LSTM SMOTE: An Effective Strategies for DDoS Detection in Imbalanced Network Environments DOI Open Access
Rissal Efendi, Teguh Wahyono, Indrastanti Ratna Widiasari

et al.

Published: July 24, 2024

In detecting DDoS, deep learning faces challenges and difficulties such as high computational demands, long training times, complex model interpretation. This research focuses on overcoming these by proposing an effective strategy for DDoS attacks in unbalanced network environments. uses SMOTE to increase the class distribution of data set allowing models using LSTM learn time anomalies effectively when occur. The experiments carried out have shown significant improvement performance integrated with SMOTE. These include validation loss results 0.048 0.1943 without SMOTE, accuracy 99.50 97.50. Apart from that, there was f1 score 93.4% 98.3%. this research, it is proven that can be used improve heterogeneous networks, well increasing robustness reliability.

Language: Английский

LSTM SMOTE: An Effective Strategies for DDoS Detection in Imbalanced Network Environments DOI Open Access
Rissal Efendi, Teguh Wahyono, Indrastanti Ratna Widiasari

et al.

Published: July 24, 2024

In detecting DDoS, deep learning faces challenges and difficulties such as high computational demands, long training times, complex model interpretation. This research focuses on overcoming these by proposing an effective strategy for DDoS attacks in unbalanced network environments. uses SMOTE to increase the class distribution of data set allowing models using LSTM learn time anomalies effectively when occur. The experiments carried out have shown significant improvement performance integrated with SMOTE. These include validation loss results 0.048 0.1943 without SMOTE, accuracy 99.50 97.50. Apart from that, there was f1 score 93.4% 98.3%. this research, it is proven that can be used improve heterogeneous networks, well increasing robustness reliability.

Language: Английский

Citations

1