| Presentation | 2016-11-25 Performance of link-mining techniques to detect malicious websites Yasuhiro Takano, Daiki Ito, Tatsuya Nagai, Masaki Kamizono, Masami Mohri, Yoshiaki Shiraishi, Yuji Hoshizawa, Masakatu Morii, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Conventional techniques to avoid malicious websites techniques by referring URL's keywords reported in black lists have been studied. Since attackers can modify the URL quite often, however, the conventional techniques are concerned that they are difficult to follow the frequent updates. Our previous contribution has shown that the malicious websites have a certain correlation among them. This paper evaluates, therefore, performance of supervised-inkmining techniques to detect the malicious websites by inputting the link structure captured from the actual websites. The experimental evaluation results shows that by determining the networks automatically the convolutional neural networks (CNN) algorithms achieves the accuracy = 87%, which outperform the support vector classification (SVC) techniques significantly. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | drive-by-download attack / linkmining / support vector classification (SVC) / convolutional neural networks (CNN) |
| Paper # | ICSS2016-44 |
| Date of Issue | 2016-11-18 (ICSS) |
| Conference Information | |
| Committee | ICSS |
|---|---|
| Conference Date | 2016/11/25(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Institute of Information Security |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Information and Communication System Security, etc. |
| Chair | Yutaka Miyake(KDDI R&D Labs.) |
| Vice Chair | Yoshiaki Shiraishi(Kobe Univ.) / Takeshi Ueda(Mitsubishi Electric) |
| Secretary | Yoshiaki Shiraishi(NII) / Takeshi Ueda(Yokohama National Univ.) |
| Assistant | Kazunori Kamiya(NTT) / Takahiro Kasama(NICT) |
| Paper Information | |
| Registration To | 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) | Performance of link-mining techniques to detect malicious websites |
| Sub Title (in English) | |
| Keyword(1) | drive-by-download attack |
| Keyword(2) | linkmining |
| Keyword(3) | support vector classification (SVC) |
| Keyword(4) | convolutional neural networks (CNN) |
| 1st Author's Name | Yasuhiro Takano |
| 1st Author's Affiliation | Kobe University(Kobe Univ.) |
| 2nd Author's Name | Daiki Ito |
| 2nd Author's Affiliation | Kobe University(Kobe Univ.) |
| 3rd Author's Name | Tatsuya Nagai |
| 3rd Author's Affiliation | Kobe University(Kobe Univ.) |
| 4th Author's Name | Masaki Kamizono |
| 4th Author's Affiliation | PwC Cyber Services LLC(PwC Cyber Services) |
| 5th Author's Name | Masami Mohri |
| 5th Author's Affiliation | Gifu University(Gifu Univ.) |
| 6th Author's Name | Yoshiaki Shiraishi |
| 6th Author's Affiliation | Kobe University(Kobe Univ.) |
| 7th Author's Name | Yuji Hoshizawa |
| 7th Author's Affiliation | PwC Cyber Services LLC(PwC Cyber Services) |
| 8th Author's Name | Masakatu Morii |
| 8th Author's Affiliation | Kobe University(Kobe Univ.) |
| Date | 2016-11-25 |
| Paper # | ICSS2016-44 |
| Volume (vol) | vol.116 |
| Number (no) | ICSS-328 |
| Page | pp.pp.31-35(ICSS), |
| #Pages | 5 |
| Date of Issue | 2016-11-18 (ICSS) |