CCNC

A Collusion-Resistant Automation
Scheme for Social Moderation Systems
        Jing-Kai Lou12, Kuan-Ta Chen1, Chin-La...
The Rise of User-Generated Content
• eMarketer projects that the number of US
  UGC creators will rise to 108 million in 2...
Inappropriate UGC
• While most UGC creators behave responsibly, a minority of
  creators may upload inappropriate content,...
Social Moderation System
                                                                            X

   • A user-assist...
Is Social Moderation good enough?
• Advantages of social moderation system:
      1. Fewer official moderators
      2. De...
Social Moderation Automation
• This is our motivation for proposing social
  moderation automation, which automatically
  ...
There is an intuitive way…
• Count-based Scheme identifies misbehaving users by
  considering the number of accusations (r...
However, there are many colluders…
 2009/1/12   CCNC 2009 / Jing‐Kai Lou   8
Not All Users Are Trustable
• While most users report responsibly, colluders
  report fake results to gain some benefits.
...
Research Question

• CAN we automatically infers which
  accusations (reports) are fair or malicious?

• Need a better aut...
Our Scheme
• Community-based scheme analyzes the
  accusation relations between the accusing
  users and accused users.

•...
Our Contributions
• The evaluation results show that our scheme
      – Achieves accuracy rate higher than 90%

      – Pr...
Accusation Relation
• Accusation Relation(R): a subset of A x A,
  A := {reporters, UGC creators}
• E.g. 5 users in this s...
Accusing Graph
• Input for our community-based scheme
• Accusing Graph(G):
      – An undirected bipartite graph G(A+B, E)...
Meanings of Nodes

                                                           V

                            C
           ...
Accusing Community
• Adopting Girvan-Newman Algorithm to detect the communities
  and the inter-community edges




      ...
Inter-community edge
• Property 1:
    It is unlikely that an inter-community edge is an accusing edge
    between a collu...
Features for each User
• inter-community edges    fair accusations
• Base on the inter-community edges, we design
  featur...
Clustering (IA, OA) pairs
                                                                                                ...
Algorithm
1. Partitioning accusing graph into communities.

2. Computing the feature pair (IA, OA) of each user

3. Cluste...
Simulation Setup
• We use simulations to evaluate the performance of
  our scheme in detecting real misbehaving users in a...
Evaluation Metric
• What we care is, False Negative
      – Misidentifying victims as misbehaving users


• Collusion Resi...
Effect of #(Misbehaving users)
                       Our method
  Count-based method




2009/1/12                       ...
Conclusion
• We propose a community-based scheme based on the
  community structure of an accusing graph.

• The results s...
Thank you for your listening



            Q&A
Upcoming SlideShare
Loading in …5
×

A Collusion-Resistant Automation Scheme for Social Moderation Systems

741 views

Published on

For current Web 2.0 services, manual examination of user uploaded content is normally required to ensure its legitimacy and appropriateness, which is a substantial burden to service providers. To reduce labor costs and the delays caused by content censoring, social moderation has been proposed as a front-line mechanism, whereby user moderators are encouraged to examine content before system moderation is required. Given the immerse amount of new content added to the Web each day, there is a need for automation schemes to facilitate rear system moderation. This kind of mechanism is expected to automatically summarize reports from user moderators and ban misbehaving users or remove inappropriate content whenever possible. However, the accuracy of such schemes may be reduced by collusion attacks, where some work together to mislead the automatic summarization in order to obtain shared benefits.

In this paper, we propose a collusion-resistant automation scheme for social moderation systems. Because some user moderators may collude and dishonestly claim that a user misbehaves, our scheme detects whether an accusation from a user moderator is fair or malicious based on the structure of mutual accusations of all users in the system. Through simulations we show that collusion attacks are likely to succeed if an intuitive countbased automation scheme is used. The proposed scheme, which is based on the community structure of the user accusation graph, achieves a decent performance in most scenarios.

Published in: Technology, Business
  • Be the first to comment

  • Be the first to like this

A Collusion-Resistant Automation Scheme for Social Moderation Systems

  1. 1. CCNC A Collusion-Resistant Automation Scheme for Social Moderation Systems Jing-Kai Lou12, Kuan-Ta Chen1, Chin-Laung Lei2 Institute of Information Science, Academia Sinica1 Department of Electrical Engineering, National Taiwan University2
  2. 2. The Rise of User-Generated Content • eMarketer projects that the number of US UGC creators will rise to 108 million in 2012, from 77 million in 2007. 2009/1/12 CCNC 2009 / Jing‐Kai Lou 2
  3. 3. Inappropriate UGC • While most UGC creators behave responsibly, a minority of creators may upload inappropriate content, such like • pictures that violate copyright laws • splatter movies • … • Content censorship is essential for Web 2.0 services • One Solution: • hiring lots of official moderators • But, such high labor cost is a great burden to the service provider • Another Solution: Social moderation has been proposed to solve the content censorship problem 2009/1/12 CCNC 2009 / Jing‐Kai Lou 3
  4. 4. Social Moderation System X • A user-assist moderation O X X • Every user is a reviewer! ? ?? !? Official moderators  inspect and evaluate  You report/accuse  what your report while browsing Blogger Album Video 2009/1/12 CCNC 2009 / Jing‐Kai Lou 4
  5. 5. Is Social Moderation good enough? • Advantages of social moderation system: 1. Fewer official moderators 2. Detecting inappropriate content quickly • BUT, the number of the reports is still large. • Even 1% uploading photos in Flickr are problematic, there are about 43,200 reports each day. • Can we help? 2009/1/12 CCNC 2009 / Jing‐Kai Lou 5
  6. 6. Social Moderation Automation • This is our motivation for proposing social moderation automation, which automatically summarizes the reports submitted by users. • A preprocess: For eliminating manual inspection by official moderators as much as possible. 2009/1/12 CCNC 2009 / Jing‐Kai Lou 6
  7. 7. There is an intuitive way… • Count-based Scheme identifies misbehaving users by considering the number of accusations (reports). 37 3 47 These photos are accused no These photos are accused more than (N =20) users more than (N =20) users 2009/1/12 CCNC 2009 / Jing‐Kai Lou 7
  8. 8. However, there are many colluders… 2009/1/12 CCNC 2009 / Jing‐Kai Lou 8
  9. 9. Not All Users Are Trustable • While most users report responsibly, colluders report fake results to gain some benefits. • Counted-based scheme may misidentify! 2009/1/12 CCNC 2009 / Jing‐Kai Lou 9
  10. 10. Research Question • CAN we automatically infers which accusations (reports) are fair or malicious? • Need a better automation scheme to deal with collusion attacks 2009/1/12 CCNC 2009 / Jing‐Kai Lou 10
  11. 11. Our Scheme • Community-based scheme analyzes the accusation relations between the accusing users and accused users. • Based on the derived information, the scheme infers whether the accusations are fair or malicious; that is, it distinguishes users that genuinely misbehave from victims of collusion attacks. 2009/1/12 CCNC 2009 / Jing‐Kai Lou 11
  12. 12. Our Contributions • The evaluation results show that our scheme – Achieves accuracy rate higher than 90% – Prevents at least 90% victims from collusion attacks 2009/1/12 CCNC 2009 / Jing‐Kai Lou 12
  13. 13. Accusation Relation • Accusation Relation(R): a subset of A x A, A := {reporters, UGC creators} • E.g. 5 users in this system, namely U1, U2, U3, U4, U5 • Accusation Relation Matrix(M): User 1 2 3 4 5 – U1 accuses (reports) U2 1 0 1 0 0 0 – U2 accuses U4 2 0 0 0 1 0 – U3 accuses U2 & U5 – U4 accuses none 3 0 1 0 0 1 – U5 accuses U2 4 0 0 0 0 0 5 0 1 0 0 0 2009/1/12 CCNC 2009 / Jing‐Kai Lou 13
  14. 14. Accusing Graph • Input for our community-based scheme • Accusing Graph(G): – An undirected bipartite graph G(A+B, E) – A: {accusing identity of users} – B: {accused identity of users} User 1 2 3 4 5 1 0 1 0 0 0 2 0 0 0 1 0 3 0 1 0 0 1 4 0 0 0 0 0 5 0 1 0 0 0 2009/1/12 CCNC 2009 / Jing‐Kai Lou 14
  15. 15. Meanings of Nodes V C L Identity of accused user Identity of accusing user • Colluders O • Victim • Careless accuser • Unfortunate user • Honest accuser M • Misbehaving user • User doesn’t accuse • Low-abiding user H L M 2009/1/12 CCNC 2009 / Jing‐Kai Lou 15
  16. 16. Accusing Community • Adopting Girvan-Newman Algorithm to detect the communities and the inter-community edges ge y ed it m un om er -c Int 2009/1/12 CCNC 2009 / Jing‐Kai Lou 16
  17. 17. Inter-community edge • Property 1: It is unlikely that an inter-community edge is an accusing edge between a colluder and a victim. • Property 2: It is unlikely that an inter-community edge is an accusing edge between a careless accuser and an unfortunate user. • Property 3: An inter-community edge most likely is an accusing edge between an honest accuser and a misbehaving user. 2009/1/12 CCNC 2009 / Jing‐Kai Lou 17
  18. 18. Features for each User • inter-community edges fair accusations • Base on the inter-community edges, we design features for nodes – Incoming Accusation, IA(k) = 2, – Outgoing Accusation, OA(k) = 5 a k b c W = {a, b, c} 2009/1/12 CCNC 2009 / Jing‐Kai Lou 18
  19. 19. Clustering (IA, OA) pairs Picked Outgoing Accusation Unpicked Incoming Accusation Unpicked unfortunat users Picked Unfortunate users Unpicked misbehaving users Picked misbehaving users Unpicked victims Picked victims 2009/1/12 CCNC 2009 / Jing‐Kai Lou 19
  20. 20. Algorithm 1. Partitioning accusing graph into communities. 2. Computing the feature pair (IA, OA) of each user 3. Clustering based on their (IA, OA) pairs, and label users in the cluster with larger (IA, OA) as misbehaving users. 2009/1/12 CCNC 2009 / Jing‐Kai Lou 20
  21. 21. Simulation Setup • We use simulations to evaluate the performance of our scheme in detecting real misbehaving users in a social moderation system. • Simulation Assumption: 1. A honest user should only accuses users that definitely misbehave. 2. A colluder accuses victims. 3. All users including colluders have a probability of making an accusation by mistake. 2009/1/12 CCNC 2009 / Jing‐Kai Lou 21
  22. 22. Evaluation Metric • What we care is, False Negative – Misidentifying victims as misbehaving users • Collusion Resistance 2009/1/12 CCNC 2009 / Jing‐Kai Lou 22
  23. 23. Effect of #(Misbehaving users) Our method Count-based method 2009/1/12 CCNC 2009 / Jing‐Kai Lou 23
  24. 24. Conclusion • We propose a community-based scheme based on the community structure of an accusing graph. • The results show that the collusion resistance of our scheme is around 90%. • We believe that collusion-resistant schemes will play an important role in the design of social moderation systems for Web 2.0 services 2009/1/12 CCNC 2009 / Jing‐Kai Lou 24
  25. 25. Thank you for your listening Q&A

×