An Intrusion Detection System Based on Deep Belief Networks

Belarbi, Othmane; Khan, Aftab; Carnelli, Pietro; Spyridopoulos, Theodoros

doi:10.1007/978-3-031-17551-0_25

Cited by 32 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section reviews recent federated learning strategies for intrusion-detection systems (IDS) and compares them with the approach proposed in this paper. The authors in [ 54 ] employ an architecture very similar to the one we propose, concluding that utilizing an initially pre-trained model leads to better results. This mirrors the approach we adopt, initiating with a Baseline K-means model that has been pre-trained.…”

Section: Discussionmentioning

confidence: 99%

“…Contrary to our work, which formulates the problem as a semi-supervised novelty detection task, they use a Deep Neural Network (DNN) and Deep Belief Network (DBN) for supervised multi-class classification. The work in [ 54 ] might be more suitable for IoT devices with substantial memory and computational capabilities, such as the Raspberry Pi 4, whereas our approach, due to the simplicity of the K-means algorithm compared to a neural network, can be embedded on more constrained devices like the ESP32.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cross-Layer Federated Learning for Lightweight IoT Intrusion Detection Systems

Hajj

Azar

Abdo

et al. 2023

Sensors

View full text Add to dashboard Cite

With the proliferation of IoT devices, ensuring the security and privacy of these devices and their associated data has become a critical challenge. In this paper, we propose a federated sampling and lightweight intrusion-detection system for IoT networks that use K-meansfor sampling network traffic and identifying anomalies in a semi-supervised way. The system is designed to preserve data privacy by performing local clustering on each device and sharing only summary statistics with a central aggregator. The proposed system is particularly suitable for resource-constrained IoT devices such as sensors with limited computational and storage capabilities. We evaluate the system’s performance using the publicly available NSL-KDD dataset. Our experiments and simulations demonstrate the effectiveness and efficiency of the proposed intrusion-detection system, highlighting the trade-offs between precision and recall when sharing statistics between workers and the coordinator. Notably, our experiments show that the proposed federated IDS can increase the true-positive rate up to 10% when the workers and the coordinator collaborate.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Cross-Layer Federated Learning for Lightweight IoT Intrusion Detection Systems

Hajj

Azar

Abdo

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…As the intrusion detection system is the main source of security elements in situation awareness, its accuracy directly affects the assessment of network security. It can detect the maliciousness without compromising the security of hosts and networks [32]. This article further combines network intrusion security with security factors, such as devices and applications, to construct a multifactor fusion network security situation assessment scheme, further improving the effectiveness and accuracy of security situation assessment.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Network Security Grade Protection Combined With Deep Learning for Intrusion Detection

Lin,

Feng,

Jiang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Using deep learning models, we predict information system security indicators and obtain corresponding security evaluation scores. The scores of these predicted security evaluation are used as the input data of regression tree model, and the security grade protection evaluation system is constructed. The model training process involves four different models: VGG19, ResNet-50, XceptionNet, and EfficientNet. Based on the training results, we find that the EfficientNet model consumes fewer computational resources in single detection while achieves a detection accuracy of 99.93% .Subsequently, we apply the CART regression tree to assess the network security posture of 14 commercial systems. The test results of the model show that the mean absolute percentage error(MAPE) is 0.029 and the correlation coefficient is 0.9. These empirical results strongly support the performance of the proposed model and show its significant potential in improving security assessments. With these training results, we gain preliminary insights into the performance of each model and select the EfficientNet model with the best performance for the generation of subsequent security posture evaluation data.Ultimately, the developed security grade protection assessment system provides a reliable and efficient evaluation means for the network security.

show abstract

“…The KDD-CUP99 dataset was again used, showing reduced FPs and improved speeds. Belarbi et al [32] proposed a multi-class NIDS based on a deep belief network (DBN) using the CICIDS2017 dataset to train and evaluate performance. The experimental results demonstrated that DBNs can surpass traditional multilayer perceptron classification performance, significantly improving overall recall.…”

Section: B Algorithm-level Mitigation Effortsmentioning

confidence: 99%

Hybrid Intrusion Detection System Based on Data Resampling and Deep Learning

Chen,

You,

Shiue

2024

IJACSA

View full text Add to dashboard Cite

The growth of the internet has advanced information-sharing capabilities and vastly increased the importance of global network security. However, because new and inconspicuous abnormal behaviors are nearly impossible to detect in massive network access environments, modern intrusion detection systems have identified a high rate of false-positive (FP) and false-negative (FN) attacks. To overcome this, this paper proposes a hybrid deep learning model that significantly mitigates the disadvantages of consistently imbalanced sample attack data. First, it resolves imbalanced data using random undersampling and synthetic minority oversampling techniques. Then, convolutional neural networks (CNNs) extract local and spatial features, and a transformer encoder extracts global and temporal features. The novelty of this combination increases recognition accuracy at the algorithm level, which is crucial to reducing FPs and FNs. The model was subjected to multiclassification testing on the NSL-KDD and CICIDS2017 benchmark datasets, and the results show that our model has higher classification accuracy and lower FP rates than state-ofthe-art intrusion detection models. Moreover, it significantly improves the detection rate of low-frequency attacks.

show abstract

An Intrusion Detection System Based on Deep Belief Networks

Cited by 32 publications

References 32 publications

Cross-Layer Federated Learning for Lightweight IoT Intrusion Detection Systems

Cross-Layer Federated Learning for Lightweight IoT Intrusion Detection Systems

Evaluation of Network Security Grade Protection Combined With Deep Learning for Intrusion Detection

Hybrid Intrusion Detection System Based on Data Resampling and Deep Learning

Contact Info

Product

Resources

About