| Presentation | 2023-09-08 Network anomaly detection and failure scale estimation method Naoya Ogawa, Ryoichi Kawahara, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a network anomaly detection and failure scale estimation method using AI. For anomaly detection, we use an autoencoder that is unsupervised learning, and apply the autoencoder to each communication group for the network to be monitored. By learning the relationship between monitoring items under normal communication conditions, we detect an anomaly from the mean square error obtained from each autoencoder when an anomaly occurs and estimate the scale of the failure from the number of autoencoders determined to be anomalous. We conduct experiments on communication on a virtual network constructed by Mininet, a network emulator, and evaluate the effectiveness of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Anomaly detection / Failure scale / Autoencoder / Mininet |
| Paper # | NS2023-57 |
| Date of Issue | 2023-08-31 (NS) |
| Conference Information | |
| Committee | NS / IN / CS |
|---|---|
| Conference Date | 2023/9/7(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tohoku University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Session management (SIP/IMS), Interoperability/Standardization, NGN/NwGN/Future networks, Cloud/Data center networks, SDN (OpenFlow, etc.)/NFV, IPv6, Machine learning, etc. |
| Chair | Tetsuya Oishi(NTT) / Kunio Hato(NTT) / Daisuke Umehara(Kyoto Inst. of Tech.) |
| Vice Chair | Takumi Miyoshi(Shibaura Inst. of Tech.) / Tsutomu Murase(Nagoya Univ.) / Seiji Kozaki(Mitsubishi Electric) |
| Secretary | Takumi Miyoshi(NTT) / Tsutomu Murase(Kogakuin Univ.) / Seiji Kozaki(NTT) |
| Assistant | Hiroshi Yamamoto(NTT) / / Hikaru Kawasaki(NICT) / Takeshi Suehiro(Mitsubishi Electric) |
| Paper Information | |
| Registration To | Technical Committee on Network Systems / Technical Committee on Information Networks / Technical Committee on Communication Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Network anomaly detection and failure scale estimation method |
| Sub Title (in English) | |
| Keyword(1) | Anomaly detection |
| Keyword(2) | Failure scale |
| Keyword(3) | Autoencoder |
| Keyword(4) | Mininet |
| 1st Author's Name | Naoya Ogawa |
| 1st Author's Affiliation | Toyo University(Toyo Univ.) |
| 2nd Author's Name | Ryoichi Kawahara |
| 2nd Author's Affiliation | Toyo University(Toyo Univ.) |
| Date | 2023-09-08 |
| Paper # | NS2023-57 |
| Volume (vol) | vol.123 |
| Number (no) | NS-177 |
| Page | pp.pp.32-37(NS), |
| #Pages | 6 |
| Date of Issue | 2023-08-31 (NS) |