Publisher

IAIIIAII

Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informas)iJurnal RESTI (Rekayasa Sistem dan Teknologi Informas)i Abstract

The rising frequency and complexity of Distributed Denial of Service (DDoS) attacks pose a severe threat to network security. This study aims to develop an effective and interpretable DDoS detection framework using a hybrid deep learning approach. The proposed method integrates Convolutional Neural Networks (CNN) to capture local traffic patterns and Long Short-Term Memory (LSTM) networks to model temporal dependencies. The CICIDS 2017 dataset, after preprocessing steps including data cleaning, standardization, and class balancing with SMOTE, was used to train and evaluate the model. Experimental results show that the framework achieved 99.98% accuracy and a 99.83% F1-Score, with minimal false positive and false negative rates. This study integrates SHAP to improve model interpretability, aligning feature importance with network security expertise. Future research will focus on real-time deployment, cross-dataset validation, and exploring alternative explainable AI techniques for improved scalability.

Conclusion

This study successfully developed a hybrid CNN-LSTM model for accurate and interpretable DDoS attack detection.The model achieved near-perfect performance, demonstrating its effectiveness in distinguishing malicious from benign network traffic.The integration of SHAP enhanced the models transparency by revealing the key features influencing its predictions, aligning with domain knowledge and fostering trust in its decisions.

Future Research

Future research should explore adaptive explainability mechanisms to maintain interpretability in dynamic network environments. Investigating online learning strategies will enable the model to continuously adapt to evolving attack patterns and maintain high detection accuracy over time. Furthermore, extending the interpretability framework to incorporate causal inference techniques could provide deeper insights into the root causes of DDoS attacks and inform more effective mitigation strategies, ultimately enhancing network resilience and security posture.

References

1. A Hybrid Deep Learning Approach to Network Traffic Anomaly Detection Enhanced by SHAP and LIME Interpretability... ieeexplore.ieee.org/document/11013553A Hybrid Deep Learning Approach to Network Traffic Anomaly Detection Enhanced by SHAP and LIME Interpretability ieeexplore ieee document 11013553
2. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informas)i. enhancing network security evaluating sdn enabled... doi.org/10.29207/resti.v9i1.6056Jurnal RESTI Rekayasa Sistem dan Teknologi Informas i enhancing network security evaluating sdn enabled doi 10 29207 resti v9i1 6056
3. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informas)i. explainable ddos detection cnn lstm hybrid model... jurnal.iaii.or.id/index.php/RESTI/article/view/6865Jurnal RESTI Rekayasa Sistem dan Teknologi Informas i explainable ddos detection cnn lstm hybrid model jurnal iaii index php RESTI article view 6865

Metadata

File size	413.22 KB
Pages	8
DMCA	Report