wherefore art thou r3579x? anonymized social networks, hidden patterns, and structural stenography

25
Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Upload: jean-ross

Post on 12-Jan-2016

216 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Page 2: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

A social network occurs anywhere there is social interaction between people.

Examples include Email, instant messaging, Facebook, blogging trackbacks, coauthor networks

Page 3: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography
Page 4: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

The structure of social networks can be interesting

How are friendships usually structured? Are there hubs, such as Heather, who connect separate networks? How many degrees of Kevin Bacon?

We can investigate these questions if we have the data to mine.

Page 5: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

For our examples, we will use a network of emails sent between users.

How do we protect users’ privacy while still releasing the data for research?

John Mary

Vertex

Vertex

Directed edge

Page 6: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Remove any identifiable information, such as name and other attributes.

Randomly rename the vertices

R3579X R73313

Page 7: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Convert directed edges to undirected edges. This increases the complexity and makes it harder to attack.

R3579X R73313

Undirected edge

Page 8: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Let’s say you want to know if two vertices are connected onthe graph.

All the identifying info has beenremoved, so how do we do it?

Page 9: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

An active attack involves the adversary creating vertices in the graph before the graph is released

The adversary will create edges between the vertices in a fashion that it can then recognize later on in when the graph is released

Page 10: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

We create k new vertices around 2*(log n) where n is the total number of vertices

We create new do – d1 edges between these new vertices and the other ones in the graph

Then, we randomly create edges between these new nodes with independent probability of 1/2

Page 11: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Given the graph, how do we find the subgraph that we created?

Create a search tree, pruning the tree based on the properties of our subgraph, such as the number of degrees of our new vertices

Page 12: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Tom

John

Mary

Mike

Zoe

Page 13: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Tom

John

Mary

k5 k1

k2k4

k3

Mike

Zoe

Page 14: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Tom

John

Mary

k5 k1

k2k4

k3

Mike

Zoe

Page 15: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Tom

John

Mary

k5 k1

k2k4

k3

Mike

Zoe

Page 16: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

JKL

ZXCV

QWER

DFGWER

UYTASD

HGF

ASDF

BNM

Page 17: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

JKL

ZXCV

QWER

k5 k1

k2k4

k3

ASDF

BNM

Page 18: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

JKL

John

Mary

k5 k1

k2k4

k3

ASDF

BNM

Page 19: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

The paper proves that the search tree does not grow too large and that the algorithm displays good performance

Also, it proves that the subgraph is unique so that we don’t identify the wrong subgraph

Page 20: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

They simulate an attack on LiveJournal friendship links. They create the accounts on the website, make the connections, and then crawl the site and anonymize the data

The network has 4.4 million nodes and 77 million edges

Page 21: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography
Page 22: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

Only needs sqrt(log(n)) new nodes to attack the graph

However, it’s much more computationally intensive and less practical in the real world, although it takes less nodes

Page 23: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography
Page 24: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

It’s a lot like an active attack, except you don’t create new nodes, instead you collaborate with your friends and find yourselves in the graph

However, because you did not specifically target certain people, you may not be able to identify other people when you find yourself

Page 25: Wherefore Art Thou R3579X? Anonymized Social Networks, Hidden Patterns, and Structural Stenography

We cannot rely on anonymization to ensure privacy in social networks

Possible improvements: add noise to the data by adding/removing random edges