doi: 10.18178/ijfcc.2017.6.2.490
Mail Detection Model of Campus Network Based on the Adaptive Learning Algorithm
- Nanjing Normal University, Jiangsu, China.
Abstract
Concerning the problem that a large number ofspam disturbing the user, a method named adaptive learningalgorithm was proposed. The passive attack method based onthe Simple Mail Transfer Protocol(SMTP) session log initiatedby the mail host in the campus during half a year. Analysis onthe status of delivery rate and many types of failure message ofthe host behavior in the session record, and ultimately achieveeffective adaptation by detecting spam source host behavior onthe recent email classification. The experimental results showthat the implementation of a number of rounds of classificationstrategy adjustment, at last the detection accuracy can reach94.7%. The design is very useful for network administrators, hecan effectively detect spam internal host status, and control thebehavior of the spam host in the beginning.
Keywords
- Spam host
- SMTP session
- adaptive learning
- categorizer
- failure information
How to Cite
Bin Chen, Yizhou Dong, and Mingrong Mao, "Mail Detection Model of Campus Network Based on the Adaptive Learning Algorithm," International Journal of Future Computer and Communication, vol. 6, no. 2, pp. 63-66, 2017. https://doi.org/ 10.18178/ijfcc.2017.6.2.490
Copyright & License
Copyright © 2017 by the authors. 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).