Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
7
,
No
.
2
,
J
u
ly
20
26
,
p
p
.
1
41
~
1
58
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v
7
i
2
.
p1
41
-
1
58
141
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
Im
pro
v
ing
B
ot
n
et
hos
t
pred
iction
w
ith
enc
ry
ption a
n
d
G
RU
for
enha
nced n
etwor
k securi
ty
O
m
eg
a
J
o
el
P
a
t
ria
M
o
a
t
a
,
I
r
wa
ns
y
a
h Sa
pu
t
ra
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
N
u
sa
M
a
n
d
i
r
i
U
n
i
v
e
r
s
i
t
y
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
7
,
2
0
2
5
R
ev
is
ed
Au
g
2
8
,
2
0
2
5
Acc
ep
ted
No
v
2
8
,
2
0
2
5
Th
is
p
a
p
e
r
e
x
a
m
in
e
s
th
e
c
h
a
ll
e
n
g
e
s
o
f
re
li
a
b
ly
a
n
d
se
c
u
re
ly
p
re
d
ictin
g
Bo
t
n
et
h
o
sts,
a
c
ru
c
ial
a
sp
e
c
t
o
f
n
e
two
rk
se
c
u
rit
y
.
E
x
isti
n
g
B
o
t
n
et
d
e
tec
ti
o
n
sy
ste
m
s
o
ften
fa
il
to
a
d
d
re
ss
d
a
ta
p
riv
a
c
y
c
o
n
c
e
rn
s
a
n
d
stru
g
g
le
with
e
v
o
lv
in
g
a
tt
a
c
k
m
e
th
o
d
s.
T
h
is
s
tu
d
y
p
ro
p
o
se
s
a
n
i
n
n
o
v
a
ti
v
e
a
p
p
ro
a
c
h
t
o
imp
ro
v
e
t
h
e
se
c
u
rit
y
a
n
d
a
c
c
u
ra
c
y
o
f
Bo
t
n
et
h
o
st
p
re
d
icti
o
n
b
y
i
n
teg
ra
ti
n
g
d
e
e
p
lea
rn
in
g
with
e
n
c
ry
p
ti
o
n
.
Th
e
p
ro
p
o
se
d
m
e
th
o
d
e
m
p
l
o
y
s
e
n
c
ry
p
ti
o
n
tec
h
n
iq
u
e
s
su
c
h
a
s
d
a
ta
e
n
c
ry
p
t
io
n
sta
n
d
a
rd
(
DES
)
a
n
d
b
lu
m
-
b
lu
m
-
sh
u
b
(
BBS
)
to
p
ro
tec
t
se
n
siti
v
e
d
a
ta
in
a
tex
t
d
a
ta
se
t
o
f
2
,
1
0
0
IP
a
d
d
re
ss
e
s,
c
o
n
sistin
g
o
f
B
o
t
n
et
h
o
sts
a
n
d
b
e
n
ig
n
h
o
sts.
S
e
v
e
ra
l
p
re
-
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s,
i
n
c
lu
d
in
g
m
o
v
i
n
g
a
v
e
ra
g
e
a
n
d
m
issin
g
v
a
lu
e
h
a
n
d
li
n
g
,
a
re
imp
lem
e
n
ted
t
o
o
p
ti
m
ize
t
h
e
m
o
d
e
l
p
e
rf
o
rm
a
n
c
e
.
Th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
t
h
e
sy
ste
m
is
e
v
a
lu
a
ted
u
sin
g
p
e
rfo
rm
a
n
c
e
m
e
tri
c
s
su
c
h
a
s
F
1
-
s
c
o
re
,
re
c
a
ll
,
a
c
c
u
ra
c
y
,
a
n
d
p
re
c
isio
n
.
E
x
p
e
r
ime
n
tal
re
su
lt
s
sh
o
w
t
h
a
t
th
e
p
ro
p
o
se
d
a
p
p
ro
a
c
h
sig
n
ifi
c
a
n
tl
y
o
u
tp
e
rf
o
r
m
s
e
x
isti
n
g
m
e
th
o
d
s
in
a
c
c
u
ra
c
y
,
wh
ich
h
a
v
e
n
o
t
a
c
h
iev
e
d
th
e
m
a
x
im
u
m
a
c
c
u
ra
c
y
p
e
r
IP
Ho
st
with
i
n
a
g
iv
e
n
ti
m
e
fra
m
e
,
wh
il
e
p
ro
v
id
in
g
e
n
h
a
n
c
e
d
se
c
u
rit
y
t
h
ro
u
g
h
e
n
c
ry
p
ti
o
n
o
n
tex
t
d
a
ta.
Th
e
stu
d
y
c
o
n
c
lu
d
e
s
th
a
t
c
o
m
b
i
n
in
g
d
e
e
p
lea
rn
i
n
g
with
e
n
c
ry
p
ti
o
n
o
n
tex
t
d
a
ta
o
ffe
rs
a
p
ro
m
isin
g
so
l
u
ti
o
n
fo
r
re
li
a
b
le
a
n
d
se
c
u
re
B
o
t
n
et
h
o
st
p
re
d
ictio
n
d
a
ta.
F
u
t
u
re
re
se
a
rc
h
will
fo
c
u
s
o
n
tes
ti
n
g
larg
e
r
a
n
d
m
o
re
d
i
v
e
rse
d
a
ta
se
ts,
a
s
we
ll
a
s
a
n
a
l
y
z
in
g
t
h
e
imp
a
c
t
o
f
d
iffere
n
t
e
n
c
ry
p
ti
o
n
t
e
c
h
n
iq
u
e
s
o
n
t
h
e
o
v
e
ra
ll
a
c
c
u
ra
c
y
a
n
d
se
c
u
ri
ty
o
f
th
e
s
y
ste
m
.
K
ey
w
o
r
d
s
:
B
o
t
n
et
d
etec
tio
n
Dee
p
lear
n
in
g
o
p
tim
izatio
n
E
n
cr
y
p
tio
n
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
I
P a
d
d
r
ess
an
aly
s
is
Netwo
r
k
s
ec
u
r
ity
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
:
Om
eg
a
J
o
el
Patr
ia
Mo
ata
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Nu
s
a
Ma
n
d
ir
i
Un
i
v
er
s
ity
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
1
4
2
3
0
0
1
6
@
n
u
s
am
an
d
i
r
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
is
s
tu
d
y
b
u
ild
s
o
n
th
e
w
o
r
k
o
f
Olu
wasey
e
et
a
l.
[
1
]
,
w
h
o
ex
p
l
o
r
ed
m
alwa
r
e
d
etec
tio
n
in
b
o
tn
ets
u
s
in
g
d
ee
p
lear
n
in
g
.
Ho
wev
er
,
th
eir
s
tu
d
y
d
id
n
o
t
in
teg
r
ate
en
cr
y
p
tio
n
o
r
in
f
o
r
m
atio
n
s
ec
u
r
ity
in
to
th
e
d
ee
p
lear
n
in
g
m
o
d
el.
T
o
ex
p
a
n
d
t
h
e
ca
p
ab
ilit
ies
o
f
B
o
t
n
et
d
ete
ctio
n
,
th
is
r
esear
ch
in
co
r
p
o
r
a
tes
tex
t
en
cr
y
p
tio
n
tech
n
iq
u
es,
d
ata
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
,
d
ee
p
lear
n
in
g
o
p
tim
izatio
n
s
tr
ateg
ies,
an
d
o
v
e
r
f
itti
n
g
p
r
ev
en
tio
n
tech
n
iq
u
es.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
d
esig
n
ed
to
i
m
p
r
o
v
e
b
o
t
h
th
e
lear
n
in
g
ef
f
icien
cy
an
d
p
r
e
d
ictiv
e
ac
cu
r
ac
y
o
f
a
s
ec
u
r
e
B
o
t
n
et
h
o
s
t p
r
ed
ictio
n
m
o
d
el.
T
h
e
th
r
ea
t
o
f
c
y
b
er
cr
im
e
,
p
ar
ticu
lar
ly
B
o
tn
ets,
co
n
tin
u
es
to
in
cr
ea
s
e
g
lo
b
ally
.
I
n
I
n
d
o
n
esia,
cy
b
er
lo
s
s
es
ar
e
esti
m
ated
at
$
8
9
5
b
illi
o
n
,
r
ep
r
esen
tin
g
1
.
2
0
%
o
f
t
o
tal
g
lo
b
al
lo
s
s
es
o
f
$
7
1
.
6
2
tr
illi
o
n
ac
co
r
d
in
g
to
DAKA
Ad
v
is
o
r
y
[
2
]
.
T
h
e
u
r
g
en
c
y
o
f
in
f
o
r
m
atio
n
s
y
s
t
em
s
ec
u
r
ity
is
f
u
r
th
e
r
am
p
lifie
d
in
t
h
e
er
a
o
f
So
ciety
5
.
0
,
wh
e
r
e
tech
n
o
lo
g
i
es
s
u
ch
as
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
an
d
ar
tific
ial
in
tellig
en
ce
(
AI
)
p
lay
a
v
ital
r
o
le
[
3
]
.
Un
f
o
r
tu
n
ately
,
m
an
y
AI
-
b
ased
p
r
ed
ictio
n
s
y
s
tem
s
in
s
ec
to
r
s
s
u
ch
as
ed
u
ca
tio
n
,
g
o
v
er
n
m
en
t,
an
d
h
ea
lth
ca
r
e
h
av
e
n
o
t
im
p
lem
e
n
ted
en
c
r
y
p
tio
n
,
lea
v
in
g
s
en
s
itiv
e
p
er
s
o
n
al
in
f
o
r
m
atio
n
v
u
ln
er
ab
le
t
o
th
e
f
t
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
2
,
J
u
ly
20
26
:
141
-
1
58
142
m
is
u
s
e.
T
h
is
v
u
ln
er
ab
ilit
y
is
e
x
em
p
lifie
d
b
y
th
e
m
ass
iv
e
d
at
a
leak
s
ca
r
r
ied
o
u
t
b
y
th
e
h
ac
k
er
“Bj
o
r
k
a,
”
wh
ich
ex
p
o
s
ed
s
en
s
itiv
e
d
ata
o
f
I
n
d
o
n
esian
citizen
s
,
in
clu
d
in
g
NI
K
,
KK
n
u
m
b
er
s
,
an
d
telep
h
o
n
e
n
u
m
b
er
s
,
alleg
ed
ly
o
b
tain
ed
f
r
o
m
in
s
titu
tio
n
s
s
u
ch
as
I
n
d
ih
o
m
e,
KPU,
an
d
SIM
r
eg
is
tr
atio
n
d
atab
ases
[
4
]
.
Su
c
h
in
c
id
e
n
ts
h
ig
h
lig
h
t
th
e
f
r
ag
ilit
y
o
f
n
atio
n
al
d
ig
ital
in
f
r
astru
ctu
r
e
an
d
t
h
e
u
r
g
en
t
n
ee
d
f
o
r
p
r
o
ac
tiv
e
s
o
lu
tio
n
s
to
p
r
o
tect
s
en
s
itiv
e
in
f
o
r
m
atio
n
,
p
ar
ticu
l
ar
ly
I
P
ad
d
r
ess
es
u
s
ed
in
b
o
tn
et
h
o
s
t
id
en
tific
atio
n
.
Glo
b
all
y
,
r
an
s
o
m
wa
r
e
an
d
p
h
is
h
in
g
r
em
ain
d
o
m
in
an
t
th
r
ea
ts
,
ac
co
u
n
tin
g
f
o
r
m
o
r
e
th
a
n
3
0
.
2
5
%
o
f
c
y
b
er
attac
k
s
in
r
ec
en
t
d
ec
ad
es.
T
h
ese
ev
o
lv
in
g
t
h
r
ea
ts
d
em
an
d
t
h
e
d
ev
elo
p
m
e
n
t
o
f
a
d
ap
tiv
e
an
d
s
ec
u
r
e
d
etec
tio
n
s
y
s
tem
s
.
Fig
u
r
e
1
illu
s
tr
ates
g
lo
b
al
cy
b
e
r
cr
im
e
ac
tiv
ity
b
as
ed
o
n
r
ea
l
-
tim
e
in
tr
u
s
io
n
d
ete
ctio
n
d
ata,
em
p
h
asizin
g
th
e
s
c
ale
an
d
p
er
s
is
ten
ce
o
f
th
ese
th
r
ea
ts
.
Fig
u
r
e
1
.
Data
s
o
u
r
ce
(
h
ttp
s
://cy
b
er
m
ap
.
k
asp
er
s
k
y
.
co
m
/s
tats
#
co
u
n
tr
y
=1
4
4
&
ty
p
e=
I
DS&
p
e
r
io
d
=w
)
T
h
e
r
an
s
o
m
war
e
is
s
u
e
th
at
ca
n
b
e
d
etec
ted
f
r
o
m
th
e
in
tr
u
s
io
n
d
etec
tio
n
s
ca
n
s
y
s
tem
in
th
e
last
f
ew
wee
k
s
an
d
p
h
is
h
in
g
also
c
o
n
t
in
u
e
to
d
o
m
in
ate
th
e
cy
b
er
th
r
ea
t
lan
d
s
ca
p
e,
d
em
an
d
in
g
t
h
e
d
ev
elo
p
m
en
t
o
f
a
m
o
r
e
a
d
ap
tiv
e
a
n
d
s
ec
u
r
e
d
et
ec
tio
n
s
y
s
tem
.
Ar
o
u
n
d
m
o
r
e
t
h
an
3
0
.
2
5
%
o
f
cy
b
e
r
th
r
e
ats
r
ec
o
r
d
ed
in
t
h
e
last
f
ew
d
ec
ad
es.
T
o
o
v
er
co
m
e
th
e
s
ec
u
r
ity
g
a
p
an
d
i
m
p
r
o
v
e
ac
cu
r
ac
y
,
th
is
s
tu
d
y
im
p
lem
en
ts
th
e
d
ata
en
cr
y
p
tio
n
s
tan
d
ar
d
(
DE
S)
[
5
]
a
n
d
b
lu
m
-
b
lu
m
-
s
h
u
b
(
B
B
S)
[
6
]
e
n
cr
y
p
ti
o
n
alg
o
r
ith
m
s
.
DE
S,
as
a
s
y
m
m
etr
ic
b
lo
c
k
cip
h
er
,
is
wid
ely
u
s
ed
f
o
r
en
c
r
y
p
tin
g
p
er
s
o
n
al
d
ata,
wh
ile
B
B
S
en
h
an
ce
s
r
an
d
o
m
n
ess
an
d
s
ec
u
r
it
y
in
k
ey
g
en
er
atio
n
.
R
ec
en
t
f
ea
s
ib
ilit
y
tes
tin
g
co
n
f
ir
m
s
th
at
th
e
im
p
r
o
v
ed
DE
S
-
B
B
S
m
eth
o
d
s
ig
n
if
ican
tly
s
tr
en
g
th
en
s
en
cr
y
p
tio
n
s
ec
u
r
ity
wh
ile
m
ain
tai
n
in
g
ef
f
icien
cy
,
with
av
er
a
g
e
p
r
o
ce
s
s
in
g
tim
es
o
f
o
n
l
y
2
s
ec
o
n
d
s
.
T
ab
le
1
p
r
esen
ts
ex
am
p
les
o
f
en
cr
y
p
tio
n
an
d
d
ec
r
y
p
tio
n
r
esu
lts
,
d
em
o
n
s
tr
atin
g
th
e
r
o
b
u
s
tn
ess
an
d
e
f
f
icien
cy
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
T
ab
le
1
.
E
n
cr
y
p
tio
n
d
ec
r
y
p
tio
n
tex
t (
h
ttp
s
://d
o
i.o
r
g
/1
0
.
6
3
4
4
7
/jimik
.
v
6
i2
.
1
3
8
5
)
N
o
P
l
a
i
n
t
t
e
x
t
C
h
i
p
e
r
t
e
x
t
Ti
me
p
r
o
c
e
ss
1
G
r
e
a
t
!
Y
o
u
r
w
o
r
k
i
s
v
e
r
y
g
o
o
d
a
n
d
d
e
t
a
i
l
e
d
.
I
r
e
a
l
l
y
a
p
p
r
e
c
i
a
t
e
y
o
u
r
e
f
f
o
r
t
a
n
d
d
e
d
i
c
a
t
i
o
n
i
n
c
o
mp
l
e
t
i
n
g
t
h
i
s t
a
s
k
.
u
u
z
j
E
g
o
B
1
4
n
x
+
TF6
o
H
v
R
1
K
b
mY
f
O
j
G
n
e
g
V
g
I
f
R
9
j
z
9
M
i
P
u
K
7
U
c
y
l
u
/
m
j
a
W
K
G
L
y
X
K
LK
q
Y
K
+
d
c
D
J4
3
c
a
W
o
D
Jb
6
U
7
s
x
R
d
3
a
H
I
y
V
3
z
e
4
n
U
s
y
M
i
7
n
w
W
F
t
x
V
T7
X
8
n
V
H
+
g
d
3
b
I
4
LA
ZZ
k
Q
0
o
O
S
8
X
L6
p
S
t
v
mJQ
+
W
F
6
mz
l
K
ZWF
X
Lf
M
A
V
F
f
H
2
F
U=
5
ms
2
P
e
r
h
a
p
s w
e
c
o
u
l
d
c
o
n
si
d
e
r
so
m
e
mi
n
o
r
i
mp
r
o
v
e
me
n
t
s t
o
t
h
e
u
ser
i
n
t
e
r
f
a
c
e
t
o
ma
k
e
i
t
m
o
r
e
u
ser
-
f
r
i
e
n
d
l
y
.
I
b
e
l
i
e
v
e
i
t
w
o
u
l
d
i
m
p
r
o
v
e
t
h
e
o
v
e
r
a
l
l
u
ser
e
x
p
e
r
i
e
n
c
e
.
t
O
X
P
b
TG
U
c
M
5
n
4
y
B
D
a
Eb
LY
k
i
6
x
n
J
O
9
I
C
C
U
B
3
B
a
z
A
p
sR
4
C
+
M
R
4
y
4
t
U
f
X
F
o
K
l
7
o
k
F
v
k
7
3
d
U
3
a
/
1
e
O
3
k
0
1
+
q
t
o
R
d
s
y
B
H
n
A
4
7
w
X
EH
c
2
8
W
C
w
8
8
LJ
d
n
o
p
R
2
f
b
v
f
t
m8
i
0
t
f
M
y
t
l
M
q
H
i
7
3
s
4
V
X
w
W
x
P
O
Lq
l
P
L
x
F
i
H
f
I
C
A
X
8
2
Q
TEY
Td
1
f
Q
/
/
D
0
g
A
Y
k
4
z
U
n
n
o
W
Q
h
5
JA
3
N
Eb
B
k
k
x
X
i
Q
O
9
C
s
=
2
ms
3
Y
o
u
r
p
r
e
s
e
n
t
a
t
i
o
n
i
s
a
l
r
e
a
d
y
g
o
o
d
,
b
u
t
t
r
y
t
o
s
p
e
a
k
a
t
a
s
l
o
w
e
r
p
a
c
e
a
n
d
e
n
g
a
g
e
mo
r
e
w
i
t
h
t
h
e
a
u
d
i
e
n
c
e
.
Th
i
s
w
i
l
l
ma
k
e
y
o
u
r
p
r
e
s
e
n
t
a
t
i
o
n
mo
r
e
m
e
m
o
r
a
b
l
e
a
n
d
me
mo
r
a
b
l
e
X
d
w
J6
l
0
7
4
H
y
N
n
l
a
I
n
f
p
I
EX
Lu
h
G
Q
8
R
H
mK
p
k
N
X
7
Q
x
G
v
Q
1
i
o
JH
1
N
H
s
n
k
q
3
r
O
U
b
3
b
V
4
I
S
w
c
z
e
+
Y
r
9
S
u
S
X
A
1
a
E
8
W
0
0
ZU
9
P
h
Lf
B
V
k
3
w
O
T
R
H
n
a
J
2
P
A
F
r
g
X
o
A
b
s
j
6
8
x
z
l
H
9
u
7
C
C
O
I
4
3
D
r
k
/
9
s
2
p
ZH
c
3
Z
C
2
d
W
O
c
Zj
G
h
z
G
r
7
d
Y
+
z
U
T
x
t
F
V
Y
j
i
Y
q
o
L
u
r
4
+
U
7
sW
C
f
b
B
Le
k
2
j
c
y
Y
q
/
TN
1
n
7
W
b
D
Y
7
V
k
c
7
O
z
Q
=
=
1
ms
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
I
mp
r
o
vin
g
B
o
t
n
et
h
o
s
t p
r
ed
ict
io
n
w
ith
en
cryp
tio
n
a
n
d
GR
U
fo
r
en
h
a
n
ce
d
… (
Ome
g
a
Jo
el
P
a
tr
ia
Mo
a
ta
)
143
B
u
ild
in
g
o
n
th
ese
f
o
u
n
d
atio
n
s
,
th
is
s
tu
d
y
i
n
teg
r
ates
en
cr
y
p
ti
o
n
with
m
ac
h
in
e
lea
r
n
in
g
tec
h
n
iq
u
es
to
im
p
r
o
v
e
th
e
p
r
ed
ictio
n
o
f
n
etwo
r
k
s
o
r
I
P
a
d
d
r
ess
es
s
u
s
p
ec
ted
o
f
b
ein
g
B
o
tn
ets.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
is
th
e
in
teg
r
atio
n
o
f
DE
S
an
d
B
B
S
en
cr
y
p
tio
n
with
a
d
ee
p
lear
n
i
n
g
m
o
d
el
b
ased
o
n
Gate
d
R
ec
u
r
r
en
t
Un
its
(
GR
U)
f
o
r
B
o
tn
et
h
o
s
t
p
r
ed
ictio
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
d
em
o
n
s
tr
ates
s
ig
n
if
ican
t
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
e
n
ts
,
ac
h
iev
in
g
h
ig
h
ac
c
u
r
ac
y
o
n
te
s
t
d
ata
wh
ile
m
ain
tain
in
g
r
ea
l
is
tic
ad
ap
tab
ilit
y
to
d
y
n
a
m
ic
n
etwo
r
k
co
n
d
iti
o
n
s
.
T
o
f
u
r
th
er
en
h
an
ce
r
eliab
ilit
y
,
p
r
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es
s
u
ch
as
o
u
tlier
h
a
n
d
lin
g
[
7
]
,
m
is
s
in
g
d
ata
tr
ea
tm
en
t
[
8
]
,
an
d
m
o
v
in
g
a
v
er
ag
es
ar
e
ap
p
lied
.
Mo
d
el
ef
f
icien
c
y
is
o
p
tim
ized
u
s
in
g
th
e
Ad
am
o
p
tim
izer
an
d
ea
r
ly
s
to
p
p
in
g
,
e
n
s
u
r
in
g
r
o
b
u
s
t p
er
f
o
r
m
an
ce
with
o
u
t o
v
e
r
f
itti
n
g
.
B
ased
o
n
th
ese
co
n
s
id
er
ati
o
n
s
,
th
is
s
tu
d
y
ad
d
r
ess
es
th
r
ee
k
ey
r
esear
ch
q
u
esti
o
n
s
:
i
)
Ho
w
ca
n
a
B
o
tn
et
h
o
s
t
p
r
ed
ictio
n
s
y
s
tem
b
e
d
esig
n
ed
a
n
d
o
p
tim
ized
?
ii
)
Ho
w
d
o
es
th
e
en
c
r
y
p
tio
n
alg
o
r
ith
m
af
f
ec
t
th
e
s
ec
u
r
ity
o
f
tex
t
d
ata
in
th
e
p
r
ed
i
ctio
n
s
y
s
tem
?
an
d
iii
)
H
o
w
ef
f
ec
tiv
e
ar
e
th
e
Ad
a
m
o
p
tim
izer
an
d
ea
r
ly
s
to
p
p
in
g
tech
n
iq
u
es
in
im
p
r
o
v
in
g
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
?
P
r
ev
io
u
s
s
tu
d
ies
h
av
e
n
o
t
ex
p
li
citly
ad
d
r
ess
ed
th
e
in
teg
r
atio
n
o
f
en
cr
y
p
tio
n
in
t
o
d
ee
p
lear
n
in
g
-
b
ased
B
o
tn
e
t
p
r
ed
ictio
n
,
m
ak
in
g
t
h
is
r
esear
ch
an
im
p
o
r
tan
t
co
n
tr
ib
u
tio
n
.
T
h
e
s
ig
n
if
ican
ce
o
f
th
is
wo
r
k
lies
in
its
d
u
al
f
o
cu
s
o
n
ac
cu
r
ac
y
an
d
s
ec
u
r
ity
.
B
y
i
n
teg
r
atin
g
en
cr
y
p
tio
n
with
GR
U
-
b
ased
p
r
ed
ictio
n
,
th
e
s
tu
d
y
p
r
o
v
id
es
a
s
ec
u
r
e
an
d
ef
f
icien
t
f
r
am
ew
o
r
k
f
o
r
B
o
tn
et
h
o
s
t
d
etec
tio
n
.
T
h
is
ap
p
r
o
ac
h
n
o
t
o
n
ly
s
tr
en
g
th
e
n
s
d
ata
p
r
o
te
ctio
n
b
u
t
also
en
h
an
ce
s
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
,
o
f
f
er
in
g
p
r
ac
tical
b
en
ef
its
f
o
r
g
o
v
er
n
m
e
n
ts
,
en
ter
p
r
is
es,
an
d
s
er
v
ice
p
r
o
v
id
er
s
.
Ultim
a
tely
,
th
e
p
r
o
p
o
s
ed
s
y
s
tem
co
n
tr
ib
u
tes
t
o
b
u
ild
i
n
g
r
esil
ien
t
cy
b
er
s
ec
u
r
ity
in
f
r
ast
r
u
ctu
r
es
in
th
e
er
a
o
f
So
ciety
5
.
0
,
wh
e
r
e
in
ter
co
n
n
ec
ted
I
o
T
a
n
d
AI
s
y
s
tem
s
ar
e
in
cr
ea
s
in
g
ly
v
u
ln
er
ab
le
to
ex
p
lo
itatio
n
.
2.
RE
L
E
A
T
E
D
WO
RK
S
A
b
asic
u
n
d
er
s
tan
d
in
g
o
f
th
e
p
r
in
cip
les
o
f
d
ata
en
cr
y
p
tio
n
a
n
d
b
asic
tech
n
iq
u
es
o
f
m
ac
h
in
e
lear
n
in
g
an
d
s
tan
d
ar
d
en
cr
y
p
tio
n
ar
e
th
e
f
o
u
n
d
atio
n
o
f
th
is
r
esear
ch
.
I
n
th
is
p
ap
er
,
B
o
t
n
et
s
will
b
e
d
etec
ted
b
ased
o
n
th
e
ch
ar
ac
ter
is
tics
o
f
n
etwo
r
k
tr
af
f
ic
an
d
its
f
lo
w
with
m
ac
h
in
e
lear
n
in
g
.
E
x
is
tin
g
B
o
t
n
et
d
etec
tio
n
s
y
s
tem
s
ar
e
m
ain
ly
b
ased
o
n
in
tr
u
s
io
n
d
etec
tio
n
a
n
d
id
e
n
tific
at
io
n
o
f
co
m
m
an
d
an
d
co
n
tr
o
l
(
C
&
C
)
s
er
v
er
s
u
s
in
g
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
tech
n
iq
u
es.
T
h
e
m
ai
n
lim
itatio
n
o
f
cu
r
r
en
t
m
o
d
els
is
th
at
th
e
n
am
e
o
f
th
e
C
&
C
s
er
v
er
ca
n
ch
an
g
e
f
r
e
q
u
en
tly
u
s
in
g
v
ar
io
u
s
n
am
e
-
c
h
an
g
in
g
al
g
o
r
ith
m
s
a
n
d
in
t
r
u
s
io
n
s
ig
n
atu
r
es.
T
h
i
s
r
esear
ch
f
o
cu
s
es
o
n
B
o
t
n
et
d
etec
tio
n
b
ased
o
n
n
etwo
r
k
tr
a
f
f
ic.
An
alter
n
ativ
e
ap
p
r
o
ac
h
in
d
ev
elo
p
in
g
th
is
m
ac
h
in
e
lear
n
in
g
m
o
d
el
also
in
v
o
lv
es
e
n
cr
y
p
tio
n
t
o
m
ain
ta
in
in
f
o
r
m
atio
n
s
ec
u
r
ity
an
d
s
ec
u
r
e
th
e
ex
tr
ac
tio
n
o
f
r
esu
lts
f
r
o
m
e
ac
h
o
p
er
atio
n
,
in
clu
d
in
g
co
r
r
elatio
n
r
esu
lts
,
en
tr
o
p
y
r
esu
lts
,
an
d
m
o
d
el
ev
a
lu
atio
n
r
esu
lts
[
9
]
.
2
.
1
.
B
o
t
n
et
B
o
t
n
et
is
a
n
etwo
r
k
o
f
“b
o
ts
,
”
wh
ich
is
a
co
llectio
n
o
f
in
ter
c
o
n
n
ec
ted
n
etwo
r
k
s
m
a
n
ag
ed
b
y
a
s
in
g
le
en
tity
k
n
o
wn
as
a
“b
o
t
-
h
er
d
er
.
”
I
f
an
attac
k
er
i
n
ten
d
s
to
tar
g
et
a
lar
g
e
o
r
g
a
n
izatio
n
s
u
ch
as
Go
o
g
le
o
r
Am
az
o
n
,
t
h
ey
will
n
ee
d
s
ig
n
if
ican
t
co
m
p
u
tin
g
r
eso
u
r
ce
s
to
p
en
etr
ate
a
web
s
er
v
er
’
s
s
ec
u
r
ity
f
ir
ewa
ll.
E
s
s
en
tially
,
attac
k
er
s
f
o
r
m
a
n
ar
m
y
u
s
in
g
th
eir
m
alwa
r
e
n
etwo
r
k
.
T
h
ey
in
itially
tar
g
et
in
d
iv
id
u
al
u
s
er
s
th
r
o
u
g
h
h
ac
k
in
g
m
eth
o
d
s
s
u
ch
as
p
h
is
h
in
g
o
r
m
alwa
r
e
a
ttack
s
,
g
ain
in
g
co
m
m
an
d
a
n
d
co
n
tr
o
l
o
v
er
th
eir
d
ev
ices.
T
h
e
attac
k
er
t
h
en
ta
k
es
o
v
er
all
th
e
c
o
m
p
r
o
m
is
ed
d
ev
ices,
f
o
r
m
in
g
th
e
m
in
to
a
n
etwo
r
k
.
W
ith
th
e
h
elp
o
f
th
is
n
etwo
r
k
,
th
e
attac
k
er
ca
n
lau
n
ch
d
en
ial
-
of
-
s
er
v
ice
attac
k
s
o
r
b
r
u
te
-
f
o
r
ce
attac
k
s
,
wh
ich
ca
n
d
is
r
u
p
t
n
etwo
r
k
tr
a
f
f
ic
o
r
d
a
m
ag
e
th
e
v
ictim
’
s
n
etwo
r
k
s
er
v
er
s
[
1
0
]
.
T
h
e
n
etwo
r
k
tr
a
f
f
ic
m
ec
h
a
n
is
m
is
illu
s
tr
ated
in
Fig
u
r
e
2
.
2
.
2
.
Da
t
a
prepro
ce
s
s
ing
T
h
e
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
,
illu
s
tr
ated
in
th
e
f
is
h
b
o
n
e
d
iag
r
a
m
in
Fig
u
r
e
3
,
s
tar
t
with
th
e
cs4
4
8
b
_
ip
asn
d
ataset
wh
ich
co
n
tain
s
B
o
t
n
et
-
r
elate
d
in
f
o
r
m
atio
n
.
T
h
e
in
itial
d
ataset
s
tatis
tics
s
h
o
w
a
m
ea
n
o
f
4
8
%,
a
m
ed
ia
n
o
f
5
1
%,
a
n
d
a
m
o
d
e
o
f
0
%.
Sev
er
al
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
ar
e
ap
p
lied
,
s
tar
tin
g
with
o
u
tlier
h
an
d
lin
g
to
d
etec
t
an
d
r
em
o
v
e
ex
tr
em
e
v
alu
es
th
a
t
m
ay
in
ter
f
er
e
with
th
e
m
o
d
elin
g
p
r
o
ce
s
s
[
7
]
.
Miss
in
g
d
ata
h
an
d
lin
g
is
also
p
er
f
o
r
m
e
d
to
ad
d
r
ess
g
ap
s
in
th
e
d
ataset
[
8
]
.
I
n
ad
d
itio
n
,
t
h
e
m
o
v
in
g
av
er
ag
e
tech
n
iq
u
e
is
u
s
ed
to
s
m
o
o
th
o
u
t
d
ata
f
lu
ctu
atio
n
s
an
d
h
ig
h
li
g
h
t
g
en
er
al
tr
e
n
d
s
,
with
v
is
u
aliza
tio
n
th
r
o
u
g
h
lin
e
g
r
ap
h
s
.
As
a
wid
ely
u
s
ed
tech
n
iq
u
e
in
tim
e
s
er
ies
an
a
ly
s
is
,
m
o
v
in
g
av
e
r
ag
es
h
elp
s
u
m
m
ar
ize
o
v
er
all
d
ata
p
atter
n
s
ef
f
icien
tly
[
1
0
]
.
Af
ter
p
r
e
-
p
r
o
ce
s
s
in
g
,
th
e
ch
a
r
ac
ter
i
s
tics
o
f
th
e
d
ataset
ch
an
g
e
to
a
m
ea
n
o
f
2
8
.
2
%,
a
m
ed
ian
o
f
2
9
.
9
%,
an
d
a
m
o
d
e
o
f
4
9
.
9
%,
r
ev
ea
lin
g
a
n
an
o
m
alo
u
s
n
etwo
r
k
with
a
r
ep
ea
tin
g
p
atter
n
,
wh
ich
is
a
n
ew
asp
ec
t
ad
ap
te
d
f
r
o
m
t
h
e
r
ef
er
en
ce
liter
atu
r
e.
T
o
im
p
r
o
v
e
th
e
p
r
ed
ictiv
e
ca
p
ab
ilit
y
,
u
s
in
g
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
s
(
R
NN
)
ar
e
u
s
ed
to
an
aly
ze
th
e
3
0
-
d
ay
f
o
r
war
d
p
r
e
d
ictio
n
p
er
io
d
b
y
co
m
p
ar
in
g
t
h
e
“L
o
ca
l
I
P
Flo
w”
v
alu
es
ac
r
o
s
s
d
a
y
s
f
o
r
ten
d
i
f
f
er
en
t
I
Ps
.
T
h
is
ap
p
r
o
ac
h
h
elp
s
id
en
tify
d
aily
p
atter
n
s
i
n
n
etwo
r
k
ac
tiv
ity
.
Stu
d
ies
h
av
e
s
h
o
wn
th
at
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
ST
M)
n
etwo
r
k
s
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
m
eth
o
d
s
a
n
d
b
aselin
e
R
NN
m
o
d
els,
esp
ec
i
ally
f
o
r
lo
n
g
-
ter
m
f
o
r
ec
asts
.
Fo
r
ex
am
p
le,
L
STM
m
o
d
els
h
av
e
b
ee
n
u
s
ed
t
o
p
r
ed
ict
lak
e
wate
r
le
v
els
with
7
8
%
h
ig
h
e
r
ac
cu
r
ac
y
th
an
th
e
Naïv
e
Me
t
h
o
d
f
o
r
6
0
-
d
ay
f
o
r
ec
asts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
2
,
J
u
ly
20
26
:
141
-
1
58
144
Ad
d
itio
n
ally
,
GR
U
h
av
e
b
ee
n
s
h
o
wn
to
b
e
ef
f
ec
tiv
e
f
o
r
l
o
n
g
er
p
r
ed
ictio
n
p
e
r
io
d
s
,
s
u
c
h
as
1
2
0
-
d
a
y
wate
r
lev
el
f
o
r
ec
asts
,
wh
er
e
GR
U
o
u
tp
er
f
o
r
m
s
b
o
th
R
NN
an
d
L
STM
in
p
er
f
o
r
m
a
n
ce
m
etr
ics.
Du
e
to
th
eir
f
aster
tr
ain
in
g
tim
e,
GR
Us
ar
e
we
ll
-
s
u
ited
f
o
r
r
ea
l
-
tim
e
h
y
d
r
o
l
o
g
ical
p
r
ed
ictio
n
s
th
at
r
eq
u
i
r
e
f
r
eq
u
e
n
t
m
o
d
el
u
p
d
ates.
Hy
b
r
id
m
o
d
els,
wh
ich
in
teg
r
ate
R
NNs,
L
STM
s
,
an
d
GR
Us
with
o
th
er
s
tatis
tica
l
an
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es su
ch
as L
STM
-
C
NN,
f
u
r
th
er
im
p
r
o
v
e
th
e
ac
c
u
r
a
cy
an
d
e
f
f
icien
cy
o
f
p
r
ed
ictio
n
s
[
1
0
]
.
Fig
u
r
e
2
.
I
ll
u
s
tr
atio
n
o
f
g
en
er
a
l b
o
t n
etwo
r
k
ar
ch
itectu
r
e
Fig
u
r
e
3
.
Fis
h
b
o
n
e
d
iag
r
am
o
f
en
cr
y
p
tio
n
B
o
t
n
et
,
GR
U
R
NN
p
r
o
ce
s
s
es
th
e
in
p
u
t
s
eq
u
en
ce
X1
,
X2
.
.
.
.
.
.
.
.
.
.
Xt.
At
ea
ch
tim
e
s
tep
“t”,
th
e
n
etwo
r
k
u
p
d
ates
its
h
id
d
en
s
tate
“h
”,
b
y
tak
in
g
in
t
o
ac
co
u
n
t
th
e
in
p
u
t
o
f
t
h
e
cu
r
r
en
t
tim
e
s
tep
“x
,
”
an
d
th
e
h
id
d
en
s
tate
f
r
o
m
th
e
tim
e
s
tep
“h
”
in
Fig
u
r
e
4
.
T
h
is
h
id
d
en
s
tate
is
ca
lcu
lated
u
s
in
g
(
1
)
:
ℎ
1
=
(
ℎ
×
ℎ1
+
×
+
ℎ
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
I
mp
r
o
vin
g
B
o
t
n
et
h
o
s
t p
r
ed
ict
io
n
w
ith
en
cryp
tio
n
a
n
d
GR
U
fo
r
en
h
a
n
ce
d
… (
Ome
g
a
Jo
el
P
a
tr
ia
Mo
a
ta
)
145
w
h
er
e
“h
”
is
th
e
h
id
d
e
n
s
tate
at
cu
r
r
e
n
t
tim
e
s
tep
“t”,
h
is
th
e
h
id
d
e
n
tim
e
s
tep
o
f
th
e
p
r
e
v
i
o
u
s
tim
e
s
tep
“t
-
1
”
x
is
th
e
in
p
u
t
at
cu
r
r
en
t
tim
e
s
p
an
“t”,
w
is
th
e
weig
h
t
m
atr
i
x
ass
o
ciate
d
with
th
e
h
i
d
d
en
s
tate,
w
is
th
e
weig
h
t
m
atr
ix
f
o
r
th
e
i
n
p
u
t.
h
id
d
en
s
tate,
w
is
th
e
weig
h
t
m
atr
ix
f
o
r
th
e
in
p
u
t.
b
h
is
th
e
b
ias
v
e
cto
r
“
”
is
a
n
o
n
-
lin
ea
r
ac
tiv
atio
n
f
u
n
ctio
n
,
s
u
c
h
as
tan
h
f
u
n
ctio
n
o
r
R
eL
U,
wh
ich
in
tr
o
d
u
ce
s
n
o
n
-
lin
ea
r
it
y
to
th
e
n
etwo
r
k
an
d
h
el
p
s
it
lear
n
co
m
p
lex
p
atter
n
s
.
co
m
p
le
x
p
atter
n
s
.
T
h
e
o
u
t
p
u
t
at
ea
c
h
tim
e
s
tep
“y
”
is
c
alcu
lated
u
s
in
g
th
e
cu
r
r
en
t
h
id
d
en
s
tate
“h
t”
with
(
2
)
:
=
(
×
ℎ
+
)
(
2
)
“
y
”
o
u
t
p
u
t
s
t
e
p
a
t
t
i
m
e
“
t
”
,
“
w
y
”
i
s
t
h
e
w
e
i
g
h
t
m
a
t
r
i
x
f
o
r
t
h
e
o
u
t
p
u
t
l
a
y
e
r
t
“
b
y
”
is
t
h
e
b
i
as
v
e
c
t
o
r
f
o
r
t
h
e
o
u
t
p
u
t
a
n
d
‘
ϕ
’
a
s
t
h
e
a
c
ti
v
a
t
i
o
n
f
u
n
c
t
i
o
n
u
s
e
d
i
n
t
h
e
o
u
t
p
u
t
l
a
y
e
r
.
T
h
e
R
N
N
is
t
r
a
i
n
e
d
b
y
m
i
n
i
m
i
z
i
n
g
a
l
o
s
s
f
u
n
c
t
i
o
n
L
o
v
e
r
t
h
e
e
n
t
i
r
e
s
e
q
u
e
n
c
e
,
c
a
l
c
u
l
at
e
d
a
s
t
h
e
s
u
m
o
f
th
e
i
n
d
i
v
i
d
u
a
l
l
o
s
s
es
a
t
ea
c
h
t
i
m
e
s
t
e
p
i
n
(
3
)
:
=
∑
=
1
(
)
(
3
)
W
h
er
e
“L
”
r
ep
r
esen
ts
th
e
l
o
s
s
at
tim
e
s
tep
“t,
”
an
d
“y
t”
r
e
p
r
esen
ts
th
e
an
ticip
ated
o
u
tp
u
t
a
t
tim
e
s
tep
“t.
”
T
h
e
ac
tu
al
tar
g
et
o
u
tp
u
t
y
at
tim
e
s
tep
“t,
”
wh
er
e
“t”
an
d
“T
”
r
ep
r
esen
t
th
e
to
tal
n
u
m
b
er
o
f
tim
e
s
tep
s
o
f
th
e
s
eq
u
en
ce
.
T
h
e
g
ate
d
GR
U
ar
ch
itectu
r
e
is
s
h
o
wn
.
T
h
ey
ar
e
x
t
an
d
y
t
f
o
r
in
p
u
t
an
d
o
u
tp
u
t,
r
t
an
d
zt
f
o
r
r
eset
an
d
u
p
d
ate
g
ates,
an
d
h
t
an
d
h
t
f
o
r
ac
tiv
atio
n
an
d
ca
n
d
id
ate
ac
tiv
atio
n
,
r
esp
ec
tiv
ely
.
T
h
e
two
g
ates
[
1
0
]
h
av
e
th
e
f
o
llo
win
g
d
ef
in
itio
n
s
in
(
4
)
:
=
(
+
ℎ
−
1
+
)
(
4
)
Fig
u
r
e
4
.
Flo
w
d
ia
g
r
am
o
f
R
NN
Fig
u
r
e
5
is
a
m
o
r
e
in
-
d
ep
th
in
ter
p
r
etatio
n
o
f
th
e
g
r
o
u
p
a
r
ch
itectu
r
e
.
Up
d
ate
g
ate
"Z
"
d
eter
m
in
es
wh
ich
b
its
o
f
th
e
lo
n
g
-
ter
m
s
t
ate
s
h
o
u
ld
b
e
d
elete
d
an
d
wh
i
ch
s
h
o
u
ld
b
e
ad
d
ed
.
W
h
ich
p
ar
t
o
f
th
e
p
r
ev
io
u
s
s
tate
is
s
h
o
wn
to
th
e
m
ain
la
y
er
o
r
a
ctiv
atio
n
ca
n
d
id
ate
"h
"
is
d
eter
m
in
ed
b
y
th
e
r
eset
g
ate
"r
tt."
T
h
e
GR
U
m
o
d
el
ca
n
t
h
er
ef
o
r
e
b
e
e
x
p
r
es
s
ed
in
th
e
f
o
llo
win
g
way
:
=
(
+
ℎ
ℎ
−
1
+
(
5
)
−
ℎ
=
ℎ
(
ℎ
+
ℎ
(
.
ℎ
−
1
)
+
ℎ
)
(
6
)
ℎ
=
(
1
−
)
.
ℎ
−
1
+
.
~
ℎ
(
7
)
w
h
er
e
ca
n
d
id
ate
ac
tiv
ity
“h
t”
an
aly
ze
s
th
e
in
p
u
t v
ec
to
r
“
x
t”
an
d
th
e
p
r
ev
i
o
u
s
s
h
o
r
t
-
ter
m
s
t
ate
“h
t−1
”
an
d
o
n
ly
th
e
m
o
s
t r
elev
an
t
p
ar
t is st
o
r
ed
in
th
e
v
ec
to
r
“h
t”.
T
h
is
v
ec
t
o
r
“h
t”
r
e
p
r
esen
ts
th
e
o
u
t
p
u
t state
o
f
th
e
m
o
d
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
2
,
J
u
ly
20
26
:
141
-
1
58
146
Fig
u
r
e
5
.
Ar
c
h
itectu
r
e
o
f
GR
U
ce
ll
2
.
3
.
E
ncry
ptio
n
2
.
3
.
1
.
Cry
pto
g
r
a
ph
y
C
r
y
p
to
g
r
ap
h
y
s
er
v
es
as
a
m
eth
o
d
f
o
r
in
d
iv
id
u
als
to
co
m
m
u
n
icate
s
ec
r
et
m
ess
ag
es
s
e
cu
r
ely
with
ea
ch
o
th
e
r
o
r
with
th
eir
i
n
ten
d
ed
r
ec
i
p
ien
ts
.
I
t
in
v
o
l
v
es
th
e
u
s
e
o
f
a
co
d
e
s
y
s
tem
to
en
s
u
r
e
th
at
t
h
e
m
ess
ag
e
r
em
ain
s
in
co
m
p
r
eh
e
n
s
ib
le
to
t
h
ir
d
p
ar
ties
o
r
in
d
iv
i
d
u
als
with
m
alicio
u
s
in
te
n
t,
s
u
ch
as
h
a
ck
er
s
.
T
h
is
s
ec
u
r
it
y
m
ea
s
u
r
e
b
ec
o
m
es
esp
ec
ially
im
p
o
r
ta
n
t
wh
en
th
e
tr
a
n
s
m
is
s
io
n
s
y
s
tem
is
v
u
ln
er
ab
le
to
in
ter
ce
p
tio
n
b
y
u
n
au
th
o
r
ized
p
ar
ties
.
C
r
y
p
to
g
r
ap
h
y
s
er
v
es
as
a
tech
n
iq
u
e
f
o
r
p
r
eser
v
in
g
a
n
d
tr
an
s
m
itti
n
g
d
ata
in
a
f
o
r
m
at
th
at
ca
n
o
n
ly
b
e
u
n
d
er
s
to
o
d
b
y
t
h
o
s
e
with
th
e
p
r
o
p
er
d
ec
r
y
p
tio
n
k
ey
.
u
n
d
er
s
to
o
d
b
y
th
o
s
e
with
th
e
p
r
o
p
er
d
ec
r
y
p
tio
n
k
ey
,
en
s
u
r
in
g
th
e
p
r
o
tectio
n
o
f
cr
itical
in
f
o
r
m
at
io
n
wh
eth
e
r
it
is
s
to
r
e
d
o
n
v
a
r
io
u
s
s
to
r
ag
e
m
ed
ia
o
r
tr
an
s
m
itted
o
v
er
a
co
m
m
u
n
icatio
n
s
n
etwo
r
k
[
1
1
]
.
C
r
y
p
t
o
g
r
ap
h
y
is
th
e
s
cien
ce
an
d
en
g
in
ee
r
in
g
u
s
ed
to
p
r
o
tect
d
ata
f
r
o
m
u
n
au
th
o
r
ize
d
th
ir
d
p
a
r
ties
.
T
h
e
two
f
u
n
d
a
m
en
tal
p
r
o
ce
s
s
es
in
cr
y
p
to
g
r
a
p
h
y
ar
e
e
n
cr
y
p
tio
n
an
d
d
ec
r
y
p
tio
n
.
E
n
cr
y
p
tio
n
in
v
o
lv
es
tr
an
s
f
o
r
m
in
g
p
lain
t
ex
t
in
to
cip
h
e
r
tex
t
u
s
in
g
a
k
ey
.
I
n
co
n
tr
ast,
d
ec
r
y
p
tio
n
in
v
o
lv
es
co
n
v
er
tin
g
th
e
cip
h
er
tex
t
b
ac
k
to
th
e
o
r
ig
in
al
p
lain
tex
t
u
s
in
g
th
e
s
am
e
k
ey
.
T
h
is
p
r
o
ce
s
s
is
p
ar
ticu
lar
ly
r
elev
an
t
wh
en
u
s
in
g
s
y
m
m
etr
ic
k
ey
cr
y
p
t
o
g
r
ap
h
y
,
wh
er
e
th
e
s
am
e
k
ey
is
u
s
ed
f
o
r
b
o
th
en
cr
y
p
tio
n
an
d
d
ec
r
y
p
tio
n
[
1
2
]
.
I
n
alm
o
s
t a
ll c
r
y
p
to
g
r
ap
h
ic
ap
p
licatio
n
s
,
th
e
u
s
e
o
f
p
s
eu
d
o
r
an
d
o
m
n
u
m
b
er
s
is
v
er
y
co
m
m
o
n
.
T
h
ese
n
u
m
b
er
s
ex
h
ib
it
ch
ar
ac
ter
is
tics
th
at
s
im
u
late
tr
u
e
r
an
d
o
m
n
ess
,
m
a
k
in
g
it
d
if
f
icu
lt
f
o
r
m
alicio
u
s
m
an
ip
u
latio
n
o
f
th
e
ap
p
licatio
n
.
r
a
n
d
o
m
n
ess
,
m
a
k
in
g
it
d
if
f
ic
u
lt
f
o
r
m
an
ip
u
lat
io
n
.
T
h
e
al
g
o
r
ith
m
r
esp
o
n
s
i
b
le
f
o
r
g
e
n
er
atin
g
t
h
e
s
e
p
s
eu
d
o
r
an
d
o
m
n
u
m
b
er
s
,
w
h
ich
ar
e
ess
en
tially
s
eq
u
en
ce
s
o
f
b
its
,
is
r
ef
er
r
ed
to
as
a
p
s
eu
d
o
r
an
d
o
m
n
u
m
b
e
r
g
en
er
ato
r
(
PR
NG)
[
1
3
]
.
A
PR
NG
is
a
d
eter
m
in
is
t
ic
alg
o
r
ith
m
d
esig
n
ed
t
o
g
en
er
ate
s
eq
u
en
ce
s
th
at
s
u
cc
e
s
s
f
u
lly
p
ass
v
ar
io
u
s
r
an
d
o
m
n
ess
tes
ts
.
T
h
ese
g
en
er
ato
r
s
o
f
t
en
u
s
e
r
ec
u
r
s
io
n
to
g
en
er
ate
s
eq
u
en
ce
s
o
f
n
u
m
b
e
r
s
th
at
m
im
ic
r
an
d
o
m
n
ess
.
I
n
th
is
p
r
o
ce
s
s
,
n
u
m
b
er
s
ar
e
g
e
n
er
ated
r
ec
u
r
s
iv
ely
,
with
ea
ch
s
u
b
s
eq
u
en
t
n
u
m
b
e
r
in
th
e
s
eq
u
en
ce
d
eter
m
in
e
d
b
y
th
e
p
r
ev
io
u
s
n
u
m
b
er
.
T
h
e
iter
atio
n
b
e
g
in
s
with
a
s
p
ec
if
ic
v
alu
e
k
n
o
wn
as
th
e
s
ee
d
.
I
m
p
o
r
tan
tly
,
wh
e
n
th
e
r
e
p
etitio
n
s
tar
ts
with
th
e
s
am
e
s
ee
d
,
it
will
p
r
o
d
u
ce
th
e
s
am
e
s
eq
u
en
ce
.
T
h
e
len
g
t
h
o
f
th
e
s
eq
u
e
n
ce
b
ef
o
r
e
th
e
r
ep
etitio
n
is
ca
lled
th
e
p
er
io
d
o
r
cy
cle
len
g
th
[
1
4
]
.
Fro
m
th
e
en
c
r
y
p
tio
n
o
f
t
h
e
u
s
e
o
f
th
e
DE
S a
n
d
B
B
S m
eth
o
d
s
.
2
.
3
.
2
.
Da
t
a
encr
y
ptio
n sta
nd
a
rd
T
h
e
DE
S
alg
o
r
ith
m
is
a
s
u
b
s
et
o
f
s
y
m
m
etr
ic
cr
y
p
to
g
r
a
p
h
y
,
wh
ic
h
s
p
ec
if
ically
f
alls
u
n
d
er
t
h
e
ca
teg
o
r
y
o
f
b
lo
ck
cip
h
e
r
s
.
Alth
o
u
g
h
wid
ely
ad
o
p
te
d
an
d
r
ec
o
g
n
ized
as th
e
s
tan
d
ar
d
s
y
m
m
etr
ic
k
ey
alg
o
r
ith
m
,
DE
S
is
o
b
s
o
lete
d
u
e
to
s
ec
u
r
ity
co
n
ce
r
n
s
a
n
d
h
as
b
ee
n
r
ep
la
ce
d
b
y
n
ewe
r
alg
o
r
ith
m
s
.
DE
S
o
p
er
ates
o
n
6
4
-
b
it
b
lo
ck
s
,
m
ea
n
in
g
it
en
c
r
y
p
ts
an
d
p
r
o
ce
s
s
es
6
4
b
its
o
f
p
lain
tex
t
to
p
r
o
d
u
ce
6
4
b
its
o
f
cip
h
er
tex
t.
T
h
is
en
cr
y
p
tio
n
p
r
o
ce
s
s
in
v
o
lv
es
th
e
u
s
e
o
f
a
5
6
-
b
it
in
ter
n
al
k
ey
o
r
s
u
b
k
ey
[
1
5
]
.
Data
s
ec
u
r
ity
h
as
g
r
ea
t
s
ig
n
if
ican
ce
in
t
h
e
co
n
tem
p
o
r
ar
y
d
ig
ital
lan
d
s
ca
p
e,
an
d
t
h
e
DE
S
alg
o
r
ith
m
s
tan
d
s
o
u
t
as
a
wid
ely
u
s
ed
cr
y
p
to
g
r
ap
h
ic
alg
o
r
ith
m
to
m
ain
tain
d
ata
co
n
f
id
e
n
tiality
an
d
in
teg
r
ity
.
As
a
f
u
n
d
a
m
en
tal
to
o
l
in
th
e
f
ield
o
f
cr
y
p
to
g
r
ap
h
y
,
DE
S
p
lay
s
a
v
it
al
r
o
le
in
ad
d
r
ess
in
g
th
e
ch
allen
g
es
p
o
s
ed
b
y
th
e
ev
er
-
e
v
o
lv
i
n
g
d
ig
ital
er
a
[
1
6
]
.
Plain
t
ex
t
r
ef
er
s
to
th
e
in
it
ial
m
ess
ag
e
o
r
th
e
o
r
ig
in
al
m
ess
ag
e
s
en
t
in
th
e
co
m
m
u
n
icatio
n
p
r
o
ce
s
s
.
co
m
m
u
n
icatio
n
p
r
o
ce
s
s
.
T
h
is
p
lain
tex
t
u
n
d
er
g
o
es
th
e
p
r
o
c
ess
o
f
en
cr
y
p
tio
n
a
n
d
d
ec
r
y
p
tio
n
.
C
ip
h
er
t
ex
t,
o
n
th
e
o
th
er
h
an
d
,
r
ep
r
esen
ts
th
e
h
id
d
en
m
ess
ag
e
r
esu
ltin
g
f
r
o
m
th
e
en
cr
y
p
tio
n
o
f
th
e
o
r
ig
i
n
al
m
ess
ag
e
(
p
lain
tex
t
)
d
u
r
in
g
th
e
cr
y
p
to
g
r
ap
h
y
p
r
o
ce
s
s
.
C
ip
h
er
t
ex
t
ca
n
b
e
co
n
v
er
ted
b
ac
k
to
its
o
r
ig
in
al
f
o
r
m
(
p
lain
tex
t)
u
s
in
g
th
e
p
r
o
v
id
ed
k
e
y
.
T
h
e
p
r
o
ce
s
s
in
v
o
lv
e
d
in
co
n
v
er
tin
g
d
ata
(
p
lain
tex
t)
in
to
d
is
g
u
is
ed
d
ata
(
cip
h
e
r
tex
t)
is
k
n
o
wn
as
e
n
cr
y
p
tio
n
.
T
h
e
DE
S
alg
o
r
ith
m
is
an
e
n
cr
y
p
tio
n
m
eth
o
d
u
s
ed
in
b
lo
ck
ci
p
h
er
s
y
s
tem
s
.
T
h
is
en
cr
y
p
tio
n
s
y
s
tem
s
cr
am
b
les
d
ata
b
lo
ck
b
y
b
l
o
ck
,
u
s
in
g
6
4
-
b
it
in
p
u
t
b
lo
ck
s
(
p
lain
tex
t
)
an
d
p
r
o
d
u
ce
s
o
u
tp
u
t
(
c
ip
h
er
tex
t)
in
6
4
-
b
it
b
lo
ck
s
as
well.
T
h
e
alg
o
r
ith
m
u
s
ed
is
a
s
y
m
m
etr
ic
k
ey
alg
o
r
ith
m
w
ith
a
k
ey
len
g
th
o
f
5
6
b
its
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
I
mp
r
o
vin
g
B
o
t
n
et
h
o
s
t p
r
ed
ict
io
n
w
ith
en
cryp
tio
n
a
n
d
GR
U
fo
r
en
h
a
n
ce
d
… (
Ome
g
a
Jo
el
P
a
tr
ia
Mo
a
ta
)
147
Or
ig
in
ally
estab
lis
h
ed
as
a
s
tan
d
ar
d
f
o
r
s
ec
u
r
i
n
g
t
r
an
s
m
itted
an
d
s
to
r
ed
d
ata,
th
e
DE
S
cip
h
er
s
y
s
tem
q
u
ick
ly
g
ain
e
d
in
ter
n
atio
n
al
a
d
o
p
tio
n
q
u
ick
ly
g
ain
e
d
in
ter
n
atio
n
al
ad
o
p
tio
n
f
o
r
a
v
a
r
iety
o
f
a
p
p
licatio
n
s
th
at
r
eq
u
ir
ed
en
cr
y
p
tio
n
d
u
r
i
n
g
o
p
er
atio
n
[
1
7
]
.
DE
S
is
a
s
y
m
m
etr
ic
k
ey
b
lo
ck
cip
h
er
ch
ar
ac
ter
ized
b
y
a
k
e
y
len
g
th
o
f
5
6
b
its
an
d
a
b
lo
ck
s
ize
o
f
6
4
b
its
.
Or
ig
in
ated
b
y
I
B
M
in
1
9
7
2
,
DE
S
was
o
r
ig
in
ally
d
esig
n
ed
as
a
d
ata
en
cr
y
p
tio
n
a
lg
o
r
ith
m
an
d
was
later
ad
o
p
ted
b
y
th
e
Un
ited
States
g
o
v
er
n
m
en
t
as
th
e
s
tan
d
ar
d
en
c
r
y
p
tio
n
alg
o
r
ith
m
.
E
n
cr
y
p
tio
n
alg
o
r
ith
m
o
r
ig
in
ally
im
p
lem
en
ted
wit
h
6
4
-
b
it k
ey
s
,
th
e
n
atio
n
al
s
ec
u
r
ity
ag
en
c
y
(
NSA)
later
im
p
o
s
ed
a
r
estrictio
n
,
th
e
k
ey
le
n
g
th
t
o
5
6
b
its
.
T
h
is
r
e
s
u
lted
in
DE
S
d
is
ca
r
d
in
g
8
b
it
s
f
r
o
m
th
e
o
r
i
g
in
al
64
-
b
it
k
e
y
an
d
u
s
in
g
a
co
m
p
r
ess
ed
5
6
-
b
it
k
e
y
to
en
c
r
y
p
t
d
ata
in
6
4
-
b
it
b
lo
ck
s
.
Desp
ite
its
wid
esp
r
ea
d
ad
o
p
tio
n
,
DE
S
h
as
v
u
ln
e
r
ab
ili
ties
,
esp
ec
ially
wh
en
wea
k
k
e
y
s
ar
e
u
s
ed
.
Var
io
u
s
m
o
d
es
o
f
o
p
er
atio
n
,
s
u
ch
as
C
B
C
,
E
C
B
,
C
FB
,
an
d
OF
B
,
i
n
cr
ea
s
e
its
f
lex
ib
ilit
y
.
I
n
p
ar
ticu
lar
,
DE
S
f
ac
ed
a
s
ig
n
if
ican
t
ch
allen
g
e
in
1
9
9
8
wh
en
th
e
DE
S
C
r
ac
k
er
s
u
p
er
c
o
m
p
u
ter
,
aid
e
d
b
y
m
an
y
PC
s
d
is
tr
ib
u
ted
ac
r
o
s
s
th
e
I
n
ter
n
et,
m
an
ag
e
d
t
o
cr
ac
k
DE
S
in
ju
s
t
2
2
h
o
u
r
s
[
1
8
]
.
D
E
S
b
elo
n
g
s
to
th
e
Feis
tel
cip
h
er
f
am
ily
,
an
d
its
s
tr
u
ctu
r
e
ali
g
n
s
with
th
e
ty
p
ical
ch
ar
ac
ter
is
tics
o
f
Feis
tel
cip
h
e
r
s
.
H
o
w
e
v
e
r
,
t
h
e
r
e
a
r
e
s
p
e
c
i
f
i
c
d
e
t
a
i
l
s
t
h
a
t
d
i
s
t
i
n
g
u
i
s
h
D
E
S
w
i
t
h
i
n
t
h
i
s
f
r
a
m
e
w
o
r
k
:
i
)
b
l
o
c
k
l
e
n
g
t
h
,
t
h
e
D
E
S
b
l
o
c
k
l
e
n
g
t
h
i
s
6
4
b
i
t
s
.
B
o
t
h
t
h
e
o
r
i
g
i
n
a
l
p
l
a
i
n
t
e
x
t
a
n
d
t
h
e
c
i
p
h
e
r
t
e
x
t
a
r
e
6
4
b
i
t
s
i
n
s
i
z
e
;
i
i
)
k
e
y
s
i
z
e
,
t
h
e
D
E
S
k
e
y
i
s
6
4
b
i
t
s
i
n
s
i
z
e
.
E
a
c
h
r
o
u
n
d
o
f
t
h
e
D
E
S
a
l
g
o
r
i
t
h
m
u
s
e
s
a
4
8
-
b
i
t
r
o
u
n
d
k
e
y
;
a
n
d
i
i
i
)
n
u
m
b
e
r
o
f
r
o
u
n
d
s
,
D
E
S
o
p
e
r
a
t
e
s
t
h
r
o
u
g
h
1
6
r
o
u
n
d
s
.
T
h
i
s
m
e
a
n
s
t
h
a
t
t
h
e
e
n
c
r
y
p
t
i
o
n
o
r
d
e
c
r
y
p
t
i
o
n
p
r
o
c
e
s
s
i
n
v
o
l
v
e
s
i
t
e
r
a
t
i
n
g
t
h
r
o
u
g
h
1
6
c
o
n
s
e
c
u
t
i
v
e
r
o
u
n
d
s
,
e
a
c
h
u
s
i
n
g
a
d
i
f
f
e
r
e
n
t
i
n
t
e
g
e
r
k
e
y
.
T
h
e
s
e
s
p
e
c
i
f
i
c
a
t
i
o
n
s
c
o
n
t
r
i
b
u
t
e
t
o
t
h
e
u
n
i
q
u
e
s
t
r
u
c
t
u
r
e
a
n
d
f
u
n
c
t
i
o
n
a
l
i
t
y
o
f
D
E
S
a
s
a
F
e
i
s
t
e
l
c
i
p
h
e
r
[
1
9
]
s
h
o
w
n
i
n
F
i
g
u
r
e
6
.
Fig
u
r
e
6
.
Glo
b
al
s
ch
em
e
o
f
th
e
DE
S
alg
o
r
ith
m
I
n
th
e
DE
S
e
n
cr
y
p
tio
n
p
r
o
ce
s
s
,
th
e
p
lain
tex
t
b
lo
ck
is
in
itially
d
iv
id
ed
in
to
two
p
ar
t,
th
e
le
f
t
p
ar
t
(
L
)
an
d
th
e
r
i
g
h
t
p
ar
t
(
R
)
.
I
n
t
h
e
DE
S
en
cr
y
p
tio
n
p
r
o
ce
s
s
,
th
e
p
lain
tex
t
b
lo
c
k
is
in
itially
d
i
v
id
ed
i
n
to
two
p
a
r
ts
:
th
e
lef
t
p
ar
t
(
L
)
a
n
d
th
e
r
i
g
h
t
p
ar
t
(
R
)
,
ea
ch
co
n
s
is
tin
g
o
f
3
2
b
its
.
T
h
ese
two
p
ar
ts
th
en
u
n
d
er
g
o
a
s
er
ies
o
f
1
6
r
o
u
n
d
s
in
th
e
DE
S
en
c
r
y
p
tio
n
p
r
o
ce
s
s
.
I
n
ea
ch
r
o
u
n
d
,
d
e
n
o
t
ed
as
r
o
u
n
d
i,
t
h
e
r
ig
h
t
b
lo
c
k
(
R
)
s
er
v
es
as
in
p
u
t
to
a
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
k
n
o
wn
as
f
.
I
n
th
e
f
u
n
ctio
n
f
,
th
e
r
ig
h
t
b
lo
ck
(
R
)
is
co
m
b
in
e
d
with
an
in
ter
n
al
k
ey
.
T
h
is
in
ter
n
al
k
e
y
,
wh
ich
is
s
p
ec
if
ic
to
ea
c
h
r
o
u
n
d
,
is
d
er
iv
ed
f
r
o
m
th
e
m
aster
en
c
r
y
p
tio
n
k
e
y
u
s
ed
in
DE
S.
T
h
e
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
f
p
lay
s
an
im
p
o
r
tan
t
r
o
l
e
in
tr
an
s
f
o
r
m
in
g
an
d
m
ix
i
n
g
th
e
b
its
in
th
e
r
ig
h
t
b
lo
ck
,
wh
ic
h
co
n
tr
i
b
u
tes
to
th
e
o
v
er
all
en
c
r
y
p
tio
n
p
r
o
ce
s
s
[
1
5
]
b
ec
a
u
s
e
o
f
th
e
v
u
l
n
er
ab
il
i
ty
an
d
er
a
o
f
DE
S
wh
ich
is
q
u
ite
r
esis
tan
t,
th
is
en
cr
y
p
tio
n
is
ad
d
e
d
with
B
B
S
ar
ith
m
etic
to
in
c
r
ea
s
e
th
e
r
an
d
o
m
n
ess
o
f
th
e
n
u
m
b
er
s
p
r
o
d
u
ce
d
.
2
.
3
.
3
.
B
lum
-
blum
-
s
hu
b
(
B
B
S
)
Alg
o
r
ith
m
BBS
s
er
v
es
a
s
a
p
s
eu
d
o
r
a
n
d
o
m
b
it
g
en
er
ato
r
,
p
r
o
d
u
cin
g
a
b
i
n
ar
y
s
eq
u
e
n
ce
k
n
o
wn
as
th
e
B
B
S
s
eq
u
en
ce
[
1
9
]
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
b
y
ch
o
o
s
in
g
tw
o
p
r
im
e
n
u
m
b
er
s
,
p
a
n
d
q
,
b
o
th
s
atis
f
y
in
g
th
e
co
n
d
itio
n
p
,
q
≡
3
(
m
o
d
4
)
to
e
n
s
u
r
e
cr
y
p
to
g
r
ap
h
ic
s
ec
u
r
ity
.
T
h
e
m
o
d
u
lu
s
n
is
th
en
ca
lcu
la
ted
as
th
e
p
r
o
d
u
ct
o
f
th
ese
p
r
im
e
n
u
m
b
e
r
s
(
n
=p
×
q
)
.
Nex
t,
a
r
an
d
o
m
in
te
g
er
r
is
ch
o
s
en
s
u
ch
th
at
it
is
p
r
im
e
to
n
,
m
ea
n
in
g
it
h
as
n
o
co
m
m
o
n
f
ac
t
o
r
s
with
n
.
T
h
e
in
itial
s
ee
d
i
s
s
e
t
as
x
₀=
r
²
m
o
d
n
,
wh
ich
s
er
v
es
as
th
e
s
tar
tin
g
p
o
in
t
f
o
r
g
en
er
atin
g
th
e
s
eq
u
en
ce
.
T
h
e
p
s
eu
d
o
r
an
d
o
m
s
eq
u
en
ce
is
th
en
g
en
er
ate
d
iter
ativ
ely
u
s
in
g
th
e
r
ec
u
r
r
e
n
ce
r
elatio
n
x
ₙ₊₁=
(
x
ₙ)
²
m
o
d
n
,
to
e
n
s
u
r
e
u
n
p
r
ed
ictab
le
an
d
s
tr
o
n
g
r
an
d
o
m
n
ess
p
r
o
p
er
ties
.
E
ac
h
d
ec
im
al
d
ig
it
I
is
co
n
v
er
ted
to
b
in
a
r
y
,
a
n
d
th
e
l
ea
s
t
s
ig
n
if
i
ca
n
t
b
it
(
L
SB
)
is
e
x
tr
ac
ted
to
co
n
v
er
t
th
e
g
en
e
r
a
ted
r
an
d
o
m
b
its
in
to
b
in
ar
y
f
o
r
m
.
B
y
co
n
v
en
tio
n
,
1
is
r
ep
r
esen
ted
as
1
an
d
0
as
-
1
in
t
h
e
r
ep
r
esen
tatio
n
.
I
n
a
n
u
m
b
er
o
f
ap
p
licatio
n
s
,
th
e
r
esu
ltin
g
1
an
d
-
1
s
eq
u
e
n
ce
s
ca
n
b
e
u
s
ed
as
s
p
r
ea
d
in
g
s
eq
u
e
n
ce
s
[
2
0
]
as sh
o
wn
in
F
ig
u
r
e
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
2
,
J
u
ly
20
26
:
141
-
1
58
148
Fig
u
r
e
7
.
B
lo
ck
d
iag
r
am
f
o
r
B
B
S
s
eq
u
en
ce
g
en
er
ato
r
T
h
e
BBS
n
u
m
b
er
g
en
er
ato
r
is
o
n
e
o
f
th
e
s
im
p
lest
an
d
m
o
s
t
p
o
wer
f
u
l
o
f
th
e
cr
y
p
to
g
r
ap
h
ic
ally
s
ec
u
r
e
p
s
eu
d
o
r
an
d
o
m
n
u
m
b
er
g
en
er
a
to
r
s
(
C
SP
R
N
Gs),
p
ar
ticu
lar
ly
in
ter
m
s
o
f
th
eo
r
etica
l
co
m
p
le
x
ity
.
Dev
elo
p
ed
in
1
9
8
6
b
y
L
e
n
o
r
e
B
lu
m
,
Ma
n
u
el
B
lu
m
,
an
d
Mic
h
ae
l
Sh
u
b
en
er
ato
r
BBS
[
1
2
]
,
th
e
B
B
S
alg
o
r
ith
m
u
s
es
th
e
f
o
llo
win
g
e
q
u
atio
n
t
o
g
en
e
r
ate
p
s
eu
d
o
r
an
d
o
m
n
u
m
b
er
s
.
I
n
th
is
eq
u
atio
n
,
Xn
r
ep
r
esen
ts
t
h
e
cu
r
r
en
t
v
alu
e
i
n
th
e
s
eq
u
en
ce
,
an
d
th
e
m
o
d
n
o
p
er
atio
n
d
en
o
tes
th
e
m
o
d
u
lu
s
o
p
er
atio
n
with
'
n
'
.
T
h
e
B
B
S
alg
o
r
ith
m
,
alth
o
u
g
h
s
im
p
le
in
its
f
o
r
m
u
latio
n
,
ex
h
ib
its
s
tr
o
n
g
cr
y
p
to
g
r
ap
h
ic
p
r
o
p
er
ties
th
at
m
ak
e
it
s
u
itab
le
f
o
r
s
ec
u
r
e
p
s
eu
d
o
r
an
d
o
m
n
u
m
b
er
g
e
n
er
a
tio
n
[
2
1
]
.
+
1
=
(
)
2
.
2
.
4
.
Resea
rc
h
p
a
per
T
o
s
tr
en
g
th
e
n
th
e
f
o
u
n
d
atio
n
o
f
th
is
s
tu
d
y
,
s
ev
e
r
al
r
elate
d
wo
r
k
s
o
n
B
o
tn
et
d
etec
ti
o
n
a
n
d
p
r
e
d
ictio
n
wer
e
r
ev
iewe
d
.
Pre
v
io
u
s
r
esear
ch
h
as
em
p
lo
y
ed
a
v
ar
iet
y
o
f
ap
p
r
o
ac
h
es,
r
an
g
i
n
g
f
r
o
m
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs)
f
o
r
an
al
y
z
in
g
tr
af
f
ic
p
atter
n
s
,
to
d
ec
is
io
n
tr
ee
class
if
ier
s
an
d
s
o
ci
al
co
m
m
u
n
icatio
n
d
etec
tio
n
m
eth
o
d
s
b
ased
o
n
n
etwo
r
k
f
lo
w.
W
h
ile
th
ese
s
tu
d
ies
ac
h
iev
ed
p
r
o
m
is
in
g
r
esu
lts
,
m
an
y
s
till
f
ac
e
lim
itatio
n
s
s
u
ch
as
h
ig
h
f
alse
p
o
s
itiv
e
r
ates,
lo
w
r
ec
all
v
alu
es,
o
r
in
s
u
f
f
icien
t
ad
ap
tab
ilit
y
to
ev
o
lv
in
g
attac
k
s
tr
ateg
ies.
I
n
co
n
tr
ast,
th
e
p
r
esen
t
s
tu
d
y
in
tr
o
d
u
ce
s
a
n
o
v
el
a
p
p
r
o
ac
h
t
h
at
in
teg
r
ates
DE
S
a
n
d
B
B
S
en
cr
y
p
tio
n
tech
n
iq
u
es
with
a
GR
U
-
b
ased
d
ee
p
lear
n
in
g
m
o
d
el.
T
h
is
in
teg
r
atio
n
n
o
t
o
n
ly
en
h
an
ce
s
p
r
ed
ictio
n
ac
cu
r
ac
y
b
u
t
also
en
s
u
r
es
th
e
c
o
n
f
id
en
tiality
o
f
s
en
s
itiv
e
d
ata,
ad
d
r
ess
in
g
a
cr
itical
g
ap
in
p
r
io
r
r
esear
ch
.
A
co
m
p
ar
ativ
e
s
u
m
m
ar
y
o
f
th
e
m
eth
o
d
s
,
f
ea
tu
r
es,
an
d
p
er
f
o
r
m
an
ce
m
etr
ics
f
r
o
m
ea
r
lier
s
tu
d
ies
alo
n
g
s
id
e
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
p
r
esen
ted
i
n
T
ab
le
2
.
T
ab
le
2
.
R
esear
ch
p
a
p
er
R
e
se
a
r
c
h
p
a
p
e
r
M
e
t
h
o
d
F
e
a
t
u
r
e
s
P
e
r
f
o
r
ma
n
c
e
m
e
t
r
i
c
s
(
%)
[
2
1
]
R
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
S
i
z
e
,
d
u
r
a
t
i
o
n
,
a
n
d
p
e
r
i
o
d
i
c
i
t
y
A
c
c
u
r
a
c
y
:
97
F
a
l
se
p
o
si
t
i
v
e
r
a
t
e
:
3
.
7
2
[
1
1
]
S
o
c
i
a
l
c
o
mm
u
n
i
c
a
t
i
o
n
d
e
t
e
c
t
i
o
n
N
e
t
w
o
r
k
f
l
o
w
-
b
a
se
d
R
e
c
a
l
l
:
2
.
6
P
r
e
c
i
s
i
o
n
:
80
F1
-
sc
o
r
e
:
8
.
8
[
1
4
]
D
e
c
i
s
i
o
n
t
r
e
e
N
e
t
w
o
r
k
f
l
o
w
-
b
a
se
d
A
c
c
u
r
a
c
y
:
93
F
a
l
se
p
o
si
t
i
v
e
r
a
t
e
:
30
F1
-
sc
o
r
e
:
9
.
0
[
9
]
P
e
r
i
o
d
i
c
i
t
y
i
n
n
e
t
w
o
r
k
f
l
o
w
P
e
r
i
o
d
i
c
i
t
y
i
n
p
c
a
p
d
a
t
a
F1
-
sc
o
r
e
:
9
[
1
3
]
P
a
t
t
e
r
n
-
b
a
se
d
n
e
t
w
o
r
k
f
l
o
w
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
S
t
a
t
i
st
i
c
a
l
n
e
t
w
o
r
k
f
l
o
w
-
b
a
se
d
A
c
c
u
r
a
c
y
:
9
9
.
3
6
P
r
e
c
i
s
i
o
n
:
9
8
.
9
8
R
e
c
a
l
l
:
9
8
.
4
7
F1
-
sc
o
r
e
:
9
8
.
7
2
3.
M
E
T
H
O
D
B
o
t
n
et
is
o
n
e
ty
p
e
o
f
m
alwa
r
e
th
at
o
f
te
n
b
ec
o
m
es
a
s
er
io
u
s
th
r
ea
t,
esp
ec
ially
f
o
r
lar
g
e
co
m
p
an
ies
an
d
g
o
v
er
n
m
en
t
a
g
en
cies.
T
h
is
m
alwa
r
e
in
f
ec
ts
an
d
c
o
n
tr
o
ls
a
n
u
m
b
er
o
f
d
ev
ices
co
n
n
e
cted
in
a
n
etwo
r
k
,
f
o
r
m
in
g
a
n
etwo
r
k
o
f
I
P
b
o
ts
th
at
ca
n
b
e
ex
p
lo
ited
b
y
attac
k
e
r
s
.
n
etwo
r
k
,
f
o
r
m
in
g
a
n
et
wo
r
k
o
f
I
P
b
o
ts
th
at
ca
n
b
e
ex
p
lo
ited
b
y
attac
k
er
s
with
o
u
t
th
e
k
n
o
wled
g
e
o
f
th
e
d
ev
ice
o
w
n
er
.
B
o
t
n
et
att
ac
k
s
ca
n
b
e
f
atal,
d
am
ag
in
g
n
etwo
r
k
in
f
r
astru
ct
u
r
e,
s
tealin
g
s
en
s
itiv
e
d
ata,
a
n
d
p
ar
al
y
zin
g
cr
itical
s
er
v
ice
s
.
Sev
er
al
p
r
ev
io
u
s
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
I
mp
r
o
vin
g
B
o
t
n
et
h
o
s
t p
r
ed
ict
io
n
w
ith
en
cryp
tio
n
a
n
d
GR
U
fo
r
en
h
a
n
ce
d
… (
Ome
g
a
Jo
el
P
a
tr
ia
Mo
a
ta
)
149
s
tu
d
ies
h
av
e
d
ev
elo
p
ed
p
r
ed
i
ctio
n
s
y
s
tem
s
to
d
etec
t
an
d
p
r
ev
en
t
B
o
t
n
et
attac
k
s
.
T
h
is
s
tu
d
y
f
o
c
u
s
es
o
n
d
ev
elo
p
in
g
s
u
c
h
a
p
r
e
d
ictio
n
s
y
s
tem
b
y
i
n
teg
r
atin
g
d
ata
s
ec
u
r
ity
tech
n
iq
u
es,
n
am
ely
en
cr
y
p
tio
n
.
DE
S
a
n
d
B
B
S
en
cr
y
p
tio
n
a
r
e
im
p
lem
e
n
ted
as
a
n
alter
n
ativ
e
to
p
r
o
te
ct
tex
t
d
ata
an
d
p
r
ev
en
t
p
u
b
li
c
d
ata
lea
k
s
,
wh
ich
ar
e
r
am
p
a
n
t
in
I
n
d
o
n
esia.
T
h
e
p
r
ed
ictio
n
s
y
s
tem
m
o
d
el
w
ith
en
cr
y
p
tio
n
was
d
ev
elo
p
e
d
b
y
f
o
llo
win
g
th
e
r
esear
ch
f
lo
w
illu
s
tr
ated
in
Fig
u
r
e
3
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
f
lo
w
ca
n
b
e
illu
s
tr
ated
in
Fig
u
r
e
8
.
Fig
u
r
e
8
.
Data
p
r
ep
r
o
ce
s
s
in
g
f
lo
w
3
.
1
.
Resea
rc
h
d
esig
n
T
h
e
d
ev
elo
p
ed
m
o
d
el
is
a
p
r
o
to
ty
p
e
o
f
a
n
in
f
o
r
m
ati
o
n
s
y
s
tem
im
p
lem
en
ted
u
s
in
g
Go
o
g
le
C
o
llab
o
r
ato
r
y
an
d
th
e
Py
th
o
n
p
r
o
g
r
am
m
in
g
lan
g
u
a
g
e.
T
h
e
u
s
e
o
f
th
e
T
esla
T
4
GPU
o
n
t
h
e
Go
o
g
le
C
o
llab
o
r
ato
r
y
p
la
tf
o
r
m
aim
s
to
ac
ce
ler
ate
d
ata
p
r
o
ce
s
s
in
g
,
esp
ec
ially
at
th
e
tr
ai
n
in
g
an
d
test
in
g
s
tag
es
o
f
m
o
d
els with
lar
g
e
d
atasets
.
T
h
is
allo
ws f
o
r
tim
e
ef
f
icien
cy
a
n
d
in
cr
ea
s
ed
s
y
s
tem
p
e
r
f
o
r
m
a
n
ce
.
3
.
2
.
Da
t
a
c
o
llect
io
n a
nd
prepa
ra
t
io
n
T
h
e
d
ata
co
llectio
n
p
r
o
ce
s
s
b
eg
i
n
s
b
y
tak
in
g
a
d
ataset
f
r
o
m
au
to
m
ate
d
-
m
alwa
r
e
-
a
n
aly
s
is
GitHu
b
,
s
p
ec
if
ically
th
e
cs4
4
8
b
_
ip
asn
d
ataset.
Af
ter
th
at,
d
ata
p
r
ep
r
o
ce
s
s
in
g
is
p
er
f
o
r
m
ed
to
cle
an
an
d
p
r
ep
a
r
e
th
e
d
ata
f
o
r
m
o
d
el
tr
ain
in
g
.
T
h
is
p
r
ep
r
o
ce
s
s
in
g
in
clu
d
es
h
a
n
d
li
n
g
o
u
tlier
s
,
d
ea
lin
g
with
m
is
s
in
g
v
alu
es,
ap
p
ly
i
n
g
av
er
ag
in
g
tech
n
iq
u
es,
an
d
en
cr
y
p
tio
n
.
Han
d
lin
g
o
u
t
lier
s
o
n
n
u
m
er
ic
d
ata
is
d
o
n
e
u
s
in
g
th
e
o
u
tlier
s
_
to
_
n
u
ll_
iq
r
(
f
ea
t
u
r
e)
f
u
n
ctio
n
,
wh
ich
p
r
o
ce
s
s
es
th
e
Data
Fra
m
e
(
s
er
ies)
co
lu
m
n
as
in
p
u
t.
T
h
e
f
i
r
s
t
s
tep
in
v
o
lv
es
ca
lcu
latin
g
th
e
f
ir
s
t
q
u
ar
tile
(
Q1
)
an
d
th
ir
d
q
u
a
r
tile
(
Q3
)
,
wh
er
e
Q1
r
ep
r
esen
ts
th
e
v
alu
e
th
at
s
ep
ar
ates
th
e
s
m
allest
2
5
%
o
f
th
e
d
ata,
wh
ile
Q3
s
ep
ar
ates
t
h
e
s
m
allest
7
5
%.
T
h
e
in
ter
q
u
a
r
tile
r
an
g
e
(
I
QR
)
is
th
en
ca
lcu
lated
as
th
e
d
if
f
er
en
ce
b
etwe
en
Q3
an
d
Q1
.
I
QR
is
u
s
ed
to
d
et
e
r
m
in
e
t
h
e
lo
wer
an
d
u
p
p
er
lim
its
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
2
,
J
u
ly
20
26
:
141
-
1
58
150
o
u
tlier
d
etec
tio
n
.
T
h
e
l
o
wer
li
m
it
is
d
eter
m
in
e
d
b
y
s
u
b
tr
ac
ti
n
g
1
.
5
tim
es
th
e
I
QR
f
r
o
m
Q
1
,
wh
ile
th
e
u
p
p
e
r
lim
it
is
ca
lcu
lated
b
y
ad
d
in
g
1
.
5
tim
es
th
e
I
QR
to
Q3
.
An
y
v
alu
e
th
at
f
alls
o
u
ts
id
e
th
ese
lim
its
is
co
n
s
id
er
ed
an
o
u
tlier
a
n
d
is
r
e
p
lace
d
wit
h
n
p
.
n
an
(
m
is
s
in
g
v
alu
e)
.
T
h
i
s
p
r
o
ce
s
s
is
ap
p
lied
iter
ativ
el
y
to
ea
ch
n
u
m
er
ic
co
lu
m
n
in
th
e
Data
Fra
m
e
u
s
in
g
a
lo
o
p
m
ec
h
an
is
m
.
T
h
e
o
u
tlier
s
_
to
_
n
u
ll_
iq
r
(
)
f
u
n
ctio
n
is
ex
ec
u
ted
f
o
r
ea
ch
n
u
m
er
ic
c
o
lu
m
n
,
with
th
e
r
esu
lts
s
to
r
ed
b
ac
k
i
n
to
th
e
co
r
r
esp
o
n
d
in
g
c
o
lu
m
n
in
th
e
Data
Fra
m
e.
T
h
e
o
u
tp
u
t
o
f
th
is
p
r
o
ce
s
s
is
p
r
esen
ted
in
T
a
b
le
3
.
T
ab
le
3
.
Sam
p
le
d
ata
I
n
d
e
x
D
a
t
e
I
_
i
p
n
r
_
a
s
n
f
y
d
a
y
w
d
a
y
0
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
0
4
3
6
7
0
4
.
0
1
0
6
.
0
1
8
2
5
1
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
1
1
8
2
1
9
4
.
0
6
4
0
.
0
1
8
2
5
2
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
2
2
1
2
9
6
6
.
0
1
6
7
7
.
0
1
8
2
5
3
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
3
9
6
3
7
6
.
0
2
2
.
0
1
8
2
5
4
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
4
1
2
0
5
0
7
.
0
1
8
4
.
0
1
8
2
5
5
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
5
1
2
5
6
4
7
.
0
4
4
.
0
1
8
2
5
6
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
6
1
1
7
2
2
7
.
0
6
3
.
0
1
8
2
5
7
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
7
4
7
9
5
2
4
.
0
4
1
1
.
0
1
8
2
5
8
2
0
0
6
-
07
-
0
1
0
:
0
0
:
0
0
8
3
3
9
6
0
9
.
0
4
4
8
.
0
1
8
2
5
T
h
e
in
itial
in
ter
p
r
etatio
n
o
f
e
ac
h
co
lu
m
n
in
th
e
d
ataset
is
as
f
o
llo
ws.
I
n
d
ex
r
ep
r
esen
ts
a
s
eq
u
en
ce
n
u
m
b
er
o
r
u
n
i
q
u
e
id
en
tifie
r
f
o
r
ea
ch
r
o
w
o
f
d
ata.
T
h
e
d
ate
c
o
lu
m
n
r
ec
o
r
d
s
th
e
d
ate
an
d
ti
m
e
wh
en
th
e
tr
af
f
ic
d
ata
was
co
llected
.
T
h
e
ip
n
f
ield
r
ef
er
s
to
th
e
"lo
ca
l
I
P
n
et
wo
r
k
"
o
r
"lo
ca
l
I
P
n
u
m
b
e
r
,
"
wh
ich
in
d
icate
s
th
e
lo
ca
l
I
P
ad
d
r
ess
o
r
n
etwo
r
k
.
T
h
e
r
asn
co
lu
m
n
s
tan
d
s
f
o
r
"r
e
m
o
te
au
to
n
o
m
o
u
s
s
y
s
tem
n
u
m
b
er
(
ASN
)"
,
wh
ich
id
en
tifie
s
th
e
n
etwo
r
k
f
r
o
m
w
h
ich
th
e
tr
af
f
ic
o
r
ig
in
ated
.
A
SN
r
ep
r
esen
ts
a
co
llectio
n
o
f
n
e
two
r
k
s
u
n
d
er
th
e
co
n
tr
o
l o
f
a
s
in
g
le
en
tity
,
u
s
u
a
lly
an
in
ter
n
et
s
er
v
ice
p
r
o
v
id
er
(
I
SP
)
.
T
h
e
F c
o
lu
m
n
s
h
o
ws th
e
n
u
m
b
e
r
o
f
f
lo
ws
o
r
p
ac
k
ets
in
th
e
n
etwo
r
k
tr
af
f
ic.
T
h
e
y
d
ay
f
ield
r
ep
r
esen
ts
th
e
d
ay
o
f
th
e
y
ea
r
(
e.
g
.
,
J
an
u
ar
y
1
=1
,
Dec
em
b
er
31=
3
6
5
o
r
3
6
6
in
l
ea
p
y
ea
r
s
)
,
wh
ile
th
e
wd
a
y
f
ield
i
n
d
icate
s
th
e
d
ay
o
f
t
h
e
wee
k
(
e.
g
.
,
Mo
n
d
ay
=1
,
Su
n
d
ay
=
7
)
.
Han
d
lin
g
m
is
s
in
g
v
alu
es
in
th
e
d
ataset
in
v
o
lv
e
s
d
eletin
g
th
e
af
f
ec
ted
r
o
ws
u
s
in
g
th
e
d
r
o
p
n
a(
)
f
u
n
ctio
n
with
t
h
e
in
p
lace
=
t
r
u
e
p
ar
am
eter
.
T
h
is
en
s
u
r
es
th
at
th
e
d
eletio
n
is
p
e
r
f
o
r
m
ed
d
ir
ec
tly
o
n
th
e
D
ataFr
am
e
with
o
u
t
cr
ea
tin
g
a
n
ew
co
p
y
.
Data
v
is
u
aliza
tio
n
was
th
en
p
er
f
o
r
m
e
d
to
an
aly
ze
th
e
tr
en
d
s
b
y
d
is
p
lay
in
g
ten
lin
e
g
r
ap
h
s
,
ea
ch
d
ep
ictin
g
th
e
n
u
m
b
er
o
f
f
l
o
ws
(
F)
f
r
o
m
ten
d
if
f
er
en
t
lo
c
al
I
P
ad
d
r
ess
es
(
ip
0
to
ip
9
)
o
v
er
tim
e
(
y
d
a
y
)
.
T
h
es
e
g
r
ap
h
s
wer
e
cr
ea
ted
u
s
in
g
m
atp
lo
tlib
.
p
y
p
l
o
t,
ar
r
an
g
i
n
g
th
e
f
ig
u
r
es a
n
d
ax
es in
f
iv
e
r
o
ws
an
d
two
c
o
lu
m
n
s
.
A
h
o
r
iz
o
n
tal
lin
e
was
ad
d
e
d
to
ea
ch
g
r
a
p
h
,
r
ep
r
esen
tin
g
th
e
m
ea
n
o
f
F
p
lu
s
th
r
ee
tim
es
its
s
tan
d
ar
d
d
ev
iatio
n
,
s
er
v
in
g
as
an
u
p
p
er
b
o
u
n
d
to
d
etec
t
p
o
ten
tial
an
o
m
alies
o
r
o
u
tlier
s
in
t
h
e
f
l
o
w
d
ata.
T
h
e
p
u
r
p
o
s
e
o
f
t
h
i
s
v
is
u
a
l
i
z
a
ti
o
n
w
as
t
o
o
b
s
e
r
v
e
t
r
e
n
d
s
a
n
d
p
at
t
e
r
n
s
i
n
t
h
e
n
u
m
b
e
r
o
f
f
l
o
w
s
f
r
o
m
e
a
ch
l
o
c
a
l
I
P
a
d
d
r
e
s
s
o
v
e
r
t
i
m
e
,
a
n
d
t
h
e
m
o
v
i
n
g
a
v
e
r
a
g
e
s
u
s
e
d
t
o
f
a
c
i
l
i
t
at
e
b
e
t
t
e
r
v
i
s
u
al
r
e
a
d
i
n
g
i
n
b
u
i
l
d
i
n
g
m
o
d
e
l
s
,
i
d
e
n
t
i
f
y
i
n
g
a
n
o
m
a
l
i
es
b
y
c
o
m
p
a
r
i
n
g
d
a
t
a
p
o
i
n
t
s
t
o
t
h
e
m
e
a
n
p
l
u
s
t
h
r
e
e
s
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
s
,
an
d
c
o
m
p
a
r
i
n
g
f
l
o
w
p
a
t
t
e
r
n
s
a
m
o
n
g
d
i
f
f
e
r
e
n
t
l
o
ca
l
I
P
a
d
d
r
e
s
s
e
s
.
T
h
e
r
es
u
lt
s
o
f
t
h
is
v
i
s
u
al
i
z
at
i
o
n
a
r
e
p
r
e
s
e
n
t
e
d
i
n
F
i
g
u
r
e
9
.
Fig
u
r
e
9
s
h
o
ws
a
g
r
ee
n
h
o
r
izo
n
tal
lin
e
o
n
ea
ch
i
p
g
r
ap
h
in
d
icatin
g
a
p
r
e
d
eter
m
in
ed
th
r
esh
o
ld
o
r
u
p
p
er
lim
it
in
d
icate
s
a
p
r
ed
eter
m
in
ed
th
r
esh
o
ld
o
r
u
p
p
e
r
lim
it.
Data
ab
o
v
e
th
is
lin
e
ca
n
b
e
co
n
s
id
er
ed
an
an
o
m
aly
o
r
o
u
tlier
.
I
f
s
ee
n
in
Fig
u
r
e
1
0
wh
ich
d
is
p
lay
s
a
co
m
p
ar
is
o
n
o
f
n
etwo
r
k
tr
af
f
ic
p
atter
n
s
b
etwe
en
two
lo
ca
l
I
P
ad
d
r
ess
es,
n
am
ely
L
o
ca
l
I
P
1
to
L
o
ca
l
I
P
9
.
tr
af
f
ic
p
atter
n
s
b
etwe
en
two
lo
ca
l
I
P
ad
d
r
ess
es,
in
Fig
u
r
e
1
0
t
h
e
X
-
ax
is
o
f
b
o
th
g
r
ap
h
s
s
h
o
ws
th
e
d
a
y
o
f
th
e
y
ea
r
(
y
d
ay
)
,
wh
ile
th
e
Y
-
ax
is
s
h
o
ws
th
e
n
u
m
b
e
r
o
f
f
lo
ws (
p
o
s
s
ib
ly
th
e
n
u
m
b
er
o
f
d
ata
p
ac
k
ets o
r
c
o
n
n
ec
tio
n
s
)
r
ec
o
r
d
ed
o
n
ea
c
h
I
P a
d
d
r
ess
.
I
n
ter
p
r
etatio
n
o
f
Fig
u
r
e
9
L
o
c
al
I
P
1
s
h
o
ws
a
r
elativ
ely
s
tab
le
tr
af
f
ic
p
atter
n
b
etwe
en
d
a
y
s
1
8
0
an
d
2
1
0
,
with
litt
le
f
lu
ctu
atio
n
.
s
t
ab
le
b
etwe
en
d
ay
s
1
8
0
an
d
2
1
0
,
with
li
ttle
f
lu
ctu
atio
n
.
T
h
er
e
is
a
s
ig
n
if
ican
t
s
p
ik
e
t
r
af
f
ic
s
p
ik
e
ar
o
u
n
d
d
a
y
2
2
0
,
f
o
llo
wed
b
y
a
s
h
ar
p
d
ec
lin
e
u
n
til
d
ay
2
4
0
.
L
o
ca
l
I
P
4
s
h
o
ws
a
m
o
r
e
u
n
s
tab
le
tr
af
f
ic
p
atter
n
with
m
an
y
s
p
ik
es
an
d
s
h
ar
p
d
ec
li
n
es
th
r
o
u
g
h
o
u
t
th
e
o
b
s
er
v
atio
n
p
er
io
d
.
T
h
er
e
a
r
e
s
ev
er
al
clea
r
ly
v
is
ib
le
tr
af
f
ic
s
p
ik
es,
esp
ec
ially
ar
o
u
n
d
y
d
a
y
2
0
0
,
2
2
5
,
a
n
d
2
7
0
.
C
o
m
p
a
r
is
o
n
o
f
th
ese
two
g
r
ap
h
s
s
h
o
ws
th
at
L
o
ca
l
I
P
4
h
as
m
o
r
e
v
o
latile
a
n
d
u
n
s
tab
l
e
tr
af
f
ic
t
h
an
L
o
ca
l
I
P
1
.
T
r
af
f
ic
s
p
ik
es
o
n
L
o
ca
l
I
P
4
ca
n
i
n
d
icate
u
n
u
s
u
al
ac
tiv
ity
,
wh
ich
ex
ce
ed
s
th
e
n
o
r
m
al
tr
af
f
ic
th
r
esh
o
l
d
s
u
ch
as
an
o
m
al
o
u
s
tr
af
f
ic
attac
k
s
o
r
B
o
t
n
et
ac
tiv
ity
,
o
r
s
ig
n
if
ican
t
ch
a
n
g
es
in
n
etwo
r
k
u
s
ag
e
b
y
a
p
p
ly
in
g
m
o
v
in
g
av
er
ag
e
tech
n
i
q
u
es
to
s
m
o
o
th
th
e
d
ata
an
d
v
is
u
alize
n
etwo
r
k
tr
af
f
ic
d
ata
tr
en
d
s
.
v
is
u
alize
n
etwo
r
k
tr
af
f
ic
d
ata
tr
en
d
s
.
wh
ich
is
u
s
ed
to
r
ed
u
ce
n
o
is
e
o
r
r
a
n
d
o
m
f
l
u
ctu
atio
n
s
in
d
ata,
s
o
th
at
th
e
g
en
er
al
tr
en
d
o
r
p
atter
n
o
f
th
e
d
ata
is
m
o
r
e
ea
s
i
ly
s
ee
n
.
th
e
g
e
n
er
al
p
atter
n
o
f
t
h
e
d
ata
is
m
o
r
e
ea
s
ily
s
ee
n
.
Dete
ctin
g
lo
n
g
-
te
r
m
tr
en
d
s
I
d
en
tify
in
g
s
ea
s
o
n
al
p
atter
n
s
an
d
m
a
k
in
g
it e
asier
t
o
p
r
ed
ict
f
u
tu
r
e
t
r
af
f
ic.
Evaluation Warning : The document was created with Spire.PDF for Python.