VoteTrustLeveraging Friend Invitation Graph to Defend
Social Network Sybils
Jilong Xue , Zhi Yang , Xiaoyong Yang, Xiao Wang, Lijiang Chen and Yafei Dai
Computer Science Department, Peking University
Sybil attack in Social networks
Non-popular users
Sybils
Friend invitation
reject
accept
VoteTrust: An Overview
• Basic idea:– Considering invitation feedback as voting
• Key techniques:– Trust-based votes assignment– Global vote aggregation
• Properties:– High precision in Sybil detection– Efficient in limiting Sybil’s attack ability
Graph Model
A
B
C
A
B
C
Link initiation graph Link acceptance graph
1
0
Framework of VoteTrust
• Select trust seed – high reliable users• Distribute votes• Collect votes and computing score
Outline
PreliminaryImplementation
– Trust-based vote assignment– Global vote aggregation
EvaluationConclusion
Votes Assignment
• Problem: – How to distribute votes
across users?
• Principle:– Reliable user should get
more votes
• How to implement?
vvvvvReliable user
Non-popular user Sybil
Trust-based Votes Assignment
• Step1: Assigning votes to little human-selected reliable seeds
• Step2: Propagating to whole users across the Link initiation graph
𝒗𝒐𝒕𝒆(𝑢)=𝑑 ∙ ∑𝑣: (𝑣 ,𝑢)∈𝐸 𝐼
❑ 𝒗𝒐𝒕𝒆(𝑣)𝑜𝑢𝑡𝑑𝑒𝑔𝑟𝑒𝑒(𝑣)
+(1 −𝑑 ) ∙ 𝒊𝒏𝒊𝒕 (𝑢)
Example
A B
DC E
Node A is reliable seed Total votes =5
A B C D E
5 0 0 0 0
0.75 4.25 0 0 0
0.75 0.65 0 1.80 1.80
2.59 0.94 0.31 0.58 0.58
1.69 1.57 0.14 0.80 0.80
…t=0
t=1
t=2
t=3
t=n
Outline
PreliminaryImplementation
– Trust-based vote assignment– Global vote aggregation
EvaluationConclusion
Vote Aggregating
• Problem:– How to collect votes and
compute user trust score?– Trust score
• Principle:– Trust user should have
high weight in voting.
A B
C
0 1
vote=1,score=0.2 vote=1,score=0.9
score=?
Global Vote Aggregation
• Step1: Set all users’ initial score as 0.5;• Step2: Iteratively computing each user’s trust
score according to aggregated votes.
𝒔𝒄𝒐𝒓𝒆 (𝑢)=∑ 𝑣𝑜𝑡𝑒 (𝑣 ) ∙𝒔𝒄𝒐𝒓𝒆 (𝑣 ) ∙𝑥𝑣 ,𝑢
∑ 𝑣𝑜𝑡𝑒 (𝑣 ) ∙ 𝒔𝒄𝒐𝒓𝒆 (𝑣 ),(𝑣 ,𝑢)∈𝐸𝐸
Small-sample Problem
• Number of votes is too small.
• Wilson score
– weighted average of and .
A B
vote=1,score=0.2
0 score=0 ?
A B
vote=1,score=0.2
1 score=1 ?𝒑=�̂�+
12𝑁
𝑧1 −𝛼/2❑
1+ 1𝑁
𝑧1 −𝛼/2❑
score=0.40
score=0.61
Security Properties (I)
• Theorem 1: The number of Sybil’s attack-link needs to satisfy the following upper bound
where is detection threshold.
𝑵𝒐𝒖𝒕 ≤𝜌𝑵 𝒊𝒏 ∙𝛿 𝑓 −𝛿 𝑓
2
𝛿 𝑓 −𝑟
𝑁 𝑖𝑛
𝑁 𝑜𝑢𝑡
Normal user Sybil
Simulation of Theorem 1
• Comm size: 100• # of in-links: 10
• Nout avg: 2.36• Nout max:4
Security Properties (II)
• Theorem 2: Sybil community size need to satisfy the upper bound ,
where is vote collection threshold.
𝑵 𝒔≤𝜎 ∙𝑵 𝒊𝒏
𝛿𝑣
Simulation of Theorem 2
Outline
PreliminaryImplementation
– Trust-based vote assignment– Global vote aggregation
EvaluationConclusion
Experimental Setup
• Data Set– Renren regional network (PKU) include 200K
users, 5.01 million friend invitations– 2502 Sybil accounts detected by Renren– Manual checking 73 Sybils from 500 random user
• Methodology– Compared with TrustRank and BadRank– Evaluation metrics: Precision and Recall
TrustRank vs. VoteTrust
Averagely improve 32.9% Averagely improve 75.6%
BadRank vs. VoteTrust
Averagely improve 44.5% Averagely improve 41.6%
Separating Normal User from Sybils
80% with low score
Separating Normal User from Sybils
Maximum accuracy=85.7%
Performance Summary
Outperforms TrustRank by 32.9% in detection precision averagely;
Outperforms BadRank by 44.5% in detection precision averagely;
High accurate in classifying the Sybil and normal user (include non-popular user)
Outline
PreliminaryImplementation
– Trust-based vote assignment– Global vote aggregation
EvaluationConclusion
Conclusion
• VoteTrust is a rating system– high accuracy in Sybil detection– Efficient in resisting Sybil (community)
• Key techniques– Trust-based vote assignment– Global vote aggregation
Thank you!