Presentation 2014-11-28
Detecting infected hosts with machine learning analysis of DNS responses
Wataru TSUDA, Youki KADOBAYASHI, Hirotaka FUJIWARA, Suguru YAMAGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, we face cyber attacks such as illegal money transfer via net-banking, spam mail and DDoS attacks caused by botnet. In this research, we propose novel detection system which uses Random Forest for detecting botnet-related domain names. In this system, we apply many kinds of features from DNS response packet to deal with botnets which utilize DGA, Fast Flux Domain and so on. We experimented with one month of real DNS traffic data, and our system achieved 96.96% detection rates and 1.27% false positive rates.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) malware / botnet / dns / machine learning
Paper # ICSS2014-62
Date of Issue

Conference Information
Committee ICSS
Conference Date 2014/11/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information and Communication System Security (ICSS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Detecting infected hosts with machine learning analysis of DNS responses
Sub Title (in English)
Keyword(1) malware
Keyword(2) botnet
Keyword(3) dns
Keyword(4) machine learning
1st Author's Name Wataru TSUDA
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Youki KADOBAYASHI
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Hirotaka FUJIWARA
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
4th Author's Name Suguru YAMAGUCHI
4th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2014-11-28
Paper # ICSS2014-62
Volume (vol) vol.114
Number (no) 340
Page pp.pp.-
#Pages 6
Date of Issue