| Presentation | 2018-11-04 A Machine Learning-based Method for Detecting Malicious JavaScript using Information based on Abstract Syntax Tree Ryota Sano, Junko Sato, Yoichi Murakami, Masaki Hanada, Eiji Nunohiro, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The number of Drive-by-Download attacks, which can be infected with malware via websites, has recently been increased. Since JavaScript is often used in those attacks, an efficient method for detecting malicious JavaScript with high accuracy is strongly required. In this paper, we propose a new machine learning-based method of detecting such JavaScript using three features -- keywords (character strings) appeared in the abstract syntax tree of JavaScript code, its attributes and hierarchical structure of the tree. The proposed method is evaluated based on the cross-validation on the two datasets, one is the dataset from Government related websites, the other is the MWS D3M dataset. Furthermore, the usefulness of the proposed method will be shown from the viewpoint of detection performance of malicious JavaScript. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Drive-by Download Attack / JavaScript / Machine Learning |
| Paper # | ISEC2018-75,SITE2018-53,LOIS2018-35 |
| Date of Issue | 2018-10-27 (ISEC, SITE, LOIS) |
| Conference Information | |
| Committee | SITE / ISEC / LOIS |
|---|---|
| Conference Date | 2018/11/3(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tetsuya Morizumi(Kanagawa Univ.) / Atsushi Fujioka(Kanagawa Univ.) / Tomohiro Yamada(NTT) |
| Vice Chair | Masaru Ogawa(Kobe Gakuin Univ.) / Takushi Otani(Kibi International Univ.) / Shiho Moriai(NICT) / Shoichi Hirose(Univ. of Fukui) / Toru Kobayashi(Nagasaki Univ.) |
| Secretary | Masaru Ogawa(Tokyo Health Care Univ.) / Takushi Otani(Toyo Eiwa Univ.) / Shiho Moriai(Tokai Univ.) / Shoichi Hirose(NICT) / Toru Kobayashi(NTT) |
| Assistant | Hisanori Kato(KDDI Research) / Nobuyuki Yoshinaga(Yamaguchi Pref Univ.) / Daisuke Suzuki(Hokuriku Univ.) / Kazunari Omote(Tsukuba Univ.) / Yuuji Suga(IIJ) / Shinichiro Eitoku(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Social Implications of Technology and Information Ethics / Technical Committee on Information Security / Technical Committee on Life Intelligence and Office Information Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Machine Learning-based Method for Detecting Malicious JavaScript using Information based on Abstract Syntax Tree |
| Sub Title (in English) | |
| Keyword(1) | Drive-by Download Attack |
| Keyword(2) | JavaScript |
| Keyword(3) | Machine Learning |
| 1st Author's Name | Ryota Sano |
| 1st Author's Affiliation | Tokyo University of Information Sciences(Tokyo Univ. of Information Sciences) |
| 2nd Author's Name | Junko Sato |
| 2nd Author's Affiliation | Graduate School of Informatics, Tokyo University of Information Sciences(Tokyo Univ. of Information Sciences) |
| 3rd Author's Name | Yoichi Murakami |
| 3rd Author's Affiliation | Tokyo University of Information Sciences(Tokyo Univ. of Information Sciences) |
| 4th Author's Name | Masaki Hanada |
| 4th Author's Affiliation | Tokyo University of Information Sciences(Tokyo Univ. of Information Sciences) |
| 5th Author's Name | Eiji Nunohiro |
| 5th Author's Affiliation | Tokyo University of Information Sciences(Tokyo Univ. of Information Sciences) |
| Date | 2018-11-04 |
| Paper # | ISEC2018-75,SITE2018-53,LOIS2018-35 |
| Volume (vol) | vol.118 |
| Number (no) | ISEC-279,SITE-280,LOIS-281 |
| Page | pp.pp.63-68(ISEC), pp.63-68(SITE), pp.63-68(LOIS), |
| #Pages | 6 |
| Date of Issue | 2018-10-27 (ISEC, SITE, LOIS) |