A vector space model for automatic indexing
Communications of the ACM
Discovering unexpected information from your competitors' web sites
Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
Machine learning in automated text categorization
ACM Computing Surveys (CSUR)
Document Ranking and the Vector-Space Model
IEEE Software
IEMS - The Intelligent Email Sorter
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Challenges of the Email Domain for Text Classification
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
A Comparative Study of Classification Based Personal E-mail Filtering
PADKK '00 Proceedings of the 4th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Current Issues and New Applications
An evaluation of statistical spam filtering techniques
ACM Transactions on Asian Language Information Processing (TALIP)
A comparison of event models for Naive Bayes anti-spam e-mail filtering
EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
An immune-based model for computer virus detection
CANS'05 Proceedings of the 4th international conference on Cryptology and Network Security
A new model for dynamic intrusion detection
CANS'05 Proceedings of the 4th international conference on Cryptology and Network Security
| Hi-index | 0.00 |
The technology of spam filters has recently received considerable attention as a powerful approach to Internet security management. The traditional spam filters almost adopted static measure, and filters need be updated and maintained frequently, so they can not adapt to dynamic spam. In order to get over the limitation of the traditional means, an immunity-based spam classification was proposed in this paper. A brief review about traditional technology of spam filter is given first, particularly, the Bayes probability model. Then the NASC is described in detail by introducing self, non-self, detector and detect algorithm. Finally, a simulation experiment was performed, and the important parameters of the model were analyzed. The experimental result shows that the new model increases the recall of filter greatly in condition that precision also increasing, and demonstrate that the model has the features of self-learning and self-adaptation.