Data Augmentation for Intrusion Detection and Classification in Cloud Networks

Chkirbene, Zina; Abdallah, Habib Ben; Hassine, Kawther; Hamila, Ridha; Erbad, Aiman

doi:10.1109/iwcmc51323.2021.9498633

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The scarcity of training data is still an obstacle in building a robust learning model. Chkirbene et al [23] applied the GAN structure to learn more informative instances from minority classes. They optimized parameters in inner learning steps of the discriminator in a generic GAN model, aiming to better identify potential attack types in anomaly detection with less training data.…”

Section: B Data Augmentation With Ganmentioning

confidence: 99%

Distribution Bias Aware Collaborative Generative Adversarial Network for Imbalanced Deep Learning in Industrial IoT

Zhou

et al. 2023

IEEE Trans. Ind. Inf.

102

View full text Add to dashboard Cite

The impact of Internet of Things (IoT) has become increasingly significant in smart manufacturing, while Deep Generative Model (DGM) is viewed as a promising learning technique to work with large amount of continuously generated industrial big data in facilitating modern industrial applications. However, it is still challenging to handle the imbalanced data when using conventional Generative Adversarial Network (GAN) based learning strategies. In this study, we propose a Distribution Bias aware Collaborative Generative Adversarial Network (DB-CGAN) model for imbalanced deep learning in industrial IoT, especially to solve limitations caused by distribution bias issue between the generated data and original data, via a more robust data augmentation. An integrated data augmentation framework is constructed by introducing a complementary classifier into the basic GAN model. Specifically, a conditional generator with random labels is designed and trained adversarially with the classifier to effectively enhance augmentation of the number of data samples in minority classes, while a weight sharing scheme is newly designed between two separated feature extractors, enabling the collaborative adversarial training among generator, discriminator, and classifier. An augmentation algorithm is then developed for intelligent anomaly detection in imbalanced learning, which can significantly improve the classification accuracy based on the correction of distribution bias using the rebalanced data. Compared with five baseline methods, experiment evaluations based on two real-world imbalanced datasets demonstrate the outstanding performance of our proposed model in tackling the distribution bias issue for multi-class classification in imbalanced learning for industrial IoT applications.

show abstract

Section: B Data Augmentation With Ganmentioning

confidence: 99%

Distribution Bias Aware Collaborative Generative Adversarial Network for Imbalanced Deep Learning in Industrial IoT

Zhou

et al. 2023

IEEE Trans. Ind. Inf.

102

View full text Add to dashboard Cite

show abstract

“…They have tackled the data imbalance issue through integrating Wasserstein Generative Adversarial Network-Gradient Penalty (WGAN-GP) with Supervised Adversarial Variational Auto-Encoder With Regularization (SAVAER) [71]. Even though GAN based models, proposed in references [31] and [13], have shown promising results, training these networks is not an easy task. Yang et al [71] used WGAN-GP rather than the classical GAN as it allows for more stable training of the network.…”

Section: Literature Review and Related Workmentioning

confidence: 99%

“…Using only the CNN, the F1-Score reached only 89% [3]. Chkirbene et al [13] highlighted the importance of optimizing the GAN in order to achieve higher performance. They have managed to increase the detection rate of the U2R attack type on the NSL-KDD dataset from around 20% to 57%.…”

Section: Adaptive Synthetic Sampling (Adasyn)mentioning

confidence: 99%

“…GAN are deep learning technique that is used mainly for generating new synthesized data samples to train DL models on an enhanced dataset to avoid over-fitting and to make DL models generalize well. Training a GAN model consists of training two models: a generator and a discriminator [31,13,71]. The former is the one responsible for generating new samples and the latter is used to determine the quality of the generated samples [31,71].…”

Section: Author's Declarationmentioning

confidence: 99%

“…The former is the one responsible for generating new samples and the latter is used to determine the quality of the generated samples [31,71]. The ideal situation, when training such models, is when the discriminator is unable to distinguish the fake data samples from the original data samples [31,13]. Vanilla GAN model trains on the given data to learn its distribution without paying much attention to the labels associated with different samples [31].…”

Section: Author's Declarationmentioning

confidence: 99%

See 2 more Smart Citations

Data Balancing and Hyper-parameter Optimization for Machine Learning Algorithms for Secure IoT Networks

Elghalhoud

Naik

Zaman

et al. 2022

Proceedings of the 18th ACM International Symposium on QoS and Security for Wireless and Mobile Networks on 18th ACM Internatio

View full text Add to dashboard Cite

Nowadays, many industries rely on Machine Learning (ML) algorithms and their ability to learn from existing data to make inferences about new unlabeled data. Applying ML algorithms to the network security domain is not new. However, without proper data preprocessing and proper optimization of the hyper-parameters (HPs) of ML algorithms, these algorithms might not achieve their full potential. Furthermore, attacks on network infrastructures come in a variety of forms and at different frequencies. Cyber-security experts often require the help of an automated process that filters and classifies attacks. To apply specific preventive measures for securing networks, the classification of the attack type is key. Many ML models have been proposed as a base for Network Intrusion Detection (NID) systems. However, their performance varies based on multiple factors. For instance, an ML model fitted on a highly imbalanced dataset may be biased toward over-represented attack types. On the other hand, paying attention only to the ML model's performance in the minority classes can negatively affect its performance in the majority classes or overall performance. This research proposes a framework that applies pre-processing steps, including data balancing, and utilizes optimization techniques to tune the HPs of random forest, gradient boosting machine, and deep neural networks. The conducted experiments in this research provide a performance comparison between three different optimization algorithms: Tree-structured Parzen Estimator (TPE), Bayesian Optimization and Hyperband (BOHB), and Particle Swarm Optimization (PSO). The research results show that through data balancing and optimization of the HPs and architecture of deep neural networks, their performance can improve significantly: false alarm rate of 0% and only 1.79% using the BoT-IoT and the ToN-IoT benchmark datasets, respectively.To address the issue of imbalanced datasets, this research gives a data balancing algorithm and compares its performance to other existing approaches that use: Random Over-Sampling (ROS), Synthetic Minority Oversampling TEchnique (SMOTE), Adaptive Synthetic Sampling (ADASYN), and Generative Adversarial Networks (GAN). The data balancing algorithm is combined with Convolutional Neural Networks (CNN) to extract spatial features and classify the different attack types. Using the NSL-KDD and the BoT-IoT datasets for benchmarking, the proposed system achieves high performance in the minority classes: recall scores of 70.50% and 72.08% on the User to Root (U2R) and Remote to Local (R2L) attack classes of the NSL-KDD dataset, respectively, while maintaining an overall False Alarm Rate (FAR) of 6.50% and a recall of 90.46% on the binary classification task. The proposed system scores a weighted average F1-Score of 99.45% on the multi-class classification task using the BoT-IoT dataset.

show abstract

Generative adversarial networks-based security and applications in cloud computing: a survey

Wang,

Yin,

Liu

et al. 2024

Telecommun Syst

View full text Add to dashboard Cite

Data Augmentation for Intrusion Detection and Classification in Cloud Networks

Cited by 6 publications

References 14 publications

Distribution Bias Aware Collaborative Generative Adversarial Network for Imbalanced Deep Learning in Industrial IoT

Distribution Bias Aware Collaborative Generative Adversarial Network for Imbalanced Deep Learning in Industrial IoT

Data Balancing and Hyper-parameter Optimization for Machine Learning Algorithms for Secure IoT Networks

Generative adversarial networks-based security and applications in cloud computing: a survey

Contact Info

Product

Resources

About