講演抄録/キーワード |
講演名 |
2021-03-05 10:10
A Convolutional Autoencoder Based Method for Cyber Intrusion Detection ○Xinyi She・Yuji Sekiya(Tokyo Univ.) IN2020-77 |
抄録 |
(和) |
Cyber intrusion detection systems are increasingly crucial due to the monumental growth of internet applications. However, the success of IDS is highly dependent on model design and algorithm. In this paper, we proposed an effective cyber intrusion detection method based on a convolutional autoencoder, which is an effective learning algorithm for reconstructing new feature representation in an unsupervised manner. The proposed method can learn features automatically and reduce training time considerably through dimensionality reduction. The comparative experimental results on the NSL-KDD dataset and CICIDS2017 dataset demonstrate the effectiveness of the proposed model for intrusion detection. |
(英) |
Cyber intrusion detection systems are increasingly crucial due to the monumental growth of internet applications. However, the success of IDS is highly dependent on model design and algorithm. In this paper, we proposed an effective cyber intrusion detection method based on a convolutional autoencoder, which is an effective learning algorithm for reconstructing new feature representation in an unsupervised manner. The proposed method can learn features automatically and reduce training time considerably through dimensionality reduction. The comparative experimental results on the NSL-KDD dataset and CICIDS2017 dataset demonstrate the effectiveness of the proposed model for intrusion detection. |
キーワード |
(和) |
Network Security / Intrusion Detection / Convolutional Autoencoder / / / / / |
(英) |
Network Security / Intrusion Detection / Convolutional Autoencoder / / / / / |
文献情報 |
信学技報, vol. 120, no. 414, IN2020-77, pp. 138-143, 2021年3月. |
資料番号 |
IN2020-77 |
発行日 |
2021-02-25 (IN) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
IN2020-77 |