Title | ||
---|---|---|
Behaviorial-Based Network Flow Analyses For Anomaly Detection In Sequential Data Using Temporal Convolutional Networks |
Abstract | ||
---|---|---|
In many applications the capability of Temporal Convolutional Networks (TCNs) on sequence modelling tasks has been confirmed to outperform classic approaches of recurrent neural networks (RNNs). Due to the lack of adequate network traffic flow analyses, anomaly-based approaches in intrusion detection systems are suffering from accurate deployment, analysis and evaluation. Accordingly, this study focused on network intrusion detection for DDoS threats using TCNs with network flow analyzer, CICFlowMeter-v4.0 to classify the network threats using behavior feature analyses. The experimental results reveal that that the prediction accuracy of intrusion detection goes up to 95.77% for model training with N = 50,000 for sizing (N) of samples using the IDS dataset CIC-IDS-2017. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-34986-8_12 | ADVANCES IN E-BUSINESS ENGINEERING FOR UBIQUITOUS COMPUTING |
Keywords | DocType | Volume |
Intrusion detection, Temporal convolutional networks, Recurrent neural networks, DDoS, CICFlowMeter | Conference | 41 |
ISSN | Citations | PageRank |
2367-4512 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenhui Lin | 1 | 3 | 1.40 |
Ping Wang | 2 | 235 | 15.84 |
Bao-Hua Wu | 3 | 0 | 0.34 |
Ming-Sheng Jhou | 4 | 0 | 0.34 |
Kuo-Ming Chao | 5 | 1123 | 130.82 |
Chi-Chun Lo | 6 | 593 | 54.99 |