Toward worm detection in online social networks wei xu fangfang zhang and sencun zhu
This presentation is the property of its rightful owner.
Sponsored Links
1 / 1

Toward Worm Detection in Online Social Networks Wei Xu, Fangfang Zhang and Sencun Zhu PowerPoint PPT Presentation


  • 50 Views
  • Uploaded on
  • Presentation posted in: General

Introduction & Motivation. Online Social Networking (OSN) Websites Popularity: Facebook (>400M users) MySpace (>70M) Attractive targets for worm Characteristics of OSNs Small average shortest path length High clustering Scale-free networks. OSN Worms Fast-spreading

Download Presentation

Toward Worm Detection in Online Social Networks Wei Xu, Fangfang Zhang and Sencun Zhu

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Toward worm detection in online social networks wei xu fangfang zhang and sencun zhu

Introduction & Motivation

  • Online Social Networking (OSN) Websites

    • Popularity: Facebook (>400M users) MySpace (>70M)

    • Attractive targets for worm

  • Characteristics of OSNs

    • Small average shortest path length

    • High clustering

    • Scale-free networks

  • OSN Worms

    • Fast-spreading

    • Exploiting features of OSN websites (e.g., messaging)

    • Follow social connections of infected users

  • Goal

    • An early warning OSN worm detection system

Fig. 1: Koobface Worm Infection Cycle

Toward Worm Detection in Online Social NetworksWei Xu, Fangfang Zhang and Sencun Zhu

System Design

  • Communication Module

    • Communicate with OSN administrators

  • System Overview

    • A honeypot-like surveillance network in OSNs

    • A two-level correlation scheme to minimize detection error

  • Configuration Module

    • Select as few as possible normal user accounts to deploy decoy friends

    • Leverage topological properties of OSNs

  • Evidence Collecting Module

    • Passively collect worm propagation evidence (E.g., worm messages, worm updates)

  • Worm Detection Module

    • Two-level spatial-correlation detection

    • Local correlation

    • Network correlation

Fig. 2: Worm Detection System Overview

Fig. 3: An Example of Two Level Correlation

Evaluation on Flickr Dataset

  • Early Warning Detection

  • Impact of Selected User Set Size

  • Containment Measures

Fig. 5: Worm Infection Number versus the Size of Selected Users Set

Fig. 6: Worm Infection versus Different Containment Measures

Fig. 4: Worm Infection Number versus Different Initial Infected User Accounts (Koobface worm case)

[1]. “Toward Worm Detection in Online Social Networks” To appear in Proceedings of 25th Annual Computer

Security Applications Conference (ACSAC), 2010

More information is available: http://www.cse.psu.edu/~szhu/


  • Login