Next Article in Journal
Fabrication of Micro-Needle Electrodes for Bio-Signal Recording by a Magnetization-Induced Self-Assembly Method
Next Article in Special Issue
3D Tracking via Shoe Sensing
Previous Article in Journal
A Novel Passive Wireless Sensor for Concrete Humidity Monitoring
Previous Article in Special Issue
Distributed Particle Filter for Target Tracking: With Reduced Sensor Communications
Article Menu

Export Article

Open AccessArticle
Sensors 2016, 16(9), 1522; doi:10.3390/s16091522

Combating QR-Code-Based Compromised Accounts in Mobile Social Networks

1,2
,
1,2
,
1,2
,
1,2
and
1,2,*
1
College of Computer Science and Technology, Jilin University, Changchun 130012, China
2
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
*
Author to whom correspondence should be addressed.
Academic Editors: Mianxiong Dong, Zhi Liu, Anfeng Liu and Didier El Baz
Received: 3 July 2016 / Revised: 10 September 2016 / Accepted: 12 September 2016 / Published: 20 September 2016
(This article belongs to the Special Issue New Paradigms in Cyber-Physical Social Sensing)
View Full-Text   |   Download PDF [420 KB, uploaded 20 September 2016]   |  

Abstract

Cyber Physical Social Sensing makes mobile social networks (MSNs) popular with users. However, such attacks are rampant as malicious URLs are spread covertly through quick response (QR) codes to control compromised accounts in MSNs to propagate malicious messages. Currently, there are generally two types of methods to identify compromised accounts in MSNs: one type is to analyze the potential threats on wireless access points and the potential threats on handheld devices’ operation systems so as to stop compromised accounts from spreading malicious messages; the other type is to apply the method of detecting compromised accounts in online social networks to MSNs. The above types of methods above focus neither on the problems of MSNs themselves nor on the interaction of sensors’ messages, which leads to the restrictiveness of platforms and the simplification of methods. In order to stop the spreading of compromised accounts in MSNs effectively, the attacks have to be traced to their sources first. Through sensors, users exchange information in MSNs and acquire information by scanning QR codes. Therefore, analyzing the traces of sensor-related information helps to identify the compromised accounts in MSNs. This paper analyzes the diversity of information sending modes of compromised accounts and normal accounts, analyzes the regularity of GPS (Global Positioning System)-based location information, and introduces the concepts of entropy and conditional entropy so as to construct an entropy-based model based on machine learning strategies. To achieve the goal, about 500,000 accounts of Sina Weibo and about 100 million corresponding messages are collected. Through the validation, the accuracy rate of the model is proved to be as high as 87.6%, and the false positive rate is only 3.7%. Meanwhile, the comparative experiments of the feature sets prove that sensor-based location information can be applied to detect the compromised accounts in MSNs. View Full-Text
Keywords: Cyber Physical Social Sensing; QR code; mobile social networks; compromised accounts; location-based features Cyber Physical Social Sensing; QR code; mobile social networks; compromised accounts; location-based features
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Guo, D.; Cao, J.; Wang, X.; Fu, Q.; Li, Q. Combating QR-Code-Based Compromised Accounts in Mobile Social Networks. Sensors 2016, 16, 1522.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top