QuickSquad: A new single-machine graph computing framework for detecting fake accounts in large-scale social networks

Xinyang Jiang, Qiang Li, Zhen Ma, Mianxiong Dong, Jun Wu, Dong Guo*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Graph-based approaches for fake account detection is one of the important means to fight against fake accounts’ attacks on social networks. With the growth of the scale of social networks, more and more researchers begin to use the graph computing framework to boost their detection algorithms. We make detailed analyses of social networks’ graph data and state-of-the-art graph computing frameworks, and find that some techniques of the current graph computing systems are overgeneralized and suboptimal, which means they only focus on how to design a graph processing framework on general graphs but miss the optimization of social networks graphs. So, in this paper we propose QuickSquad, a graph computing system on a single server which is specific to the optimization of social networks graph structures. QuickSquad uses the method of ”divide and rule” instead of overgeneralization. First, we divide the graph structure data into the heavy set and the light set according to the out-degree of vertices. Then, we 1) store them with different formats, 2) process them with edge-based updating and vertex-based updating appropriately in a two-phase processing model, 3) apply two selective scheduler strategies of different level, i.e. vertex-level and file-level, and 4) provide four cache priorities when the memory is not enough to cache all data. Finally, we implement two detection methods, dSybilRank and dCOLOR, on our system, and the experiments demonstrate that our system can increase the performance up to 5.91X (from 1.14X) compared with the performance of the current graph computing systems, like GridGraph.

Original languageEnglish
Pages (from-to)1385-1402
Number of pages18
JournalPeer-to-Peer Networking and Applications
Volume12
Issue number5
DOIs
Publication statusPublished - 2019 Sep 13
Externally publishedYes

Keywords

  • Distributed system
  • Fake accounts
  • Graph computing
  • Security of online social networks
  • Sybil detection

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'QuickSquad: A new single-machine graph computing framework for detecting fake accounts in large-scale social networks'. Together they form a unique fingerprint.

Cite this