Journal of KIISE (정보과학회 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Social Network Spam Detection using Recursive Structure Features

소셜 네트워크 상에서의 재귀적 네트워크 구조 특성을 활용한 스팸탐지 기법

  • 장보연 (서울대학교 컴퓨터공학부) ;
  • 정시현 (서울대학교 컴퓨터공학부) ;
  • 김종권 (서울대학교 컴퓨터공학부)
  • Received : 2017.03.17
  • Accepted : 2017.09.01
  • Published : 2017.11.15
⟨ Previous Next ⟩

Abstract

Given the network structure in online social network, it is important to determine a way to distinguish spam accounts from the network features. In online social network, the service provider attempts to detect social spamming to maintain their service quality. However the spammer group changes their strategies to avoid being detected. Even though the spammer attempts to act as legitimate users, certain distinguishable structural features are not easily changed. In this paper, we investigate a way to generate meaningful network structure features, and suggest spammer detection method using recursive structural features. From a result of real-world dataset experiment, we found that the proposed algorithm could improve the classification performance by about 8%.

온라인 소셜 네트워크는 정보전파의 용이성 및 파급 영향력이 높지만 이를 악의적으로 활용하기 위한 스패머들이 다수 활동 중이다. 이러한 스패머를 식별하기 위한 스팸 탐지기법 연구가 다양한 분야에서 이루어지고 있지만 스패머들 또한 스팸 내용이나 스팸링크, 활동 주기 등의 특성을 변경하여 탐지를 피하고 있다. 하지만 다른 특성들과 달리 온라인 소셜 네트워크의 고유 네트워크 특성인 링크 특성은 쉽게 변화시키는 어렵다. 따라서 본 논문에서는 이러한 네트워크의 구조적인 특성을 활용하여 스패머를 일반사용자와 구분하는 방법을 제시한다. 즉 일반사용자 노드가 주변 노드와 비슷한 네트워크 특성을 갖는 점에 주목하여 인접 노드를 활용한 재귀적인 구조적 특성을 생성하여 활용함으로써 스패머의 식별확률을 높이고 있다. 이를 검증하기 위한 실험은 트위터의 실제 데이터셋을 Weka 프로그램에 탑재된 랜덤포레스트 알고리즘을 활용하여 측정하였으며, 재귀적인 특성을 활용하지 않는 방법과 기존 제안 알고리즘에 비해 탐지율이 0.82에서 0.90으로 향상됨으로써 제안하는 방법이 스패머를 탐지하는데 효과적임을 제시하고 있다.

Keywords

Acknowledgement

Supported by : 한국연구재단, 서울대학교

References

  1. Ratkiewicz, Jacob, et al., "Detecting and Tracking Political Abuse in Social Media," ICWSM 11, pp. 297-304, 2011.
  2. F. Benevenuto, G. Magno, T. Rodrigues, and V. Almeida, "Detecting spammers on Twitter," Collaboration, Electronic messaging, Anti-Abuse and Spam Conf. (CEAS), 2010.
  3. Zaharia, Matei, et al., "Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing," Proc. of the 9th USENIX conference on Networked Systems Design and Implementation, USENIX Association, 2012.
  4. Lee, Sangho, and Jong Kim, "Warningbird: A near real-time detection system for suspicious urls in twitter stream," IEEE transactions on dependable and secure computing 10.3, pp. 183-195, 2013. https://doi.org/10.1109/TDSC.2013.3
  5. Akoglu, Leman, Mary McGlohon, and Christos Faloutsos, "Oddball: Spotting anomalies in weighted graphs," Advances in Knowledge Discovery and Data Mining, pp. 410-421, 2010.
  6. Stringhini, Gianluca, Christopher Kruegel, and Giovanni Vigna, "Detecting spammers on social networks," Proc. of the 26th annual computer security applications conference, ACM, 2010.
  7. Henderson, Keith, et al., "It's who you know: graph mining using recursive structural features," Proc. of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2011.
  8. Henderson, Keith, et al., "Rolx: structural role extraction & mining in large graphs," Proc. of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2012.
  9. Heymann, Paul, Georgia Koutrika, and Hector Garcia-Molina, "Fighting spam on social web sites: A survey of approaches and future challenges," IEEE Internet Computing 11.6 (2007).
  10. Song, Jonghyuk, Sangho Lee, and Jong Kim, "Spam filtering in twitter using sender-receiver relationship," International Workshop on Recent Advances in Intrusion Detection, Springer Berlin Heidelberg, 2011.
  11. Hu, Xia, et al., "Social Spammer Detection in Microblogging," IJCAI, Vol. 13, 2013.
  12. Benevenuto, Fabricio, et al., "Characterizing user navigation and interactions in online social networks," Information Sciences 195, 1-24, 2012. https://doi.org/10.1016/j.ins.2011.12.009
  13. Jeong, Sihyun, et al., "Follow spam detection based on cascaded social information," Information Sciences 369, 481-499, 2016. https://doi.org/10.1016/j.ins.2016.07.033
  14. Liu, Yuli, et al., "Pay Me and I'll Follow You: Detection of Crowdturfing Following Activities in Microblog Environment," IJCAI, 2016.
  15. Ghosh, Saptarshi, et al., "Understanding and combating link farming in the twitter social network," Proc. of the 21st international conference on World Wide Web, ACM, 2012.