Abstract
Network Intrusion leaks the personal information of network users on a large scale, causing serious security risks. It is of great significance to the Intrusion Detection Systems (IDS) to find abnormal traffic from a huge database in time. Traditional machine learning methods to detect abnormal network traffic usually need to manually extract features from the dataset, which is time-consuming and has low accuracy. This paper proposes a deep learning-based abnormal traffic detection method based on an Improved One-Dimensional Convolutional Neural Networks (ICNN-1D) to detect abnormal network traffic, which greatly improves the extraction accuracy of abnormal traffic features and improves the identification of attack traffic. CNN applies multiple filters (convolution kernels) to the raw pixel data of an image to extract and learn higher-level features. After multiple convolutions, the characteristic graph with the same number of categories as the number of samples is obtained. The experimental results on the dataset CIC-IDS2017 show that the accuracy of the hybrid algorithm is 99.8%. Compared with other learning algorithms, the accuracy of our method greatly improves, and the operation time has been reduced.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.