+ Collective Spammer Detection in Evolving Multi-Relational Social - PowerPoint PPT Presentation

+ Collective Spammer Detection in Evolving Multi-Relational Social Networks Shobeir Fakhraei (University of Maryland) James Foulds (University of California, Santa Cruz) Madhusudana Shashanka (if(we) Inc., Currently Niara Inc.) Lise Getoor (University of California, Santa Cruz)

2 Spam in Social Networks n Recent study by Nexgate in 2013: n Spam grew by more than 300% in half a year

3 Spam in Social Networks n Recent study by Nexgate in 2013: n Spam grew by more than 300% in half a year n 1 in 200 social messages are spam

4 Spam in Social Networks n Recent study by Nexgate in 2013: n Spam grew by more than 300% in half a year n 1 in 200 social messages are spam n 5% of all social apps are spammy

5 Spam in Social Networks n What’s different about social networks? n Spammers have more ways to interact with users

6 Spam in Social Networks n What’s different about social networks? n Spammers have more ways to interact with users n Messages, comments on photos, winks,…

7 Spam in Social Networks n What’s different about social networks? n Spammers have more ways to interact with users n Messages, comments on photos, winks,… n They can split spam across multiple messages

8 Spam in Social Networks n What’s different about social networks? n Spammers have more ways to interact with users n Messages, comments on photos, winks,… n They can split spam across multiple messages n More available info about users on their profiles!

9 Spammers are getting smarter! Traditional Spam: Want some replica luxury watches? Click here: http://SpammyLink.com George Shobeir

10 Spammers are getting smarter! Traditional Spam: Want some replica luxury watches? Click here: http://SpammyLink.com George � [Report Spam] Shobeir

11 Spammers are getting smarter! Traditional Spam: (Intelligent) Social Spam: Want some replica luxury Hey Shobeir! watches? Nice profile photo. I live Click here: in Bay Area too. Wanna http://SpammyLink.com chat? George Mary � [Report Spam] Shobeir Shobeir

12 Spammers are getting smarter! Traditional Spam: (Intelligent) Social Spam: Want some replica luxury Hey Shobeir! watches? Nice profile photo. I live Click here: in Bay Area too. Wanna http://SpammyLink.com chat? George Mary � [Report Spam] Sure! :) Shobeir Shobeir

13 Spammers are getting smarter! Traditional Spam: (Intelligent) Social Spam: Want some replica luxury Hey Shobeir! watches? Nice profile photo. I live Click here: in Bay Area too. Wanna http://SpammyLink.com chat? George Mary � [Report Spam] Sure! :) Shobeir Shobeir … Realistic Looking Conversation I’m logging off here., too many people pinging me! I really like you, let’s chat more here: http://SpammyLink.com Mary

14 Tagged.com n Founded in 2004, is a social networking site which connects people through social interactions and games n Over 300 million registered members n Data sample for experiments (on a laptop): n 5.6 Million users (3.9% Labeled Spammers) n 912 Million Links

15 Social Networks: Multi-relational and Time-Evolving ) ( 1 t t(2) t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t

16 Social Networks: Multi-relational and Time-Evolving Legitimate users ) ( 1 t t(2) t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t

17 Social Networks: Multi-relational and Time-Evolving Legitimate users ) ( 1 t t(2) Spammers t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t

18 Social Networks: Multi-relational and Time-Evolving Legitimate users ) ( 1 t t(2) Spammers t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t Link = Action at time t Actions = Profile view , message , poke , report abuse , etc

19 Social Networks: Multi-relational and Time-Evolving ) ( 1 t t(2) t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t Link = Action at time t Actions = Profile view , message , poke , report abuse , etc

20 Social Networks: Multi-relational and Time-Evolving Profile view ) ( 1 t t(2) t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t Link = Action at time t Actions = Profile view , message , poke , report abuse , etc

21 Social Networks: Multi-relational and Time-Evolving Message Profile view ) ( 1 t t(2) t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t Link = Action at time t Actions = Profile view , message , poke , report abuse , etc

22 Social Networks: Multi-relational and Time-Evolving Message Profile view ) ( 1 t t(2) t(5) t(10) t(6) t(4) t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t Poke Link = Action at time t Actions = Profile view , message , poke , report abuse , etc

23 Social Networks: Multi-relational and Time-Evolving Message Profile view ) ( 1 t t(2) t(5) t(10) t(6) Report t(4) spammer t ( t ( 8 7 ) ) t(3) t ( 1 1 ) ) 9 ( t Poke Link = Action at time t Actions = Profile view , message , poke , report abuse , etc

24 Our Approach Predict spammers based on: n Graph structure n Action sequences ) 1 t ( t ( 2 ) n Reporting behavior t(5) t(10) t(6) t ( 4 ) t(7) t(8) ) 3 t ( ( 1 t 1 ) t(9)

25 Our Approach Predict spammers based on: n Graph structure n Action sequences ) 1 t ( t ( 2 ) n Reporting behavior t(5) t(10) t(6) t ( 4 ) t(7) t(8) ) 3 t ( ( 1 t 1 ) t(9)

26 Graph Structure Feature Extraction Are you interested? Pagerank, 
 K-core, 
 Meet Me Play Pets Friend Request Message Wink Report Abuse Graph coloring, 
 Triangle count, Connected components, In/out degree Graphs for each relation

27 Graph Structure Feature Extraction Features Are you interested? Pagerank, 
 K-core, 
 Meet Me Play Pets Friend Request Message Wink Report Abuse Graph coloring, 
 Triangle count, Connected components, In/out degree Graphs for each relation

28 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

29 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

30 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

31 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

32 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

33 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

34 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

35 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Degree statistics n Total degree n In degree n Out degree X n k-Core n Graph coloring n Connected components n Triangle count (8 features for each of 10 relations)

36 Graph Structure Features n Extract features for each relation graph es for each of 10 rel n PageRank n Viewing profile n Friend requests n Degree statistics n Message n Total degree n Luv n In degree n Out degree n Wink X n Pets game n k-Core n Buying n Wishing n Graph coloring n MeetMe game n Connected components n Yes n No n Triangle count n Reporting abuse (8 features for each of 10 relations)

Graph Structure Features t ( 1 ) t ( 9 ) Classification method: Gradient Boosted Trees t(10) Graph Structure Viewing profile PageRank Triangle Count Out-Degree In-Degree k-Core Graph Coloring … … … Reporting abuse PageRank Triangle Count Out-Degree In-Degree k-Core Graph Coloring 37