
b
le
m
.
T
h
is
asp
e
ct
ca
n
n
o
t
b
e
s
e
e
n
i
n
r
ea
lit
y
wh
en
i
t
co
m
es
to
d
ev
e
lo
p
in
g
r
e
s
is
ta
n
ce
ag
a
in
s
t
DDo
S
attac
k
.
I
t
i
s
b
ec
au
s
e
t
h
e
attac
k
m
o
d
el
i
s
q
u
ite
co
m
p
lex
,
w
h
ich
f
u
r
t
h
er
co
m
p
licat
es
t
h
e
tr
ai
n
in
g
p
r
o
ce
s
s
.
d.
La
ck
o
f
a
d
ve
r
s
a
r
ia
l
mo
d
elin
g
:
1
0
0
%
o
f
all
t
h
e
r
esear
c
h
wo
r
k
is
ca
r
r
ied
o
u
t
in
th
e
ex
i
s
t
in
g
s
y
s
te
m
b
y
ass
u
m
in
g
t
h
e
ad
v
er
s
ar
ial
m
o
d
el
b
u
t
n
o
t
m
o
d
elin
g
i
t.
T
h
e
ex
i
s
ti
n
g
s
o
l
u
tio
n
is
s
u
cc
es
s
f
u
l
o
n
l
y
w
h
e
n
ea
v
esd
r
o
p
an
d
th
e
o
n
e
-
by
-
o
n
e
s
y
s
te
m
is
co
m
p
r
o
m
i
s
ed
u
n
til
it
lead
s
to
th
e
v
ict
i
m
s
er
v
er
.
Ho
w
e
v
er
,
an
ad
v
er
s
ar
y
ca
n
ad
o
p
t
an
y
n
u
m
b
er
o
f
s
tr
ate
g
y
to
i
n
itiate
o
r
lau
n
c
h
a
n
attac
k
,
w
h
ile
th
i
s
i
s
th
e
in
s
ta
n
t
o
f
ti
m
e
w
h
ic
h
r
eq
u
ir
es
to
b
e
id
en
ti
f
ied
.
U
n
f
o
r
t
u
n
ate
l
y
,
th
er
e
is
n
o
ex
is
ti
n
g
s
y
s
te
m
w
h
ich
ad
d
r
ess
ed
th
i
s
p
r
o
b
lem
.
Hen
ce
,
t
h
er
e
i
s
a
n
ee
d
o
f
“a
co
mp
u
ta
tio
n
a
l
mo
d
el
w
h
ich
ca
n
o
ffer
p
r
ee
mp
tive
mea
s
u
r
e
fo
r
ea
r
ly
id
en
tifi
ca
tio
n
fo
llo
w
in
g
b
y
r
esis
tin
g
DDo
S
a
tta
ck
in
S
DN
en
viro
n
men
t
.
”
T
h
e
n
ex
t
s
ec
tio
n
b
r
ie
f
s
o
f
th
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
ad
o
p
ted
as a
s
o
lu
tio
n
to
th
is
p
r
o
b
le
m
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
O
L
O
G
Y
T
h
e
p
r
o
p
o
s
ed
s
tu
d
y
i
s
d
esig
n
ed
an
d
d
ev
elo
p
ed
u
s
in
g
an
al
y
tical
r
esear
ch
m
eth
o
d
o
lo
g
y
wh
er
e
b
o
th
e
m
p
ir
ical
a
n
d
s
i
m
p
li
f
ied
m
at
h
e
m
atica
l
ap
p
r
o
ac
h
h
a
s
b
ee
n
u
s
ed
.
T
h
e
co
m
p
lete
p
la
n
n
i
n
g
o
f
i
m
p
le
m
e
n
tatio
n
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
is
b
ased
o
n
th
e
f
ac
t
t
h
at
it
is
q
u
i
te
ch
alle
n
g
in
g
to
d
if
f
er
en
t
iate
a
r
eg
u
la
r
n
o
d
e
o
r
m
ali
cio
u
s
n
o
d
e
p
r
esen
ce
i
n
SDN
a
n
d
d
i
f
f
er
en
tiat
in
g
t
h
e
m
is
a
q
u
ite
c
h
alle
n
g
in
g
ta
s
k
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
f
o
r
m
u
lates
co
n
cr
ete
c
h
ar
ac
ter
is
tics
o
f
DDo
S
at
tack
in
SDN
w
h
er
e
ch
a
n
n
el
ca
p
ac
itie
s
,
as
w
el
l
as
a
b
u
f
f
er
o
f
th
e
n
o
d
es
i
n
SDN,
ar
e
tar
g
e
ted
to
b
e
ex
h
a
u
s
ted
.
He
n
ce
,
th
e
p
r
o
p
o
s
ed
s
t
u
d
y
d
e
v
elo
p
s
a
s
i
m
p
le
f
o
r
m
o
f
m
at
h
e
m
atica
l
m
o
d
eli
n
g
w
h
er
e
t
w
o
ca
s
e
s
t
u
d
ies
ar
e
s
elec
ted
v
iz.
a
)
ca
s
e
-
1
r
ep
r
esen
ts
t
h
e
p
r
im
ar
y
v
u
ln
er
ab
le
s
ce
n
ar
io
o
f
DDo
S
a
ttack
t
h
at
s
i
g
n
i
f
ica
n
tl
y
d
ep
letes
t
h
e
c
h
an
n
e
l
ca
p
ac
it
y
as
s
h
o
w
n
in
F
ig
u
r
e
1
(
a)
an
d
(
b
)
ca
s
e
-
2
r
ep
r
esen
ts
t
h
e
v
u
ln
er
a
b
le
s
ec
o
n
d
ar
y
s
ce
n
ar
io
o
f
D
Do
S
w
h
ic
h
o
v
er
-
s
atu
r
ate
th
e
m
e
m
o
r
y
s
y
s
te
m
o
f
th
e
n
o
d
es
p
r
esen
t
i
n
SD
N
as
s
h
o
w
n
in
Fi
g
u
r
e
1
(
b
)
.
T
h
e
co
m
p
lete
i
m
p
le
m
en
ta
tio
n
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
d
ev
elo
p
e
d
u
s
i
n
g
th
r
ee
d
if
f
er
e
n
t
s
tag
e
s
.
T
h
e
fir
s
t
s
ta
g
e
o
f
i
m
p
le
m
en
ta
tio
n
i
s
ab
o
u
t
f
o
r
m
u
lati
n
g
a
s
i
m
p
li
f
ied
ex
p
r
ess
io
n
f
o
r
co
m
p
u
ti
n
g
th
e
cu
m
u
la
tiv
e
in
tr
u
s
io
n
t
h
at
co
n
s
id
er
s
b
o
th
th
e
ca
s
e
s
t
u
d
ies.
T
h
e
o
u
tco
m
e
o
f
th
i
s
s
tu
d
y
as
s
is
t
s
i
n
o
b
tain
in
g
a
q
u
alitati
v
e
v
a
lu
e
o
f
t
h
e
DDo
S
att
ac
k
o
n
th
e
SDN
n
o
d
e.
T
h
e
co
m
p
lete
f
o
r
m
u
latio
n
o
f
th
e
c
u
m
u
lat
iv
e
i
n
tr
u
s
io
n
is
ca
r
r
ied
o
u
t o
n
th
e
b
asis
o
f
p
r
o
b
ab
ilit
y
th
eo
r
y
f
o
r
co
m
p
r
eh
e
n
s
iv
e
i
n
f
er
en
ce
ab
o
u
t
th
e
at
tack
clas
s
i
f
icatio
n
.
T
h
e
s
ec
o
n
d
s
tag
e
o
f
i
m
p
le
m
e
n
tati
o
n
is
ab
o
u
t
co
n
s
tr
u
cti
n
g
m
at
h
e
m
atica
l
ex
p
r
es
s
io
n
alo
n
g
w
it
h
co
n
d
itio
n
to
w
ar
d
s
m
ea
s
u
r
i
n
g
th
e
p
r
o
b
ab
ilit
y
o
f
attac
k
co
n
s
id
er
in
g
b
o
th
th
e
ca
s
e
o
f
D
Do
S
attac
k
s
ce
n
ar
io
.
I
n
t
h
e
ca
s
e
o
f
d
eg
r
a
d
atio
n
o
f
c
h
an
n
el
ca
p
ac
it
y
,
t
h
e
p
r
o
m
i
n
e
n
t
p
ar
a
m
eter
s
th
at
a
r
e
af
f
ec
ted
d
u
r
in
g
th
e
attac
k
s
ar
e
th
e
s
ize
o
f
d
a
ta
f
o
r
w
ar
d
ed
f
o
r
m
alicio
u
s
a
s
w
el
l
as
a
r
eg
u
lar
n
o
d
e
as
t
h
e
y
te
n
d
to
r
em
ai
n
th
e
s
a
m
e.
I
t
is
b
ec
au
s
e
t
h
e
ad
v
er
s
ar
y
d
o
esn
'
t
o
f
f
er
an
y
ch
an
ce
s
to
g
et
t
h
e
m
id
en
ti
f
ied
b
y
d
i
f
f
er
e
n
t
s
ize
o
f
p
ac
k
et
f
r
o
m
a
r
eg
u
lar
n
o
d
e
d
u
r
in
g
f
lo
o
d
in
g
th
e
s
er
v
er
w
i
th
i
ter
ativ
e
f
lo
o
d
in
g
p
ac
k
e
t
s
f
r
o
m
a
d
i
f
f
er
e
n
t
d
ir
ec
tio
n
.
An
o
th
er
s
ig
n
i
f
ica
n
t
an
d
d
ep
en
d
ab
le
p
ar
am
eter
co
n
s
id
er
ed
is
b
u
f
f
er
ti
m
e
o
f
b
o
th
r
eg
u
lar
an
d
m
alicio
u
s
n
o
d
e,
w
h
ich
i
s
co
m
p
u
ted
as
th
e
ti
m
e
o
f
t
w
o
p
ac
k
ets
f
o
r
w
ar
d
ed
b
y
t
h
e
s
a
m
e
n
o
d
e.
T
h
is
p
ar
a
m
eter
o
f
b
u
f
f
er
ti
m
e
is
u
tili
ze
d
i
n
a
s
s
ess
i
n
g
th
e
r
esp
ec
ti
v
e
b
u
f
f
er
r
ate
o
f
th
e
m
alicio
u
s
as
w
ell
a
s
a
r
eg
u
lar
n
o
d
e
o
n
th
e
p
er
s
p
ec
tiv
e
o
f
t
h
e
v
ic
ti
m
n
o
d
e.
A
p
ar
t
f
r
o
m
th
is
,
u
n
-
u
tili
ze
d
ch
an
n
el
ca
p
ac
it
y
co
n
s
u
m
p
t
io
n
is
a
n
o
th
er
d
ep
en
d
ab
le
attr
ib
u
te
t
h
at
is
u
s
ed
in
m
at
h
e
m
atica
l
m
o
d
eli
n
g
in
o
r
d
er
t
o
co
m
p
u
te
t
h
e
cr
itica
lit
y
s
co
r
e
o
f
DDo
S
attac
k
.
I
n
t
h
e
ca
s
e
o
f
d
ec
lin
ati
o
n
o
f
th
e
b
u
f
f
er
o
f
t
h
e
v
icti
m
n
o
d
e,
th
e
d
ep
en
d
ab
le
p
ar
am
et
er
r
em
ai
n
s
th
e
s
a
m
e
ex
ce
p
t
th
e
y
ar
e
c
h
o
o
s
es
o
n
t
h
e
co
n
tex
t
o
f
t
h
e
b
u
f
f
er
v
alu
e
o
f
th
e
r
esp
ec
ti
v
e
n
o
d
es.
T
h
e
to
tal
s
ize
o
f
th
e
b
u
f
f
er
o
f
th
e
v
ic
ti
m
n
o
d
e
i
s
an
o
t
h
er
ess
e
n
tial
p
ar
a
m
e
ter
th
a
t
is
u
s
e
d
in
f
o
r
m
u
latio
n
to
w
ar
d
s
ass
e
s
s
i
n
g
th
e
cr
iticalit
y
s
co
r
e.
T
h
e
th
ir
d
s
ta
g
e
o
f
i
m
p
l
e
m
e
n
tatio
n
i
s
as
s
o
ciate
d
w
i
th
ap
p
ly
i
n
g
th
e
m
ac
h
i
n
e
lear
n
i
n
g
ap
p
r
o
ac
h
in
o
r
d
er
to
o
p
tim
ize
t
h
e
cla
s
s
i
f
icati
o
n
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
i
th
r
esp
ec
t to
t
h
e
DDo
S
attac
k
s
ce
n
ar
io
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
2
,
A
p
r
il 2
0
2
0
:
1
5
9
9
-
1611
1602
SDN.
T
h
e
i
m
p
l
icatio
n
o
f
m
a
ch
i
n
e
lear
n
in
g
i
s
a
n
o
th
er
m
e
ch
an
is
m
o
f
b
etter
C
la
s
s
i
f
ica
ti
o
n
o
f
t
h
e
co
m
p
lex
v
ar
iab
les
a
n
d
estab
li
s
h
e
s
a
r
o
b
u
s
t
r
ela
tio
n
s
h
ip
a
m
o
n
g
t
h
e
v
ar
iab
les.
T
h
e
r
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
er
f
o
r
m
s
a
g
r
o
u
p
-
w
i
s
e
an
al
y
s
i
s
o
f
th
e
o
u
tco
m
es
o
f
c
u
m
u
la
tiv
e
i
n
tr
u
s
io
n
v
al
u
e,
f
o
llo
w
ed
b
y
ass
es
s
in
g
th
e
s
i
m
ilar
it
y
s
co
r
e
o
f
th
ese
p
ar
am
e
ter
s
in
th
e
g
r
o
u
p
.
T
h
is
s
ig
n
if
ican
t
l
y
a
s
s
i
s
ts
i
n
b
etter
class
if
icati
o
n
p
r
o
ce
s
s
to
w
ar
d
s
s
tu
d
y
in
g
in
tr
u
s
io
n
m
ec
h
a
n
i
s
m
i
n
DDo
S.
A
p
ar
t
f
r
o
m
t
h
is
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
c
o
n
tr
ib
u
tes
to
w
ar
d
s
a
q
u
alitati
v
e
in
v
esti
g
atio
n
to
w
ar
d
s
ex
p
lo
r
in
g
t
h
e
i
m
p
ac
t
o
f
m
ac
h
in
e
lear
n
i
n
g
to
w
ar
d
s
th
e
class
i
f
icat
io
n
p
er
f
o
r
m
a
n
ce
o
f
th
e
DDo
S
att
ac
k
in
SDN.
Di
f
f
er
e
n
t
f
r
o
m
an
y
e
x
is
ti
n
g
s
y
s
te
m
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
a
co
m
p
r
eh
e
n
s
i
v
e
in
s
ig
h
t
to
t
h
e
p
o
ten
tial
c
ap
ab
ilit
ies
o
f
m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
es.
F
i
g
u
r
e
1
a
n
d
F
i
g
u
r
e
2
d
is
cu
s
s
t
h
e
o
p
er
atio
n
f
lo
w
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
i
th
r
esp
ec
t
to
ca
s
e
s
tu
d
y
an
d
ad
o
p
tio
n
o
f
m
ac
h
i
n
e
lear
n
in
g
m
ec
h
a
n
i
s
m
.
C
a
s
e
-
1
:
D
e
g
r
a
d
a
t
i
o
n
o
f
C
h
a
n
n
e
l
C
a
p
a
c
i
t
y
α
c
c
a
p
=
g
1
/
g
2
)
(
1
rn
mn
t
1
1
.
u
g
u
u
i
i
i
g
0
2
!
!
1
1
u
u
rn
rn
rn
b
s
mn
mn
mn
b
s
I
n
c
a
s
e
o
f
D
D
o
S
a
t
t
a
c
k
s
m
n
=
s
r
n
=
s
c
t
ot
a
l
c
b
s
=
c
o
n
s
t
a
n
t
0
1
rn
b
u
cc
a
p
1
mn
c
c
a
p
b
1
I
n
f
e
r
e
n
c
e
mn
rn
to
tal
mn
s
rn
s
mn
b
rn
b
=
c
h
a
n
n
e
l
c
a
p
a
c
i
t
y
u
t
i
l
i
z
e
d
b
y
m
a
l
i
c
i
o
u
s
n
o
d
e
=
c
h
a
n
n
e
l
c
a
p
a
c
i
t
y
u
t
i
l
i
z
e
d
b
y
r
e
g
u
l
a
r
n
o
d
e
=
t
o
t
a
l
c
h
a
n
n
e
l
c
a
p
a
c
i
t
y
=
s
i
z
e
o
f
p
a
c
k
e
t
f
o
r
D
D
o
S
a
t
t
a
c
k
e
r
n
o
d
e
=
s
i
z
e
o
f
p
a
c
k
e
t
f
o
r
r
e
g
u
l
a
r
n
o
d
e
=
b
u
f
f
e
r
t
i
m
e
D
D
o
S
a
t
t
a
c
k
e
r
n
o
d
e
=
b
u
f
f
e
r
t
i
m
e
f
o
r
r
e
g
u
l
a
r
n
o
d
e
=
u
n
-
u
t
i
l
i
z
e
d
C
h
a
n
n
e
l
C
a
p
a
c
i
t
y
u
C
o
n
d
i
t
i
o
n
t
o
c
o
n
s
i
d
e
r
u
n
d
e
r
D
D
o
S
a
t
t
a
c
k
(
a)
C
a
s
e
-
2
:
D
e
p
l
e
t
i
o
n
o
f
B
u
f
f
e
r
I
n
c
a
s
e
o
f
D
D
o
S
a
t
t
a
c
k
s
m
n
=
s
r
n
=
s
c
0
1
rn
b
α
b
u
f
f
=
h
1
/
h
2
t
b
t
h
1
t
b
o
i
i
i
h
!
2
rn
mn
mn
mn
mn
b
s
t
b
uff
1
mn
b
u
f
f
b
1
mn
b
1
rn
rn
rn
b
s
C
o
n
d
i
t
i
o
n
t
o
c
o
n
s
i
d
e
r
u
n
d
e
r
D
D
o
S
a
t
t
a
c
k
I
n
f
e
r
e
n
c
e
mn
s
rn
s
mn
b
rn
b
=
s
i
z
e
o
f
p
a
c
k
e
t
f
o
r
D
D
o
S
a
t
t
a
c
k
e
r
n
o
d
e
=
s
i
z
e
o
f
p
a
c
k
e
t
f
o
r
r
e
g
u
l
a
r
n
o
d
e
=
b
u
f
f
e
r
t
i
m
e
D
D
o
S
a
t
t
a
c
k
e
r
n
o
d
e
=
b
u
f
f
e
r
t
i
m
e
f
o
r
r
e
g
u
l
a
r
n
o
d
e
t
=
t
o
t
a
l
b
u
f
f
e
r
o
f
v
i
c
t
i
m
n
o
d
e
(
b
)
Fig
u
r
e
1
.
E
x
tr
ac
tin
g
i
n
f
er
e
n
ce
f
o
r
DDo
S a
ttack
i
n
p
r
o
p
o
s
ed
s
y
s
te
m
,
(
a)
Ma
th
e
m
atica
l c
o
m
p
u
ta
tio
n
al
f
lo
w
f
o
r
ca
s
e
-
1
,
(
b
)
Ma
th
e
m
atica
l c
o
m
p
u
ta
tio
n
al
f
lo
w
f
o
r
ca
s
e
-
2
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:
2
0
8
8
-
8708
P
r
ee
mp
tive
mo
d
ellin
g
to
w
a
r
d
s
cla
s
s
ifyin
g
vu
ln
era
b
ilit
y
o
f D
Do
S
a
tta
ck
in
S
DN
en
viro
n
men
t
(
N
a
r
en
d
er M
.
)
1603
A
p
p
l
y
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
G
r
o
u
p
-
1
G
r
o
u
p
-
1
G
r
o
u
p
-
m
S
i
m
i
l
a
r
i
t
y
M
e
a
s
u
r
e
-
1
S
i
m
i
l
a
r
i
t
y
M
e
a
s
u
r
e
-
2
S
i
m
i
l
a
r
i
t
y
M
e
a
s
u
r
e
-
m
S
i
m
i
l
a
r
i
t
y
M
e
a
s
u
r
e
I
f
S
i
m
i
l
a
r
i
t
y
i
n
M
i
n
i
m
a
l
C
o
n
f
i
r
m
D
D
o
S
A
t
t
a
c
k
o
n
S
D
N
N
o
d
e
S
a
f
e
S
D
N
N
o
d
e
F
o
r
c
a
s
e
-
1
F
o
r
c
a
s
e
-
2
C
o
m
p
u
t
e
C
u
m
u
l
a
t
i
v
e
I
n
t
r
u
s
i
o
n
N
e
t
w
o
r
k
D
e
p
l
o
y
m
e
n
t
S
t
a
r
t
-
-
-
-
-
-
S
t
o
p
T
F
Fig
u
r
e
2
.
P
r
o
ce
s
s
f
lo
w
o
f
DDo
S
attac
k
co
n
f
ir
m
atio
n
u
s
in
g
m
ac
h
i
n
e
lear
n
i
n
g
3.
AL
G
O
RI
T
H
M
DE
SI
G
N
T
h
e
p
r
im
e
m
o
ti
v
e
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
to
ca
r
r
y
o
u
t
a
d
is
cr
ete
an
al
y
s
is
o
f
t
h
e
DDo
S
attac
k
a
n
d
its
ad
v
er
s
ar
ial
i
m
p
ac
t
o
v
er
t
h
e
n
o
d
es
w
it
h
S
DN.
T
h
e
co
m
p
lete
d
esig
n
s
tr
ate
g
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
ca
r
r
ied
o
u
t
o
n
th
e
b
asis
th
at
a
DDo
S
attac
k
w
i
ll
lead
to
s
er
io
u
s
d
eg
r
ad
ati
o
n
o
f
th
e
s
er
v
ices
r
ela
y
ed
f
r
o
m
th
e
s
er
v
er
to
b
e
v
icti
m
ized
.
D
ev
elo
p
in
g
t
h
is
s
ce
n
ar
io
o
f
th
e
attac
k
er
is
ess
e
n
t
ia
l a
s
it
w
ill a
s
s
is
t i
n
ca
r
r
y
i
n
g
o
u
t
a
q
u
alitati
v
e
an
al
y
s
i
s
o
f
th
e
i
m
p
ac
t
o
f
attac
k
s
tr
ateg
ies
o
n
th
e
s
er
v
er
.
T
h
is
n
et
w
o
r
k
p
er
f
o
r
m
a
n
ce
w
ill
also
d
ir
ec
tl
y
co
n
tr
ib
u
te
to
w
ar
d
s
b
etter
id
en
tific
atio
n
p
r
o
ce
s
s
o
f
DDo
S
attac
k
.
Fro
m
t
h
eo
r
etica
l
u
n
d
er
s
ta
n
d
i
n
g
,
it
i
s
w
el
l
k
n
o
w
n
th
a
t
w
h
en
t
h
e
le
g
iti
m
a
te
clie
n
ts
ar
e
d
e
n
ied
ac
ce
s
s
o
v
er
t
h
e
s
er
v
er
,
th
er
e
i
s
a
s
tate
o
f
tr
e
m
en
d
o
u
s
r
eso
u
r
ce
d
ep
letio
n
o
f
th
e
s
er
v
er
as
a
p
ar
t
o
f
attac
k
s
tr
ate
g
y
.
Su
ch
f
o
r
m
s
o
f
d
ep
letio
n
o
f
r
eso
u
r
ce
s
co
u
ld
b
e
ca
r
r
ied
o
u
t
o
v
er
c
h
an
n
el
ca
p
ac
it
y
o
r
n
o
d
e
b
u
f
f
er
(
v
icti
m
)
.
T
h
e
p
r
o
ce
s
s
i
s
f
u
r
th
er
o
p
ti
m
ized
b
y
allo
w
i
n
g
a
m
ac
h
i
n
e
lear
n
in
g
al
g
o
r
ith
m
to
p
ar
ticip
ate
in
th
e
p
r
o
ce
s
s
o
f
class
i
f
y
in
g
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
n
s
tr
u
c
ts
a
n
al
g
o
r
ith
m
t
h
at
o
f
f
er
s
u
n
iq
u
e
id
en
t
if
ica
tio
n
o
f
t
h
e
t
y
p
e
o
f
attac
k
s
o
n
t
h
e
b
asi
s
o
f
t
h
e
ad
v
er
s
ar
ia
l
b
eh
av
io
r
.
3
.
1
.
Alg
o
ri
t
h
m
f
o
r
cla
s
s
if
y
in
g
DDo
S a
t
t
a
ck
T
h
e
co
r
e
id
ea
o
f
th
e
d
ev
elo
p
m
e
n
t
o
f
th
i
s
alg
o
r
ith
m
is
t
h
at
th
e
DDo
S
attac
k
lead
s
to
d
e
clin
atio
n
o
f
r
eso
u
r
ce
s
eith
er
f
r
o
m
c
h
a
n
n
el
ca
p
ac
ity
v
ie
w
p
o
in
t
o
r
f
r
o
m
b
u
f
f
er
v
ie
w
p
o
i
n
t.
T
h
e
alg
o
r
ith
m
tak
e
s
th
e
in
p
u
t
o
f
n
(
n
u
m
b
er
o
f
n
o
d
es)
an
d
th
1
/
th
2
(
th
r
esh
o
ld
)
w
h
ic
h
af
ter
p
r
o
ce
s
s
i
n
g
y
ield
s
a
n
d
o
u
tco
m
e
o
f
f
lag
m
es
s
a
g
e
o
f
C
in
t
(
C
u
m
u
lati
v
e
I
n
tr
u
s
io
n
)
.
T
h
e
co
m
p
lete
ill
u
s
tr
at
io
n
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
s
b
ased
o
n
t
w
o
ca
s
e
s
m
=2
(
L
i
n
e
-
4
)
f
o
r
co
m
p
u
ti
n
g
u
til
iz
ed
ch
an
n
el
ca
p
ac
it
y
a
n
d
b
u
f
f
er
.
T
h
e
f
ir
s
t
s
w
itc
h
ca
s
e
(
L
i
n
e
-
5
-
7
)
is
ass
o
ciate
d
w
i
th
d
ep
letio
n
o
f
ch
a
n
n
e
l
ca
p
ac
it
y
u
s
in
g
v
ar
io
u
s
at
tr
ib
u
te
s
o
f
it.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
it
h
m
f
o
r
m
u
late
s
a
n
ex
p
r
ess
io
n
ca
l
led
a
d
eg
r
ee
o
f
ch
an
n
el
ca
p
ac
it
y
co
n
s
u
m
p
tio
n
α
ccap,
α
ccap
=g
1
/g
2
(
1
)
I
n
th
e
ab
o
v
e
ex
p
r
ess
io
n
,
t
h
e
v
ar
iab
le
g
1
an
d
g
2
r
ep
r
esen
t
f
av
o
r
ab
le
ch
an
n
el
ca
p
ac
it
y
d
ep
leted
an
d
to
tal
ch
an
n
el
ca
p
ac
it
y
.
T
h
e
co
m
p
u
t
atio
n
o
f
g
1
an
d
g
2
i
s
ca
r
r
ied
o
u
t a
s
f
o
llo
w
s
,
1
1
.
u
g
u
an
d
u
i
i
i
g
0
2
!
(
2
)
I
n
th
e
e
x
p
r
ess
io
n
,
t
h
e
v
ar
iab
le
θ
ca
n
b
e
f
u
r
t
h
er
b
r
o
k
en
d
o
w
n
to
f
o
llo
w
i
n
g
e
m
p
ir
ical
e
x
p
r
ess
io
n
,
)
(
1
rn
mn
t
(
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
2
,
A
p
r
il 2
0
2
0
:
1
5
9
9
-
1611
1604
I
n
t
h
e
e
x
p
r
ess
io
n
,
th
e
v
ar
iab
le
θ
mn
,
θ
rn
,
a
n
d
θ
t
r
ep
r
esen
t
ch
a
n
n
el
ca
p
ac
it
y
u
s
ed
b
y
t
h
e
m
alic
io
u
s
n
o
d
e,
r
eg
u
lar
n
o
d
e,
an
d
to
tal
ch
an
n
e
l
ca
p
ac
it
y
,
r
esp
ec
tiv
e
l
y
.
T
h
e
c
o
m
p
u
tatio
n
o
f
θ
mn
ca
n
b
e
ca
r
r
ied
o
u
t
b
y
d
i
v
id
i
n
g
th
e
s
ize
o
f
d
ata
f
o
r
w
ar
d
ed
f
o
r
th
e
m
alicio
u
s
n
o
d
e
(
s
mn
)
to
b
u
f
f
er
ti
m
e
o
f
m
al
i
cio
u
s
n
o
d
e
(
b
mn
)
.
T
h
e
co
m
p
u
ta
tio
n
o
f
θ
rn
ca
n
b
e
ca
r
r
ied
o
u
t
b
y
d
iv
id
in
g
t
h
e
s
i
ze
o
f
d
ata
f
o
r
w
ar
d
ed
f
o
r
th
e
r
eg
u
lar
n
o
d
e
(
s
rn
)
to
b
u
f
f
er
ti
m
e
o
f
m
alicio
u
s
n
o
d
e
(
b
rn
)
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
n
tr
o
d
u
ce
s
a
n
o
th
er
p
r
ac
tic
al
co
n
ce
p
t
th
at
n
o
m
alicio
u
s
n
o
d
e
w
ill
i
n
it
iate
an
attac
k
i
n
s
u
c
h
a
w
a
y
t
h
at
b
e
h
av
io
r
lo
o
k
s
s
u
s
p
icio
u
s
an
d
t
h
e
s
ize
o
f
th
e
p
ac
k
et
is
o
n
e
s
u
ch
f
ac
to
r
w
h
ic
h
g
i
v
e
s
a
r
o
u
g
h
id
ea
ab
o
u
t
it.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
e
d
s
y
s
te
m
co
n
s
id
er
s
th
at
s
ize
o
f
th
e
d
ata
p
ac
k
et
f
o
r
w
ar
d
ed
d
u
r
in
g
i
n
v
o
k
i
n
g
DDo
S
attac
k
i
n
SDN
n
o
d
e
to
b
e
eq
u
iv
ale
n
t
to
th
at
o
f
r
e
g
u
lar
co
m
m
u
n
icatio
n
en
v
ir
o
n
m
e
n
t.
T
h
is
s
tr
ate
g
y
is
ad
o
p
ted
b
y
an
ad
v
er
s
ar
y
s
o
t
h
at
th
e
y
d
o
n
't
g
et
th
e
m
s
el
v
es
ca
u
g
h
t.
T
h
er
ef
o
r
e,
in
s
u
ch
ca
s
e,
ex
p
r
ess
io
n
(
3
)
w
il
l lo
o
k
lik
e
f
o
llo
w
in
g
,
)
(
1
rn
mn
t
rn
rn
mn
mn
t
b
s
b
s
1
I
n
ca
s
e
o
f
DDo
S a
ttac
k
s
mn
=s
rn
=s
c
,
rn
c
mn
c
t
b
s
b
s
1
rn
mn
t
c
b
b
s
1
1
mn
b
1
.
(
4
)
I
t
is
b
ec
au
s
e,
d
u
r
i
n
g
th
e
s
tate
o
f
DDo
S
a
ttack
,
s
c
/θ
t
is
co
n
s
tan
t
s
a
y
χ
an
d
1
/b
n
ar
e
n
ea
r
l
y
eq
u
iv
a
len
t
to
ze
r
o
.
Fro
m
ex
p
r
ess
io
n
(
4
)
,
it
ca
n
b
e
s
tated
th
at
θ
i
s
i
n
v
er
s
e
l
y
p
r
o
p
o
r
tio
n
al
to
th
e
b
u
f
f
er
ti
m
e
o
f
t
h
e
m
a
licio
u
s
n
o
d
e,
i.e
.
,
b
mn
.
T
h
e
p
r
o
p
o
s
ed
s
tu
d
y
co
n
s
id
er
s
b
u
f
f
er
ti
m
e
to
t
h
e
d
u
r
atio
n
o
f
ti
m
e
b
et
w
ee
n
t
w
o
d
ata
p
ac
k
ets
r
ela
y
ed
fr
o
m
a
s
i
n
g
le
SDN
n
o
d
e.
T
h
er
ef
o
r
e,
w
it
h
th
e
h
elp
o
f
ex
p
r
ess
io
n
(
1
)
an
d
(
4
)
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
ca
n
in
f
er
th
at,
u
c
c
a
p
1
an
d
mn
c
c
a
p
b
1
(
5
)
T
h
e
in
f
er
en
ce
o
f
th
e
ab
o
v
e
ex
p
r
ess
io
n
(
5
)
is
th
at
d
u
r
in
g
DDo
S
attac
k
o
n
SDN
n
o
d
e,
d
eg
r
ee
o
f
b
an
d
w
id
t
h
co
n
s
u
m
p
tio
n
i
s
d
ir
ec
tl
y
p
r
o
p
o
r
tio
n
al
to
th
e
v
ar
ia
b
le
θ
an
d
in
v
er
s
el
y
p
r
o
p
o
r
tio
n
to
b
u
f
f
er
ti
m
e
o
f
th
e
m
alicio
u
s
n
o
d
e.
T
h
e
alg
o
r
ith
m
ic
s
tep
s
ar
e
as
f
o
llo
w
s
:
Alg
o
rit
h
m
f
o
r
cla
s
s
if
y
ing
D
Do
S a
t
t
a
ck
I
np
ut
:
n
(
n
u
m
b
er
o
f
n
o
d
es),
th
1
/t
h
2
(
th
r
es
h
o
ld
)
O
utput
: Fla
g
m
e
s
s
a
g
e
o
f
C
i
nt
(
C
u
m
u
lati
v
e
I
n
tr
u
s
io
n
)
Sta
rt
1
.
in
it
n
,
th
1
,
th
2
2
.
F
o
r
i=1
:
n
3
.
C
int
1
-
(P
1
.P
2
)
4
.
S
w
it
ch
(
m
)
5
.
c
a
s
e
-
1:
6
.
α
ccap
=
g
1
/g
2
7
.
b
r
ea
k
;
8
.
c
a
s
e
-
2:
9
.
α
buff
=h
1
/h
2
1
0
.
b
r
ea
k
1
1
.
E
nd
1
2
.
If
B
t<th
1
&
&
N
c
>t
h
2
1
3
.
F
la
g
C
int
as L
A
R
GE
1
4
.
If
B
t>th
1
&
&
N
c
<t
h
2
1
5
.
F
la
g
C
int
as L
E
SS
1
6
.
E
nd
E
nd
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:
2
0
8
8
-
8708
P
r
ee
mp
tive
mo
d
ellin
g
to
w
a
r
d
s
cla
s
s
ifyin
g
vu
ln
era
b
ilit
y
o
f D
Do
S
a
tta
ck
in
S
DN
en
viro
n
men
t
(
N
a
r
en
d
er M
.
)
1605
T
h
e
n
ex
t
p
ar
t
o
f
th
e
al
g
o
r
ith
m
(
L
i
n
e
-
7
-
1
0
)
is
ab
o
u
t
th
e
s
ec
o
n
d
ca
s
e
o
f
v
u
ln
er
ab
ili
t
y
c
o
n
s
id
er
in
g
th
e
ef
f
ec
t
o
f
b
u
f
f
er
d
ec
lin
ati
o
n
d
u
r
in
g
a
DDo
S
attac
k
i
n
SDN
n
o
d
e.
I
n
th
is
ca
s
e,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
m
p
u
tes t
h
e
d
eg
r
ee
o
f
b
u
f
f
er
d
ec
lin
atio
n
a
s
,
α
buff
=h
1
/h
2
(
6
)
I
n
th
e
ab
o
v
e
ex
p
r
es
s
io
n
,
t
h
e
v
ar
iab
le
h
1
an
d
h
2
ar
e
f
o
r
m
u
late
d
n
ea
r
l
y
in
a
s
i
m
ilar
w
a
y
j
u
s
t
l
ik
e
it
w
as
d
o
n
e
f
o
r
ex
p
r
ess
io
n
(
1
)
as b
elo
w
,
t
b
t
h
1
an
d
t
b
o
i
i
i
h
!
2
(
7
)
T
h
e
s
i
m
ilar
s
ce
n
ar
io
u
s
ed
d
u
r
in
g
ex
p
r
ess
io
n
(
4
)
is
also
u
s
ed
h
er
e,
w
h
ich
ca
n
b
e
re
-
w
r
itte
n
f
o
r
b
u
f
f
er
d
ec
lin
atio
n
a
s
,
rn
rn
mn
mn
rn
mn
b
s
b
s
(
8
)
As d
u
r
in
g
DDo
S a
ttac
k
o
n
S
D
N
n
o
d
e,
mn
b
rn
mn
b
b
s
b
b
s
)
1
1
(
(
9
)
W
ith
s
i
m
ilar
lo
g
ic
t
h
at
s
mn
=s
rn
=s
b
an
d
1
/b
rn
is
eq
u
iv
ale
n
t
to
ze
r
o
d
u
r
in
g
attac
k
ev
e
n
t,
th
e
p
r
o
p
o
s
ed
lo
g
ic
n
o
w
d
er
iv
es d
o
w
n
to
th
e
f
o
llo
w
in
g
in
f
er
en
ce
,
t
b
u
f
f
1
an
d
mn
b
u
f
f
b
1
(
1
0
)
Usi
n
g
a
ll
t
h
e
ab
o
v
e
e
x
p
r
ess
i
o
n
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
f
i
n
a
ll
y
m
a
k
es
th
e
f
o
llo
w
i
n
g
i
n
f
e
r
en
ce
as
s
h
o
w
n
i
n
T
ab
le
1
f
o
r
p
er
f
o
r
m
i
n
g
a
n
al
y
s
i
s
o
f
DDo
S a
ttac
k
.
T
ab
le
1
.
A
n
al
y
s
i
s
o
f
attac
k
s
ce
n
ar
io
A
t
t
a
c
k
S
c
e
n
e
b
mn
C
o
mm
u
n
i
c
a
t
i
o
n
c
h
a
n
n
e
l
T
h
e
b
u
f
f
e
r
o
f
t
h
e
v
i
c
t
i
m
n
o
d
e
,
b
C
u
m
u
l
a
t
i
v
e
i
n
t
r
u
s
i
o
n
C
i
nt
1
2
3
N
o
d
e
su
c
c
e
ssf
u
l
l
y
c
a
p
t
u
r
e
d
(
L
e
g
e
n
d
:
L
e
ss:
,
H
i
g
h
:
)
3
.
2
.
O
ptim
izing
cla
s
s
if
ica
t
io
n us
ing
m
a
ch
ine le
a
rning
T
h
is
p
r
io
r
o
p
er
atio
n
al
s
tep
ass
is
ts
in
c
lass
if
y
i
n
g
t
h
e
t
y
p
e
o
f
DDo
S
attac
k
i
n
SD
N
n
o
d
e
w
i
th
r
esp
ec
t
to
th
e
in
te
n
s
it
y
o
f
t
h
e
attac
k
.
I
f
th
e
attac
k
in
te
n
s
it
y
i
s
h
i
g
h
,
it
f
lag
s
as
lar
g
e
alar
m
a
n
d
v
i
ce
v
er
s
a.
Ho
w
e
v
er
,
th
e
b
est
r
esu
lt
o
f
C
la
s
s
i
f
ica
ti
o
n
ca
n
b
e
o
n
l
y
o
b
tain
ed
i
f
th
e
m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
is
u
s
ed
.
T
h
e
b
asic
lo
g
ic
o
f
th
e
p
r
ec
is
e
cla
s
s
i
f
icat
io
n
p
r
o
ce
s
s
is
th
at
–
if
t
h
e
d
e
g
r
ee
o
f
ch
a
n
n
e
l
ca
p
ac
it
y
co
n
s
u
m
p
t
io
n
as
w
ell
a
s
b
u
f
f
er
u
tili
za
tio
n
is
f
o
u
n
d
p
r
o
m
in
e
n
t.
Ho
w
e
v
er
,
s
u
c
h
a
s
s
o
ciate
d
d
ata
ar
e
s
o
d
i
v
e
r
s
i
f
ied
th
at
if
t
h
e
y
ar
e
n
o
t
g
r
o
u
p
ed
,
th
e
n
it
w
i
ll
b
e
c
h
alle
n
g
in
g
to
i
m
p
r
o
v
e
t
h
e
cla
s
s
i
f
ic
atio
n
ac
c
u
r
ac
y
o
f
it.
He
n
ce
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
ap
p
lies
a
m
ac
h
i
n
e
lear
n
i
n
g
a
p
p
r
o
ac
h
f
o
r
i
m
p
r
o
v
i
n
g
clas
s
i
f
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
e
p
r
i
m
ar
y
r
ea
s
o
n
b
e
h
i
n
d
th
is
ad
o
p
tio
n
i
s
t
h
at
m
ac
h
i
n
e
lear
n
i
n
g
cla
s
s
i
f
icatio
n
s
d
o
n
’
t
h
a
v
e
a
n
y
d
ep
en
d
en
c
y
o
n
e
x
p
er
ts
o
r
s
p
ec
ialized
s
k
il
l
s
e
t,
a
n
d
it
is
a
h
i
g
h
l
y
au
t
o
m
ated
m
ec
h
a
n
i
s
m
f
o
r
p
er
f
o
r
m
i
n
g
tr
ai
n
in
g
/lear
n
i
n
g
o
p
er
atio
n
f
o
r
a
g
iv
e
n
s
et
o
f
d
ata.
A
p
ar
t
f
r
o
m
t
h
is
a
s
p
ec
t,
a
m
ac
h
in
e
lear
n
i
n
g
a
p
p
r
o
ac
h
is
also
co
s
t
-
e
f
f
ec
ti
v
e
as
w
el
l
as
h
i
g
h
l
y
f
le
x
ib
le
m
ec
h
an
i
s
m
w
i
th
m
o
r
e
s
co
p
e
o
f
ap
p
licab
ilit
y
o
n
a
n
y
f
o
r
m
o
f
t
h
e
tas
k
as
s
o
ciate
d
w
i
t
h
lear
n
i
n
g
o
p
er
atio
n
.
Hen
ce
,
ap
p
l
y
i
n
g
m
ac
h
in
e
lear
n
i
n
g
a
lg
o
r
it
h
m
co
u
ld
f
u
r
th
er
o
f
f
er
b
etter
cla
s
s
i
f
icat
io
n
p
er
f
o
r
m
a
n
c
e
f
o
r
DDo
S
attac
k
i
n
SDN
n
o
d
e.
T
h
e
s
tep
s
o
f
th
e
al
g
o
r
ith
m
ar
e
as
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
2
,
A
p
r
il 2
0
2
0
:
1
5
9
9
-
1611
1606
Alg
o
rit
h
m
f
o
r
cla
s
s
if
ica
t
io
n
o
pti
m
iza
t
io
n
I
np
ut
:
n
(
n
o
d
es),
th
r
(
th
r
es
h
o
l
d
)
O
utput
: Fla
g
o
f
DDo
S a
ttac
k
/ Saf
e
Sta
rt
1
.
ch
ec
k
n
(
m
n
=
r
n
)
2
.
r
etain
B
t
3
.
F
o
r
i=1
:n
4
.
a=
g
r
o
u
p
n
(
id
,
B
t
)
5
.
A
p
p
ly
f
(
x
)
a;
6
.
s
im
[
s
i
m
1
,
s
i
m
2
,
….
s
i
m
m
]
7
.
F
o
r
j
=1
:m
8
.
If
s
im
<
th
r
9
.
Flag
DDo
S A
ttac
k
1
0
.
E
ls
e
1
1
.
Flag
Saf
e
1
2
.
E
nd
1
3
.
E
nd
E
nd
T
h
e
in
itial
p
r
o
ce
s
s
o
f
t
h
e
al
g
o
r
ith
m
i
s
to
f
o
r
m
u
late
a
g
r
o
u
p
o
f
all
t
h
e
n
o
d
es
n
th
a
t
h
a
s
a
n
ea
r
l
y
s
i
m
ilar
id
en
tit
y
o
f
r
eg
u
lar
rn
an
d
m
alic
io
u
s
n
o
d
e
mn
(
L
i
n
e
-
1
)
.
A
ll
th
e
s
i
m
ilar
f
o
r
m
s
o
f
t
h
e
SDN
n
o
d
es
ar
e
k
ep
t
in
t
h
e
s
a
m
e
g
r
o
u
p
,
w
h
ic
h
is
ca
r
r
ied
o
u
t
o
n
th
e
b
asis
o
f
th
e
b
u
f
f
er
ti
m
e
B
t
(
L
in
e
-
4
)
.
An
ex
p
lici
t
f
u
n
c
tio
n
f
(
x
)
is
d
ev
elo
p
ed
,
w
h
ic
h
i
s
a
p
p
lied
to
th
e
ex
tr
ac
ted
g
r
o
u
p
o
f
s
i
m
ilar
SD
N
n
o
d
es
(
L
i
n
e
-
5
)
.
T
h
is
o
p
er
atio
n
r
esu
lt
s
in
a
m
atr
i
x
s
im
w
h
ic
h
r
etain
s
all
th
e
s
i
m
ilar
it
y
s
c
o
r
e
o
f
o
b
tain
ed
g
r
o
u
p
s
r
esp
ec
tiv
e
l
y
,
e.
g
.
,
s
i
m
1
,
s
i
m
2
,…
s
i
m
m
,
w
h
er
e
m
is
t
h
e
n
u
m
b
er
o
f
g
r
o
u
p
s
f
o
r
m
u
lated
(
L
i
n
e
-
6
)
.
Fo
r
all
t
h
e
n
u
m
b
er
o
f
f
o
r
m
u
lated
g
r
o
u
p
s
(
L
i
n
e
-
8
)
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
m
p
ar
es
th
e
cu
m
u
lati
v
e
s
i
m
ilar
it
y
s
co
r
e
s
im
w
it
h
a
th
r
es
h
o
ld
s
co
r
e
th
r
(
L
i
n
e
-
8
)
.
I
f
th
e
s
i
m
ilar
i
t
y
s
c
o
r
e
is
f
o
u
n
d
to
b
e
le
s
s
th
a
n
th
e
th
r
es
h
o
ld
t
h
an
it
r
ep
r
es
en
ts
a
ca
s
e
w
h
er
e
th
e
p
r
esen
ce
o
f
m
ali
cio
u
s
e
v
en
t
ca
n
b
e
ascer
tai
n
ed
.
I
n
s
u
ch
a
ca
s
e,
t
h
e
al
g
o
r
it
h
m
f
la
g
s
,
th
e
o
u
tco
m
e
a
s
co
n
f
ir
m
ed
DDo
S
attac
k
(
L
i
n
e
-
9
)
o
r
else
it
is
s
af
er
(
L
in
e
-
1
1
)
.
On
e
o
f
th
e
i
n
ter
est
in
g
p
o
in
ts
to
b
e
n
o
ted
in
th
is
alg
o
r
ith
m
is
t
h
at
it
j
u
s
t
co
n
tr
i
b
u
tes
to
p
er
f
o
r
m
i
n
g
p
r
ec
is
e
cl
ass
i
f
icatio
n
o
p
er
atio
n
b
y
p
er
f
o
r
m
i
n
g
tr
ain
i
n
g
o
n
th
e
d
ata
o
b
tain
ed
f
r
o
m
th
e
p
r
io
r
alg
o
r
ith
m
.
A
s
t
h
i
s
al
g
o
r
ith
m
is
a
co
n
t
in
u
atio
n
o
f
t
h
e
p
r
i
o
r
alg
o
r
ith
m
,
th
er
ef
o
r
e,
it
ad
d
s
m
o
r
e
p
r
ec
is
io
n
i
n
th
e
p
r
o
ce
s
s
o
f
clas
s
i
f
icatio
n
o
p
er
atio
n
.
I
r
r
esp
ec
ti
v
e
o
f
t
h
e
d
y
n
a
m
ic
b
eh
av
io
r
o
f
th
e
r
eg
u
lar
an
d
m
alicio
u
s
SDN
n
o
d
es,
th
e
p
r
o
p
o
s
ed
m
ac
h
i
n
e
lear
n
i
n
g
ap
p
r
o
ac
h
ca
n
p
er
f
o
r
m
a
p
r
ec
is
e
class
if
ica
tio
n
o
f
cr
i
tical
it
y
s
co
r
e
o
f
t
h
e
a
ttack
er
in
f
lu
e
n
ce
a
s
w
ell
as
co
n
f
ir
m
atio
n
o
f
th
e
DDo
S
attac
k
.
T
h
e
n
ex
t sectio
n
d
is
cu
s
s
es t
h
e
r
esu
l
t o
b
tain
ed
.
4.
RE
SU
L
T
A
NAL
YSI
S
T
h
is
s
ec
tio
n
d
is
c
u
s
s
es
t
h
e
r
e
s
u
lt
s
b
ei
n
g
o
b
tai
n
ed
af
ter
i
m
p
le
m
en
tin
g
t
h
e
al
g
o
r
it
h
m
.
Sc
r
ip
ted
in
MA
T
L
A
B
,
it
s
h
o
u
ld
b
e
n
o
te
d
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
i
m
s
f
o
r
q
u
an
ti
f
y
i
n
g
t
h
e
C
la
s
s
if
icatio
n
o
f
DDo
S
attac
k
p
er
f
o
r
m
a
n
ce
.
T
h
e
class
if
icatio
n
o
u
tco
m
es
o
f
t
h
e
f
ir
s
t
alg
o
r
ith
m
ar
e
ab
o
u
t
th
e
i
n
te
n
s
it
y
o
f
attac
k
w
h
i
le
th
e
cla
s
s
i
f
icat
io
n
o
u
tco
m
e
o
f
t
h
e
s
ec
o
n
d
al
g
o
r
ith
m
i
s
ab
o
u
t
f
u
r
th
er
co
n
f
ir
m
i
n
g
t
h
e
p
r
ese
n
c
e
o
f
a
D
Do
S a
ttac
k
.
T
h
er
ef
o
r
e,
th
e
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
co
n
s
id
er
ed
f
o
r
r
esu
l
t
an
al
y
s
i
s
is
m
ai
n
l
y
ac
c
u
r
ac
y
.
A
s
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
m
p
le
m
e
n
t
s
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
f
o
r
i
m
p
r
o
v
in
g
a
n
d
q
u
alita
tiv
e
an
a
l
y
s
is
o
f
c
lass
if
icatio
n
p
er
f
o
r
m
a
n
ce
;
t
h
er
ef
o
r
e,
p
r
ed
ictio
n
ti
m
e
an
d
tr
ain
i
n
g
ti
m
e
is
also
ass
es
s
ed
.
Fu
r
th
er
d
i
s
cu
s
s
io
n
o
f
r
esu
lt
an
al
y
s
i
s
is
as
:
4
.
1
.
Ana
ly
s
is
o
f
s
t
ra
t
e
g
y
T
h
e
f
in
al
o
b
j
ec
tiv
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
to
en
s
u
r
e
th
a
t
a
n
o
d
e
r
u
n
n
i
n
g
o
v
er
SDN
s
h
o
u
ld
b
e
ab
le
to
p
er
f
o
r
m
s
a
f
er
co
m
m
u
n
ica
tio
n
an
d
co
u
ld
p
o
ten
tiall
y
r
esis
t
DDo
S
attac
k
,
ev
e
n
b
ef
o
r
e
it
tak
es
p
lace
.
Ma
j
o
r
ity
o
f
th
e
ex
i
s
ti
n
g
ap
p
r
o
ac
h
es
to
w
ar
d
s
r
esis
tin
g
DD
o
S
attac
k
is
o
n
l
y
ap
p
licab
le
w
h
e
n
an
y
e
v
en
o
f
DDo
S
ta
k
es
p
lace
.
I
t
is
b
ec
au
s
e
s
u
c
h
m
et
h
o
d
s
f
ail
to
id
e
n
ti
f
y
t
h
e
m
alic
io
u
s
b
eh
a
v
io
r
t
h
at
an
ad
v
er
s
ar
y
co
u
ld
ad
o
p
t
to
in
itiate
a
DDo
S
att
ac
k
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
ec
u
r
i
t
y
p
r
o
ce
s
s
is
as
s
u
m
ed
to
b
e
ex
ec
u
t
ed
i
n
th
e
co
n
tr
o
l
la
y
er
o
f
SDN
s
tan
d
ar
d
ar
ch
itect
u
r
e,
w
h
ic
h
r
esid
es
in
b
et
w
ee
n
th
e
ap
p
l
icatio
n
la
y
er
an
d
i
n
f
r
astru
c
tu
r
e
la
y
er
.
T
h
e
i
n
p
u
t
to
t
h
is
co
n
tr
o
l
la
y
er
co
u
ld
b
e
n
et
w
o
r
k
/co
m
m
u
n
icat
i
on
-
r
elate
d
in
f
o
r
m
at
io
n
,
w
h
er
ea
s
t
h
e
o
u
tp
u
t o
f
t
h
e
co
n
t
r
o
ller
w
ill
b
e
a
s
et
o
f
r
u
le
s
t
h
at
w
ill b
e
f
o
llo
w
ed
b
y
a
ll t
h
e
n
o
d
es r
u
n
n
i
n
g
w
it
h
i
n
it.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
n
s
tr
u
cts t
h
e
r
u
le
o
n
th
e
b
asi
s
o
f
t
h
e
in
f
o
r
m
atio
n
a
n
d
in
f
er
en
ce
d
i
s
cu
s
s
ed
in
T
ab
le
1
.
A
cc
o
r
d
in
g
to
th
e
p
r
o
p
o
s
ed
r
u
le
s
et,
f
o
llo
w
i
n
g
ar
e
th
e
d
is
tin
ct
c
h
ar
ac
ter
is
t
ics
u
n
d
er
DDo
S
attac
k
e.
g
.
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:
2
0
8
8
-
8708
P
r
ee
mp
tive
mo
d
ellin
g
to
w
a
r
d
s
cla
s
s
ifyin
g
vu
ln
era
b
ilit
y
o
f D
Do
S
a
tta
ck
in
S
DN
en
viro
n
men
t
(
N
a
r
en
d
er M
.
)
1607
a
)
cu
m
u
lat
iv
e
d
ep
letio
n
o
f
o
v
er
all
r
eso
u
r
ce
s
o
f
t
h
e
v
u
l
n
er
ab
le
n
o
d
e
(
v
icti
m
n
o
d
e)
is
i
n
v
er
s
el
y
p
r
o
p
o
r
tio
n
al
to
th
e
r
ate
o
f
b
u
f
f
e
r
ti
m
e
o
f
t
h
e
ad
v
er
s
ar
y
n
o
d
e,
b
)
th
e
p
r
o
b
ab
ilit
y
o
f
t
h
e
r
e
s
o
u
r
ce
co
n
s
u
m
p
tio
n
i
n
cr
ea
s
es
o
f
th
e
b
u
f
f
er
ti
m
e
i
s
s
m
aller
,
c
)
if
t
h
e
s
ize
o
f
b
u
f
f
er
is
m
ai
n
tain
ed
h
i
g
h
er
th
a
n
r
eso
u
r
ce
d
ep
letio
n
co
u
ld
b
e
co
n
tr
o
lle
d
,
iv
)
th
e
p
r
ese
n
ce
o
f
m
an
y
n
u
m
b
er
s
o
f
u
n
-
u
til
ize
d
ch
an
n
el
ca
p
ac
it
y
ca
n
al
s
o
s
ig
n
if
ican
t
l
y
co
n
tr
o
l
th
e
c
h
a
n
n
el
ca
p
ac
it
y
d
r
ain
a
g
e
f
o
r
t
h
e
v
u
ln
er
ab
le
n
o
d
e.
R
ef
er
r
in
g
to
T
ab
le
1
an
d
t
h
e
f
ir
s
t
clas
s
i
f
icatio
n
alg
o
r
ith
m
,
th
er
e
ar
e
th
r
ee
in
f
e
r
en
ce
ex
tr
ac
ted
.
T
h
e
fir
s
t
in
feren
ce
(1
st
attac
k
s
ce
n
ar
io
)
o
b
tain
ed
is
-
it
ca
n
b
e
s
tated
th
at
cu
m
u
lati
v
e
i
n
tr
u
s
io
n
C
in
t
v
al
u
e
h
as
t
h
e
h
i
g
h
e
s
t
i
m
p
ac
t
o
n
n
o
d
es
w
h
e
n
a
v
u
ln
e
r
ab
le
n
o
d
e
is
f
o
u
n
d
w
i
th
a)
s
m
al
ler
b
u
f
f
er
ti
m
e,
b
)
less
av
a
ilab
ilit
y
o
f
u
n
-
u
til
iz
ed
ch
an
n
el
ca
p
ac
it
y
,
c
)
s
m
a
ll
er
s
ize
o
f
t
h
e
b
u
f
f
er
(
o
r
m
e
m
o
r
y
)
.
T
h
e
s
ec
o
n
d
in
feren
ce
(2
nd
attac
k
s
ce
n
ar
io
)
o
b
tain
ed
i
s
–
t
h
e
c
u
m
u
lati
v
e
i
n
t
r
u
s
io
n
C
int
v
alu
e
is
less
f
o
r
t
h
e
v
u
ln
er
ab
le
n
o
d
e
w
i
th
h
i
g
h
b
u
f
f
er
ti
m
e
an
d
h
i
g
h
er
s
ize
o
f
t
h
e
b
u
f
f
er
(
o
r
m
e
m
o
r
y
)
as
w
ell
as
a
h
ig
h
er
n
u
m
b
er
o
f
u
n
-
u
ti
liz
ed
ch
an
n
el
ca
p
ac
it
y
.
T
h
e
th
i
r
d
in
feren
ce
(3
rd
attac
k
s
ce
n
ar
io
)
o
b
tain
ed
is
–
th
e
p
r
o
b
ab
ilit
y
v
alu
e
o
f
th
e
cu
m
u
lati
v
e
in
tr
u
s
io
n
is
s
aid
to
b
e
co
m
p
r
o
m
i
s
ed
if
b
u
f
f
er
ti
m
e
is
f
o
u
n
d
less
alo
n
g
w
i
th
a
lar
g
e
n
u
m
b
er
o
f
a
v
aila
b
ilit
y
o
f
u
n
-
u
tili
ze
d
c
h
a
n
n
el
c
ap
ac
it
y
a
n
d
h
i
g
h
er
s
ize
o
f
t
h
e
b
u
f
f
er
.
T
h
er
ef
o
r
e,
un
-
u
tili
ze
d
c
h
an
n
el
ca
p
ac
it
y
a
n
d
s
ize
o
f
th
e
b
u
f
f
er
is
th
e
d
o
m
i
n
an
t
p
r
ed
icto
r
o
f
DDo
S
attac
k
an
d
h
en
ce
ca
n
also
b
e
u
s
ed
f
o
r
r
esis
ti
n
g
s
u
ch
in
tr
u
s
io
n
.
4
.
2
.
Abo
ut
d
a
t
a
s
et
T
h
e
an
al
y
s
is
o
f
DDo
S
attac
k
w
i
ll
n
ee
d
a
r
ea
l
f
o
r
m
o
f
D
Do
S
attac
k
to
b
e
i
n
v
o
l
v
ed
i
n
t
h
e
e
x
p
er
i
m
e
n
t.
Ho
w
e
v
er
,
it
is
ch
alle
n
g
in
g
to
test
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
waitin
g
f
o
r
a
r
ea
l
-
ti
m
e
s
ce
n
ar
io
o
f
a
DDo
S
attac
k
.
I
n
o
r
d
er
t
o
ca
r
r
y
o
u
t
th
e
i
m
p
le
m
en
tatio
n
o
f
t
h
e
p
r
o
p
o
s
e
d
alg
o
r
ith
m
f
o
r
C
las
s
if
icatio
n
o
f
DDo
S
attac
k
,
th
e
s
y
s
te
m
d
e
m
a
n
d
s
n
et
w
o
r
k
in
g
d
ata
w
h
en
s
u
b
j
ec
ted
to
a
DDo
S
attac
k
.
A
t
th
e
s
a
m
e
t
i
m
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
i
ll
also
n
ee
d
g
r
o
u
n
d
tr
u
th
d
ata
(
d
ata
w
it
h
o
u
t
D
Do
S
attac
k
,
i.e
.
,
s
af
e
n
et
w
o
r
k
)
f
o
r
ca
r
r
y
i
n
g
o
u
t
v
alid
atio
n
.
T
h
er
ef
o
r
e,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
s
es t
h
e
d
ata
s
et
a
s
s
o
ciate
d
w
it
h
r
ea
l
-
ti
m
e
tr
ac
es
o
f
c
y
b
er
r
is
k
[
38
]
.
T
h
is
d
ataset
is
co
llected
b
y
u
s
i
n
g
s
ta
n
d
ar
d
p
r
o
b
in
g
m
ec
h
an
is
m
o
v
er
t
h
e
in
ter
n
et
(
I
P
v
4
an
d
I
P
v
6
)
w
it
h
a
s
tan
d
ar
d
co
llectio
n
o
f
m
o
r
e
th
a
n
6
0
co
u
n
tr
ies
w
i
th
m
o
r
e
th
a
n
6
0
m
e
g
ab
y
te
s
o
f
d
ata
co
llected
p
er
d
ay
.
Av
a
il
a
b
il
it
y
o
f
c
y
b
e
r
d
a
ta
a
s sh
o
w
n
in
F
ig
u
re
3
.
F
ig
u
re
3
.
A
v
a
il
a
b
il
it
y
o
f
c
y
b
e
r
d
a
ta [3
5
]
4
.
3
.
Co
re
s
t
ud
y
f
ind
ing
s
T
h
e
an
al
y
s
is
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
2
0
0
u
n
iq
u
e
n
o
d
es
w
it
h
a
d
is
tin
c
t
id
en
tit
y
.
T
h
e
d
ataset
is
cu
r
at
ed
w
it
h
an
eq
u
al
d
is
tr
ib
u
tio
n
o
f
1
0
0
r
eg
u
lar
n
o
d
es
an
d
1
0
0
m
alicio
u
s
n
o
d
es.
On
l
y
i
n
f
o
r
m
atio
n
r
elate
d
to
b
u
f
f
er
ti
m
e,
d
ata
ar
r
iv
al
f
r
eq
u
en
c
ies
(
s
ec
)
,
an
d
th
r
o
u
g
h
p
u
t
ar
e
co
n
s
id
er
ed
f
o
r
th
e
co
m
p
lete
d
ata
s
et
w
h
ic
h
is
s
p
li
t
i
n
to
t
w
o
p
ar
ts
,
i.e
.
,
f
ir
s
t
p
ar
t
r
ep
r
esen
t
s
f
o
r
n
o
r
m
al
co
m
m
u
n
icat
io
n
s
ce
n
ar
io
w
h
ile
s
ec
o
n
d
p
ar
t
r
ep
r
esen
ts
f
o
r
DDo
S
attac
k
s
ce
n
ar
io
.
T
h
e
an
al
y
s
is
i
s
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
th
e
i
n
tr
u
d
in
g
t
i
m
e
to
b
e
3
0
s
ec
o
n
d
s
f
o
r
all
th
e
n
o
d
es.
As
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
clai
m
s
o
f
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
f
o
r
o
p
ti
m
izi
n
g
th
e
cl
ass
i
f
icatio
n
p
er
f
o
r
m
an
ce
,
it
is
ess
en
tia
l
to
p
er
f
o
r
m
a
co
m
p
ar
ativ
e
an
al
y
s
i
s
to
s
h
o
w
ca
s
e
t
h
e
b
etter
v
er
s
io
n
o
f
m
ac
h
in
e
lear
n
in
g
.
T
h
e
co
m
p
ar
ativ
e
an
a
l
y
s
is
is
ca
r
r
ied
o
u
t
u
s
i
n
g
al
m
o
s
t
all
t
y
p
es
o
f
e
x
is
tin
g
c
lass
if
ica
t
i
o
n
m
eth
o
d
s
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
m
ec
h
a
n
is
m
v
iz.
i)
lo
g
is
tic
r
eg
r
es
s
io
n
,
en
s
e
m
b
le
lear
n
i
n
g
,
K
-
Nea
r
e
s
t
Neig
h
b
o
r
(
KNN)
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
,
an
d
tr
ee
-
b
ased
class
i
f
icatio
n
ap
p
r
o
ac
h
.
T
h
e
n
u
m
er
ical
o
u
tco
m
e
s
o
b
tain
ed
f
r
o
m
t
h
e
p
r
o
p
o
s
ed
s
t
u
d
y
ar
e
s
h
o
w
ca
s
ed
in
g
r
ap
h
ical
f
o
r
m
Fig
u
r
e
4
to
Fig
u
r
e
5
.
T
h
e
o
u
tco
m
es
ar
e
q
u
ite
in
ter
e
s
tin
g
an
d
ex
h
ib
it
m
u
lt
i
p
le
s
ets
o
f
in
f
er
e
n
ce
.
Fro
m
Fi
g
u
r
e
4
,
it
ca
n
b
e
j
u
s
t
s
aid
th
a
t
lo
g
is
tic
r
eg
r
es
s
io
n
a
n
d
tr
ee
-
b
ased
o
f
f
er
s
t
h
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
o
f
m
o
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
2
,
A
p
r
il 2
0
2
0
:
1
5
9
9
-
1611
1608
th
a
n
9
7
%
in
co
m
p
ar
is
o
n
to
o
th
er
ex
i
s
ti
n
g
c
lass
if
icatio
n
t
ec
h
n
iq
u
e.
T
h
e
r
ea
s
o
n
b
e
h
in
d
th
i
s
ar
e:
-
lo
g
is
tic
r
eg
r
ess
io
n
is
b
est
s
u
ited
f
o
r
s
o
lv
i
n
g
b
in
ar
y
clas
s
i
f
icat
io
n
p
r
o
b
lem
(
alt
h
o
u
g
h
,
w
e
h
av
e
f
o
u
r
cla
s
s
i
f
icat
io
n
f
ac
to
r
s
–
t
w
o
f
ac
to
r
s
(
lar
g
e
an
d
s
m
al
ler
in
te
n
s
it
y
o
f
DDo
S
attac
k
)
o
b
t
ain
ed
f
r
o
m
f
ir
s
t
alg
o
r
ith
m
a
n
d
t
w
o
(
p
r
esen
ce
o
r
ab
s
en
ce
o
f
DDo
S
attac
k
)
f
r
o
m
t
h
e
s
ec
o
n
d
alg
o
r
ith
m
)
,
it
al
w
a
y
s
d
o
es
b
in
ar
y
class
i
f
icatio
n
s
tag
e
-
w
i
s
e.
T
h
e
class
i
f
icatio
n
o
u
tc
o
m
e
ex
h
ib
ited
b
y
t
h
e
lo
g
i
s
ti
c
r
eg
r
ess
io
n
m
o
d
el
is
p
o
ten
t
iall
y
e
n
r
ich
ed
w
it
h
in
f
o
r
m
at
io
n
as
co
m
p
ar
ed
to
o
th
er
clas
s
if
ier
s
.
T
h
is
asp
e
ct
ca
n
b
e
s
ee
n
as
Fi
g
u
r
e
4
s
h
o
w
s
th
a
t
lo
g
i
s
tic
r
eg
r
ess
io
n
o
f
f
er
s
a
m
ax
i
m
u
m
n
u
m
b
er
o
f
o
b
s
er
v
at
io
n
to
b
e
p
r
ed
icted
in
co
n
tr
ast
to
o
t
h
er
class
i
f
ier
s
h
o
w
ev
er
i
t
is
ca
r
r
ied
b
y
co
n
s
u
m
i
n
g
m
o
r
e
tr
ain
in
g
ti
m
e
to
co
n
f
ir
m
f
as
ter
co
n
v
er
g
e
n
ce
as
s
h
o
w
n
in
Fig
u
r
e
5
.
T
h
e
n
ex
t
an
al
y
s
i
s
is
f
o
r
d
ec
is
io
n
tr
ee
-
b
ased
ap
p
r
o
ac
h
,
w
h
ic
h
h
as
co
n
s
id
er
ed
av
er
ag
in
g
t
h
r
ee
tr
ee
-
ba
s
ed
m
eth
o
d
s
(
i.e
.
,
co
ar
s
e,
m
ed
i
u
m
,
a
n
d
f
i
n
e
tr
ee
)
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
d
ec
is
io
n
tr
ee
(
9
8
.
6
%)
is
s
l
ig
h
tl
y
h
ig
h
er
t
h
an
th
e
lo
g
i
s
tic
r
eg
r
e
s
s
io
n
ap
p
r
o
ac
h
.
Fig
u
r
e
4
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
ac
cu
r
ac
y
Fig
u
r
e
5
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
p
r
ed
ictio
n
s
p
ee
d
T
h
e
p
r
im
e
r
ea
s
o
n
f
o
r
th
is
is
d
ec
is
io
n
tr
ee
b
ased
ap
p
r
o
ac
h
as
s
is
t
s
in
e
f
f
ic
ien
t
f
ea
t
u
r
e
ex
tr
ac
tio
n
w
h
ic
h
is
ab
s
o
l
u
tel
y
n
o
t
i
m
p
ac
ted
b
y
an
y
n
o
n
-
li
n
ea
r
r
elatio
n
s
h
ip
(
i
f
t
h
e
y
ar
r
iv
e
o
w
in
g
to
DDo
S
attac
k
)
b
ec
au
s
e
o
f
th
is
r
ea
s
o
n
,
th
e
tr
ai
n
i
n
g
ti
m
e
as
s
h
w
n
i
n
Fi
g
u
r
e
6
is
least
f
o
r
d
ec
is
io
n
tr
ee
an
d
its
o
b
s
er
v
atio
n
ca
p
ab
i
lit
y
as
s
h
o
w
n
i
n
Fi
g
u
r
e
4
is
also
q
u
ite
h
ig
h
co
m
p
ar
ed
to
o
th
er
class
if
ier
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
a
cc
u
r
ac
y
,
as
w
ell
as
o
b
s
er
v
atio
n
r
ea
d
in
g
ca
p
ab
ilit
y
o
f
t
h
e
e
n
s
e
m
b
le
cla
s
s
i
f
ier
,
is
f
o
u
n
d
to
b
e
lo
w
er
t
h
a
n
o
th
er
cla
s
s
i
f
ier
s
.
T
h
e
b
ig
g
est
ch
alle
n
g
e
in
t
h
e
en
s
e
m
b
le
m
ec
h
an
is
m
is
th
a
t
it
ca
n
n
o
t
g
i
v
e
u
n
b
iased
o
u
tc
o
m
e
f
o
r
o
n
e
m
o
d
el,
w
h
ic
h
i
s
d
o
m
i
n
a
n
t
a
n
d
h
e
n
ce
co
u
ld
r
esu
lt
i
n
i
n
ter
o
p
er
ab
ilit
y
p
r
o
b
lem
.
T
h
e
f
o
u
r
t
h
cla
s
s
i
f
ie
r
is
KNN
ap
p
r
o
ac
h
w
h
o
s
e
ac
c
u
r
ac
y
i
s
f
o
u
n
d
to
b
e
h
i
g
h
er
th
a
n
th
e
e
n
s
e
m
b
le
ap
p
r
o
ac
h
an
d
le
s
s
t
h
an
lo
g
i
s
tic
r
e
g
r
ess
io
n
a
n
d
d
ec
is
io
n
tr
ee
-
b
ased
clas
s
i
f
ier
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
a
s
b
e
en
a
n
al
y
ze
d
w
it
h
d
if
f
er
e
n
t
v
a
r
ian
ts
o
f
t
h
e
K
NN
ap
p
r
o
ac
h
(
e.
g
.
,
f
in
e,
m
ed
iu
m
,
co
ar
s
e,
co
s
in
e,
cu
b
ic,
a
n
d
w
e
ig
h
ted
)
.
T
h
e
f
if
t
h
a
n
d
s
i
x
t
h
cl
ass
i
f
ied
,
i.e
.
,
SVM
an
d
T
r
ee
co
n
s
id
er
in
g
w
it
h
/
w
i
t
h
o
u
t
p
r
in
c
ip
al
co
m
p
o
n
e
n
t
an
a
l
y
s
i
s
,
d
o
es
n
'
t
e
x
h
ib
it
b
etter
o
u
tco
m
es.
T
h
er
ef
o
r
e,
th
e
co
r
e
s
tu
d
y
f
in
d
i
n
g
s
ar
e
as
:
a
)
alth
o
u
g
h
lo
g
i
s
tic
r
eg
r
es
s
i
o
n
ap
p
r
o
ac
h
o
f
f
er
s
h
i
g
h
er
ac
c
u
r
ac
y
as
w
ell
as
it
ca
n
n
o
t
ca
p
t
u
r
e
m
a
x
i
m
u
m
o
b
s
er
v
atio
n
a
s
s
ee
n
b
y
T
r
ee
-
b
ased
class
i
f
ier
.
Mo
r
eo
v
er
,
its
tr
ain
i
n
g
ti
m
e
is
s
ig
n
i
f
ica
n
tl
y
h
i
g
h
er
b
ec
au
s
e
o
f
ex
te
n
s
i
v
e
p
r
ed
ictiv
e
o
u
tco
m
es.
He
n
ce
,
th
e
lo
g
is
tic
r
eg
r
ess
io
n
a
p
p
r
o
a
c
h
is
w
ell
s
u
ited
fo
r
o
ffl
in
e
a
n
a
lysi
s
a
n
d
n
o
t
fo
r
o
n
lin
e
a
n
a
lysi
s
.
b
)
A
d
ec
is
io
n
tr
ee
is
t
h
e
b
est
s
u
ited
clas
s
i
f
ied
f
o
r
p
r
o
p
o
s
ed
r
esear
ch
p
r
o
b
lem
o
f
C
la
s
s
i
f
ica
ti
o
n
o
f
D
Do
S
atta
ck
.
I
t
is
w
ell
s
u
i
ted
f
o
r
b
o
th
o
f
f
li
n
e
as
w
ell
as
o
n
lin
e
a
n
al
y
s
i
s
as
it
o
f
f
er
s
h
i
g
h
l
y
r
ed
u
ce
d
tr
ai
n
in
g
ti
m
e
ex
h
ib
itin
g
t
h
e
lea
s
t
co
m
p
u
t
atio
n
al
co
m
p
le
x
it
y
in
v
o
lv
ed
w
it
h
m
o
r
e
ca
p
ab
ilit
y
to
r
ea
d
m
a
x
i
m
u
m
o
b
s
er
v
a
tio
n
.
I
t
is
also
o
b
s
er
v
ed
th
at
a
f
in
e
-
s
tr
u
ct
u
r
ed
d
ec
is
io
n
tr
ee
i
s
m
o
r
e
r
ec
o
m
m
e
n
d
ed
f
o
r
s
li
g
h
tl
y
h
ig
h
er
a
cc
u
r
ac
y
a
s
co
m
p
ar
ed
to
t
h
e
co
u
r
s
e
an
d
m
ed
i
u
m
d
ec
is
io
n
tr
ee
.
c)
T
h
e
n
at
u
r
e
o
f
th
e
e
n
s
e
m
b
le
ap
p
r
o
ac
h
is
q
u
ite
co
m
p
u
tatio
n
a
ll
y
e
x
p
e
n
s
iv
e
a
n
d
h
e
n
ce
n
o
t
r
ec
o
m
m
e
n
d
ed
f
o
r
o
n
li
n
e
a
n
a
l
y
s
i
s
o
f
DDo
S
at
tack
.
i
v
)
K
NN
alg
o
r
it
h
m
is
an
o
t
h
er
s
u
it
ab
le
alg
o
r
ith
m
f
o
r
an
al
y
zin
g
th
e
attac
k
i
n
o
f
f
lin
e
m
o
d
e.
I
t
i
s
b
ec
au
s
e
o
f
f
lin
e
m
o
d
e
w
ill
g
e
n
er
ate
m
a
s
s
i
v
e
tr
ac
es
o
f
d
ata,
w
h
ich
is
th
e
h
i
g
h
l
y
s
u
itab
le
s
ce
n
ar
io
f
o
r
KNN
class
if
icat
io
n
.
R
ed
u
ce
d
tr
ain
in
g
ti
m
e
is
a
n
o
th
er
a
d
v
an
ta
g
e
o
f
KNN.
Ho
w
e
v
er
,
o
w
in
g
to
m
a
x
i
m
u
m
co
m
p
u
tatio
n
co
s
t
a
n
d
d
ep
en
d
en
c
y
,
o
n
l
y
w
ei
g
h
ted
KNN
ap
p
r
o
ac
h
is
r
ec
o
m
m
e
n
d
ed
f
o
r
ad
o
p
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.