| Presentation | 2022-11-24 Research on Anomaly Detection through Analysis of Observed Traffic Using Self-Attention Yuhang Zhou, Akihiro Nakao, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Nowadays, threat activities have become an integral part of our network lives. The sophistication and variety of different types of cyberattacks are growing at an alarming rate, cyber-security has become a primary concern. The intrusion detection (ID) technique was made to deal with this problem, but traditional network intrusion detection system (NIDS) often fail to detect zero-day attacks, their capacity to swiftly respond to emerging intrusions is restricted. As a consequence, anomaly-based deep learning IDS is widely researched. Though it has demonstrated exceptional ability in learning good representations from complex data, it suffers from a low recall rate, poor data efficiency, and speed-performance balancing issues. This paper proposes a new structure for detecting anomalies using a self-attention-based model to leverage the time-series information among the packets to detect not only single point anomalies but also time-dependent anomalies, without relying on any time features given by the statistical system or suffering the long computation time, also improves the model’s generalization performance in the case of a lack of labeled data. The experiment result shows the proposal is effective in improving recall rate than the traditional deep learning model up to 30% without suffering the long computation time. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Anomaly Detection / Self-attention / Denoising Auto Encoder / Machine Learning |
| Paper # | NS2022-108 |
| Date of Issue | 2022-11-17 (NS) |
| Conference Information | |
| Committee | NS / ICM / CQ |
|---|---|
| Conference Date | 2022/11/24(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Humanities and Social Sciences Center, Fukuoka Univ. + Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network quality, Network measurement/management, Network virtualization, Network service, Blockchain, Security, Network intelligence/AI, etc. |
| Chair | Tetsuya Oishi(NTT) / Yuji Nomura(Fujitsu) / Jun Okamoto(NTT) |
| Vice Chair | Takumi Miyoshi(Shibaura Insti of Tech.) / Yu Miyoshi(NTT) / Eiji Takahashi(NEC) / Takefumi Hiraguri(Nippon Inst. of Tech.) / Gou Hasegawa(Tohoku Univ.) |
| Secretary | Takumi Miyoshi(NTT) / Yu Miyoshi(Kogakuin Univ.) / Eiji Takahashi(NTT) / Takefumi Hiraguri(Fujitsu) / Gou Hasegawa(NTT) |
| Assistant | Kotaro Mihara(NTT) / Ryo Yamamoto(Univ. of Electro-Comm) / Kimiko Kawashima(NTT) / Ryo Nakamura(Fukuoka Univ.) / Toshiro Nakahira(NTT) / Kenta Tsukatsune(Tokyo Metroplitan Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Network Systems / Technical Committee on Information and Communication Management / Technical Committee on Communication Quality |
|---|---|
| Language | ENG-JTITLE |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Research on Anomaly Detection through Analysis of Observed Traffic Using Self-Attention |
| Sub Title (in English) | |
| Keyword(1) | Anomaly Detection |
| Keyword(2) | Self-attention |
| Keyword(3) | Denoising Auto Encoder |
| Keyword(4) | Machine Learning |
| 1st Author's Name | Yuhang Zhou |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Akihiro Nakao |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2022-11-24 |
| Paper # | NS2022-108 |
| Volume (vol) | vol.122 |
| Number (no) | NS-274 |
| Page | pp.pp.47-52(NS), |
| #Pages | 6 |
| Date of Issue | 2022-11-17 (NS) |