Data Augmentation for Intrusion Detection and Classification in Cloud Networks
| Autor: | Kawther Hassine, Ridha Hamila, Habib Ben Abdallah, Aiman Erbad, Zina Chkirbene |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Flexibility (engineering)
Discriminator Training set Class imbalance business.industry Computer science Cloud computing Intrusion detection system Machine learning computer.software_genre Machine learning technique Human interaction Security Wireless The Internet Artificial intelligence Architecture business computer Accuracy |
| Zdroj: | IWCMC |
| Popis: | Cloud computing is a paradigm that provides multiple services over the internet with high flexibility in a cost-effective way. However, the growth of cloud-based services comes with major security issues. Recently, machine learning techniques are gaining much interest in security applications as they exhibit fast processing capabilities with real-time predictions. One major challenge in the implementation of these techniques is the available training data for each new potential attack category. In this paper, we propose a new model for secure network based on machine learning algorithms. The proposed model ensures better learning of minority classes using Generative Adversarial Network (GAN) architecture. In particular, the new model optimizes the GAN parameter including the number of inner learning steps for the discriminator to balance the training datasets. Then, the optimized GAN generates highly informative"like real" instances to be appended to the original data which improve the detection of the classes with relatively small training data. Our experimental results show that the proposed approach enhances the overall classification performance and detection accuracy even for the rarely detectable classes for both UNSW and NSL-KDD datasets. The simulation results show also that the proposed model could detect better the network attacks compared to the state-of-art techniques. 2021 IEEE ACKNOWLEDGMENT This work was supported by Qatar University Internal Grant IRCC-2020-001. The statements made herein are solely the responsibility of the author[s]. Scopus |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|