The document summarizes a keynote presentation by Ponnurangam Kumaraguru on privacy and security in online social media. Some key points:
- Kumaraguru is an associate professor who researches social computing, computational social science, and security/privacy in human behavior and complex networks.
- His presentation discusses research analyzing non-trustworthy content like fake news and rumors on social media. It describes building machine learning models to detect credibility of tweets about different events.
- The presentation also covers challenges like privacy concerns around sharing personal details on social networks and resolving identities across different online social networks.
Keynote at 4th International Symposium on Secuirty in Computing at Communications
1. Privacy
and
Security
in
Online
Social
Media
Keynote
@
SSCC’16
Sept
22,
2016
Ponnurangam
Kumaraguru
(“PK”)
Associate
Professor
ACM
Distinguished
Speaker
fb/ponnurangam.kumaraguru,
@ponguru
2. Who
am
I?
– Associate
Professor,
IIIT-‐Delhi
– Ph.D.
from
School
of
Computer
Science,
Carnegie
Mellon
University
(CMU)
– Research
interests
-Social
Computing,
Computational
Social
Science,
Complex
Networks
pertaining
to
Human
Behavior,
specifically
in
the
context
of
Security
&
Privacy
– Co-‐ordinate
and
manage
Precog,
precog.iiitd.edu.in
– ACM
Distinguished
Speaker
2
7. Training
Data
– 500
Tweets
per
event
– Used
CrowdFlower
7
Event Tweets Users
Boston
Marathon
Blasts
(2013) 7,888,374 3,677,531
Typhoon Haiyan /
Yolanda
(2013) 671,918 368,269
Cyclone
Phailin (2013) 76,136 34,776
Washington
Navy yard shootings (2013) 484,609 257,682
Polar
vortex cold wave (2014) 143,959 116,141
Oklahoma
Tornadoes (2013) 809,154 542,049
Total
10,074,150 4,996,448
8. Credibility
Modeling
8
Feature
set
Features (45)
Tweet
meta-‐data
Number
of
seconds
since
the
tweet;
Source
of
tweet
(mobile
/
web/
etc);
Tweet
contains
geo-‐coordinates
Tweet
content
(simple)
Number
of
characters;
Number
of
words;
Number
of
URLs;
Number
of
hashtags;
Number
of
unique
characters;
Presence
of
stock
symbol;
Presence
of
happy
smiley;
Presence
of
sad
smiley;
Tweet
contains
`via';
Presence
of
colon
symbol
Tweet
content
(linguistic)
Presence
of
swear
words;
Presence
of
negative
emotion
words;
Presence
of
positive
emotion
words;
Presence
of
pronouns;
Mention
of
self
words
in
tweet
(I;
my;
mine)
Tweet
author
Number
of
followers;
friends;
time
since
the
user
if
on
Twitter;
etc.
Tweet
network
Number
of
retweets;
Number
of
mentions;
Tweet
is
a
reply;
Tweet
is
a
retweet
Tweet links
WOT
score
for
the
URL;
Ratio
of
likes
/
dislikes
for
a
YouTube
video
15. Challenges
15
ProfessionalOpinion
Dating
Heterogeneous
OSNs
Personal
Degree
of
Details
Quality
and
descriptive
personal
And
professional
information
Little
personal
information
Descriptive
opinions
Attribute
Evolution
Time
Information
evolved
on
one
but
not
on
other
{jainpari,
Bangalore}
Registration
with
same
information
on
both
OSNs
{paridhij,
New
Delhi}
17. Heuristic
Identity
Search
17
cerc.iiitd.ac.in
Profile
Content
Self-mention
Network
Syntactic
and Image
Search Linking
If self-identified /
returned by
more than one
search method
No
Yes
Candidate
Identities
name,
location,
username
mobile no,
post,
friends,
followers
Paridhi
Jain,
Ponnurangam Kumaraguru,
and
Anupam Joshi.
2013.
@I
seek
‘fb.me’:
Identifying
Users
across
Multiple
Online
Social
Networks.
In
Proceedings
of
the
22nd
International
Conference
on
World
Wide
Web,
WWW
’13
Companion.
ACM,
New
York,
NY,
USA,
1259-‐ 1268.
DOI=http://dx.doi.org/10.1145/2487788.2488160
[Honorable
Mention
Award}
20. 20
How
many
of
you
have
posted
mobile
numbers
on
Online
Social
Networks?
How
many
of
you
have
seen
mobile
numbers
being
posted
on
Online
Social
Networks?
30. Demographics
Gender
(N=
10,232)
Male 67.57
Female 32.43
30
Age
(N=10,350)
<18 1.54
18-‐24 21.31
25-‐29 32.20
30-‐39 25.90
40-‐49 14.09
50-‐64 4.46
65+ 0.50
Age
31. Internet
&
Social
Media
What
do
you
feel
about
privacy
of
your
personal
information
on
your
OSN?
31
Q42,
N
=
6,855
It
is
not
a
concern
at
all
Since
I
have
specified
my
privacy
settings,
my
data
is
secure
from
a
privacy
breach
Even
though,
I
have
specified
my
privacy
settings,
I
am
concerned
about
privacy
of
my
data
It
is
a
concern,
but
I
still
share
personal
information
It
is
a
concern;
hence
I
do
not
share
personal
data
on
OSN
32. Internet
&
Social
Media
What
do
you
feel
about
privacy
of
your
personal
information
on
your
OSN?
32
Q42,
N
=
6,855
It
is
not
a
concern
at
all
Since
I
have
specified
my
privacy
settings,
my
data
is
secure
from
a
privacy
breach
42.13
Even
though,
I
have
specified
my
privacy
settings,
I
am
concerned
about
privacy
of
my
data
It
is
a
concern,
but
I
still
share
personal
information
It
is
a
concern;
hence
I
do
not
share
personal
data
on
OSN
33. Internet
&
Social
Media
What
do
you
feel
about
privacy
of
your
personal
information
on
your
OSN?
33
Q42,
N
=
6,855
It
is
not
a
concern
at
all
19.30
Since
I
have
specified
my
privacy
settings,
my
data
is
secure
from
a
privacy
breach
42.13
Even
though,
I
have
specified
my
privacy
settings,
I
am
concerned
about
privacy
of
my
data
23.84
It
is
a
concern,
but
I
still
share
personal
information
8.02
It
is
a
concern;
hence
I
do
not
share
personal
data
on
OSN
6.71
34. Internet
&
Social
Media
If
you
receive
a
friendship
request
on
your
most
frequently
used
OSN,
which
of
the
following
people
will
you
add
as
friends?
34
Q43,
N
=
6,929
Person
of
opposite
gender
People
from
my
hometown
Person
with
nice
profile
picture
Strangers
(people
you
do
not
know)
Somebody,
whom
you
do
not
know
or
recognize
but
have
mutual
/
common
friends
with
Anyone
35. Internet
&
Social
Media
If
you
receive
a
friendship
request
on
your
most
frequently
used
OSN,
which
of
the
following
people
will
you
add
as
friends?
35
Q43,
N
=
6,929
Person
of
opposite
gender
People
from
my
hometown
Person
with
nice
profile
picture 10.12
Strangers
(people
you
do
not
know)
Somebody,
whom
you
do
not
know
or
recognize
but
have
mutual
/
common
friends
with
Anyone
36. Internet
&
Social
Media
If
you
receive
a
friendship
request
on
your
most
frequently
used
OSN,
which
of
the
following
people
will
you
add
as
friends?
36
Q43,
N
=
6,929
Person
of
opposite
gender 27.39
People
from
my
hometown
Person
with
nice
profile
picture 10.12
Strangers
(people
you
do
not
know)
Somebody,
whom
you
do
not
know
or
recognize
but
have
mutual
/
common
friends
with
Anyone 2.99
37. Internet
&
Social
Media
If
you
receive
a
friendship
request
on
your
most
frequently
used
OSN,
which
of
the
following
people
will
you
add
as
friends?
37
Q43,
N
=
6,929
Person
of
opposite
gender 27.39
People
from
my
hometown 19.51
Person
with
nice
profile
picture 10.12
Strangers
(people
you
do
not
know) 4.99
Somebody,
whom
you
do
not
know
or
recognize
but
have
mutual
/
common
friends
with 8.31
Anyone 2.99
39. Takeaways
– Online
Social
Media
is
a
different
beast
in
terms
of
privacy,
identity,
and
credibility
-Research
/
technologies
should
be
developed
– Multiple
interesting
research,
engineering,
and
innovation
waiting
to
be
done
– Interested
in
hosting
students
– B.Tech.,
M.Tech.,
Ph.D.
39