Earticle

초록

영어

Spam is a serious problem not only the number of floods but also more and more volatile type. It has caused a great impact on people's daily lives. Especially fraud spam, even cause huge losses to companies or individuals possibility. Therefore, it is imminent to filter spam efficiently. Existing spam filtering mechanism is mainly based on the character and content of the spam message. However, once the spam filter uses in other user's mailbox, the existing spam filtering techniques can not be well adapted. In this paper, we propose the adaptive spam filtering method for the above shortcomings. The method uses the unlabeled spam data that from other user or domain to enhance the adaptive and opposability of the anti-spam system. We use the transfer learning model to build the spam filtering system. A transfer learning model can use the untagged data, and migrate knowledge between different filter model, and improve the active collaboration of the filter.

목차

Abstract
 1. Introduction
 2. Related Work
 3. Transfer Learning using Markov Logic Networks
  3.1 Markov Logic Networks
  3.2 Transfer Learning using MLN
 4. System Framework
  4.1 Knowledge Transfer Framework for Spam Filtering
  4.2 Predicate Design of MLN
  4.3 Structure Learning of MLN
  4.4 Transfer Learning of MLN
 5. Experiments and Results
  5.1 Experimental Environment
  5.2 Data Preprocessing
  5.3 Predicate Mapping
  5.4 Spam Detection Results
 6. Conclusion and Future Work
 Acknowledgements
 References

키워드

저자

• Xing Wang [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]
• Bin-Xing Fang [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]
• Hui He [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]
• Hong-Li Zhang [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Security and Its Applications

• 간기

  격월간

• pISSN

  1738-9976

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605