Recommending Inferior Results: A General and Feature-Free Model for Spam Detection

被引:3
作者
Liu, Yuli [1 ,2 ]
机构
[1] Australian Natl Univ, Canberra, ACT, Australia
[2] CSIRO, Data61, Canberra, ACT, Australia
来源
CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT | 2020年
关键词
spam detection; pairwise ranking; label propagation;
D O I
10.1145/3340531.3411900
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Spam activities on multifarious online platforms, such as the opinion spam and fake following relationships have been extensively studied for years. Existing works separately employ hand-crafted features - mainly extracted from user behavior, text information, and relational network, to detect the specific spamming phenomenon on a certain kind of online platform. Although these attempts have made some headway, rapidly emerging spamming categories and frequently changing cheating strategies lead detection models to be subject to circumscribed usability and fragile effectiveness. This paper is the first attempt to develop a general and featurefree fraud detection model, tackling the longstanding and thorny challenges in spam detection area. To achieve this, we first transform diverse relational networks that are contaminated by fraudsters into the unified matrix form. We then deal with the spam problem from a fresh perspective inspired by the pairwise learning thought in the area of recommender system. By comparing pairwise ranking relations of all the entities in the unified matrix, a new pairwise loss objective function is formulated to identify instances that occupy higher rankings as inferior (spamming) results. To further boost detection performance, we incorporate the pairwise ranking detection method and the widely used structure-based algorithm into an integrated framework. Experiments on real-word datasets of differentWeb applications show significant improvements of our proposed framework over competitive methods.
引用
收藏
页码:955 / 964
页数:10
相关论文
共 52 条
  • [1] [Anonymous], 2010, 4 INT AAAI C WEBL SO
  • [2] [Anonymous], 2009, NDSS
  • [3] Bagdouri M., 2015, Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, CIKM '15, P1707
  • [4] Opinion Spam Detection in Web Forum: A Real Case Study
    Chen, Yu-Ren
    Chen, Hsin-Hsi
    [J]. PROCEEDINGS OF THE 24TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB (WWW 2015), 2015, : 173 - 183
  • [5] An Improved Sampler for Bayesian Personalized Ranking by Leveraging View Data
    Ding, Jingtao
    Yu, Guanghui
    He, Xiangnan
    Feng, Fuli
    Li, Yong
    Jin, Depeng
    [J]. COMPANION PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2018 (WWW 2018), 2018, : 13 - 14
  • [6] Uncovering Crowdsourced Manipulation of Online Reviews
    Fayazi, Amir
    Lee, Kyumin
    Caverlee, James
    Squicciarini, Anna
    [J]. SIGIR 2015: PROCEEDINGS OF THE 38TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2015, : 233 - 242
  • [7] SybilBelief: A Semi-Supervised Learning Approach for Structure-Based Sybil Detection
    Gong, Neil Zhenqiang
    Frank, Mario
    Mittal, Prateek
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2014, 9 (06) : 976 - 987
  • [8] Robust Multivariate Autoregression for Anomaly Detection in Dynamic Product Ratings
    Gunnemann, Nikou
    Gunnemann, Stephan
    Faloutsos, Christos
    [J]. WWW'14: PROCEEDINGS OF THE 23RD INTERNATIONAL CONFERENCE ON WORLD WIDE WEB, 2014, : 361 - 371
  • [9] Gyongyi Z., 2004, P 30 INT C VERY LARG, P576, DOI 10.1016/B978-012088469-8.50052-8
  • [10] Web Spambot Detection Based on Web Navigation Behaviour
    Hayati, Pedram
    Potdar, Vidyasagar
    Chai, Kevin
    Talevski, Alex
    [J]. 2010 24TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS (AINA), 2010, : 797 - 803