Malware detection Based on Behavior in Delay Tolerant Network using Support Vector Machine |
Author(s): |
| K.M.Rajiha , Francis Xavier Engineering College; D.C.Winnie Wise, Francis Xavier Engineering College; S.N.Ananthi, Francis Xavier Engineering College |
Keywords: |
| Delay tolerant network (DTN), Support Vector Machine (SVM), Naïve Bayes |
Abstract |
|
Delay tolerant network (DTN) is widely being used for short range communication as it works well in intermittent connectivity areas. DTN propagates information in its network via opportunistic contacts of its nodes. Proximity malware exploits this propagation nature of DTN. The previous methods for behavioral characterization of proximity malware have used naive Bayes model. To improve detection rate, we propose a Support Vector Machine (SVM) that detects the malware in the delay tolerant networks in an efficient and quick way. SVM is a supervisory learning model that can analyze and classify patterns. It not only recognizes the already existing patterns of malware based on its behavior but also the predictable patterns. SVM is less prone to over fitting, which becomes an advantage and makes it desirable for bigger networks. |
Other Details |
|
Paper ID: IJSRDV3I1004 Published in: Volume : 3, Issue : 1 Publication Date: 01/04/2015 Page(s): 5-7 |
Article Preview |
|
|
|
|
