Presentation 2015-06-12
Detecting Malicious Domain Names based on the Time-series Analysis of Attackers Network Resources
Daiki Chiba, Takeshi Yagi, Mitsuaki Akiyama, Tatsuya Mori, Takeshi Yada, Takeo Hariu, Shigeki Goto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Attackers launching cyber attacks frequently change their malicious websites to evade countermeasures such as blacklisting. To detect such changing malicious websites, many detection methods using the network and domain name based characteristics have been proposed. However, a typical detection method fails to evaluate changing malicious websites since the method only relies on the information at a certain point in time. Therefore, we propose a new detection method of malicious domain names focusing on the characteristics of attackers behavior, especially the changing situation of malicious domain names. Moreover, we realize the method for determining the optimal granularity of malicious domain names for preventing users from accessing them. Our evaluation using large and latest real dataset reveals that our method successfully detects previously undetectable malicious domain names by the typical method. The evaluation also shows that many malicious websites can be effectively blocked using the granularity of domain names.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Drive-by download attack / Domain name / Blacklisting / DNS / Machine learning
Paper # IA2015-10,ICSS2015-10
Date of Issue 2015-06-04 (IA, ICSS)

Conference Information
Committee IA / ICSS
Conference Date 2015/6/11(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyushu Institute of Technology Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Internet Security, etc.
Chair Ken-ichi Yoshida(Univ. of Tsukuba) / Yutaka Miyake(KDDI R&D Labs.)
Vice Chair Hiroyuki Osaki(Kwansei Gakuin Univ.) / Masahiro Jibiki(NICT) / Yutaka Nakamura(Kyushu Inst. of Tech.) / Takashi Nishide(Univ. of Tsukuba) / Yoshiaki Shiraishi(Kobe Univ.)
Secretary Hiroyuki Osaki(Tokyo Inst. of Tech.) / Masahiro Jibiki(Osaka Univ.) / Yutaka Nakamura(Mitsubishi Electric) / Takashi Nishide(NII) / Yoshiaki Shiraishi
Assistant Yuichiro Hei(KDDI R&D Labs.) / Hiroshi Yamamoto(Ritsumeikan Univ.) / Toshiki Watanabe(NEC) / Katsunari Yoshioka(Yokohama National Univ.) / Kazunori Kamiya(NTT)

Paper Information
Registration To Technical Committee on Internet Architecture / Technical Committee on Information and Communication System Security
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Detecting Malicious Domain Names based on the Time-series Analysis of Attackers Network Resources
Sub Title (in English)
Keyword(1) Drive-by download attack
Keyword(2) Domain name
Keyword(3) Blacklisting
Keyword(4) DNS
Keyword(5) Machine learning
1st Author's Name Daiki Chiba
1st Author's Affiliation Nippon Telegraph and Telephone Corporation/Waseda University(NTT/Waseda Univ.)
2nd Author's Name Takeshi Yagi
2nd Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
3rd Author's Name Mitsuaki Akiyama
3rd Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
4th Author's Name Tatsuya Mori
4th Author's Affiliation Waseda University(Waseda Univ.)
5th Author's Name Takeshi Yada
5th Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
6th Author's Name Takeo Hariu
6th Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
7th Author's Name Shigeki Goto
7th Author's Affiliation Waseda University(Waseda Univ.)
Date 2015-06-12
Paper # IA2015-10,ICSS2015-10
Volume (vol) vol.115
Number (no) IA-80,ICSS-81
Page pp.pp.51-56(IA), pp.51-56(ICSS),
#Pages 6
Date of Issue 2015-06-04 (IA, ICSS)