| Presentation | 2016-03-04 Cyber Attack Prediction using News Article Analysis Baatarsuren Munkhdorj, Sekiya Yuji, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The common operation of current cyber defense systems is to search a signature of cyber attack by monitoring network traffic and system stats. If some signature is detected, a countermeasure is made. That means the defense systems encounter cyber attacks with no preparation, and it is a severe problem. On the other hand, some researchers verified that cyber attacks were caused by social actions/opinion. In this study, the author aims to predict cyber attack from social actions/opinion. To realize this, two issues of how to figure out social actions and how to predict cyber attack have to be resolved. The author proposes collecting and analyzing the news articles about cyber attack targets to figure out social actions. To predict cyber attack, Natural Language Processing and SVM classification were applied. The experiment was conducted for 4 attack types by adopting 2 types of features. To train and test the SVM classifier, 85% and 15% of dataset were used respectively. As a result, when using the 1000 keywords which mostly appeared in over 6000 articles as the feature, DDoS, Targeted attack, and SQL injection were predicted with maximum accuracy of 70.3%, 62.4%, and 59.1% respectively. With the 500 positive and 500 negative keywords which mostly appeared in the articles, Account hijacking was predicted with maximum accuracy of 64.0%. As future work, additional information sources, feature selection, and prediction algorithm will be reconsidered. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Cyber Attack / Cyber Attack Prediction / Social Action Analysis / Natural Language Processing / News Article Analysis / SVM Classification |
| Paper # | IN2015-136 |
| Date of Issue | 2016-02-25 (IN) |
| Conference Information | |
| Committee | NS / IN |
|---|---|
| Conference Date | 2016/3/3(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Phoenix Seagaia Resort |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | General |
| Chair | Atsushi Hiramatsu(NTT-AT) / Hidetsugu Kobayashi(NTT) |
| Vice Chair | Hideki Tode(Osaka Pref. Univ.) / Katsunori Yamaoka(Tokyo Inst. of Tech.) |
| Secretary | Hideki Tode(Univ. of Fukui) / Katsunori Yamaoka(NTT) |
| Assistant | Shohei Kamamura(NTT) / Yuichi Sudo(NTT) / Kunitake Kaneko(Keio Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Network Systems / Technical Committee on Information Networks |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Cyber Attack Prediction using News Article Analysis |
| Sub Title (in English) | |
| Keyword(1) | Cyber Attack |
| Keyword(2) | Cyber Attack Prediction |
| Keyword(3) | Social Action Analysis |
| Keyword(4) | Natural Language Processing |
| Keyword(5) | News Article Analysis |
| Keyword(6) | SVM Classification |
| 1st Author's Name | Baatarsuren Munkhdorj |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Sekiya Yuji |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2016-03-04 |
| Paper # | IN2015-136 |
| Volume (vol) | vol.115 |
| Number (no) | IN-484 |
| Page | pp.pp.165-170(IN), |
| #Pages | 6 |
| Date of Issue | 2016-02-25 (IN) |