A Semi-supervised Deep Auto-encoder Based Intrusion Detection for IoT

Fenanir, Samir; Semchedine, Fouzi; Harous, Saad; Baadache, Abderrahmane

doi:10.18280/isi.250503

Cited by 12 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [20], the authors use a deep autoencoder as an intrusion detection system that works based on anomaly detection. Their proposed system trains only with normal data, and the pattern of normal data is learned only by using the characteristics of normal behavior.…”

Section: Literature Reviewmentioning

confidence: 99%

Practical autoencoder based anomaly detection by using vector reconstruction error

2023

View full text Add to dashboard Cite

Nowadays, cloud computing provides easy access to a set of variable and configurable computing resources based on user demand through the network. Cloud computing services are available through common internet protocols and network standards. In addition to the unique benefits of cloud computing, insecure communication and attacks on cloud networks cannot be ignored. There are several techniques for dealing with network attacks. To this end, network anomaly detection systems are widely used as an effective countermeasure against network anomalies. The anomaly-based approach generally learns normal traffic patterns in various ways and identifies patterns of anomalies. Network anomaly detection systems have gained much attention in intelligently monitoring network traffic using machine learning methods. This paper presents an efficient model based on autoencoders for anomaly detection in cloud computing networks. The autoencoder learns a basic representation of the normal data and its reconstruction with minimum error. Therefore, the reconstruction error is used as an anomaly or classification metric. In addition, to detecting anomaly data from normal data, the classification of anomaly types has also been investigated. We have proposed a new approach by examining an autoencoder’s anomaly detection method based on data reconstruction error. Unlike the existing autoencoder-based anomaly detection techniques that consider the reconstruction error of all input features as a single value, we assume that the reconstruction error is a vector. This enables our model to use the reconstruction error of every input feature as an anomaly or classification metric. We further propose a multi-class classification structure to classify the anomalies. We use the CIDDS-001 dataset as a commonly accepted dataset in the literature. Our evaluations show that the performance of the proposed method has improved considerably compared to the existing ones in terms of accuracy, recall, false-positive rate, and F1-score metrics.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Practical autoencoder based anomaly detection by using vector reconstruction error

2023

View full text Add to dashboard Cite

show abstract

“…This paper aimed to develop a multi-class network intrusion detection system based on deep learning, which is not the case with [19,[25][26][27][28], whose focus was on binary classification. For baseline models, three classical machine learning multi-class classifiers were chosen based on their popularity in the literature.…”

Section: Classical Machine Learning Multi-class Classifiersmentioning

confidence: 99%

Adversarial Robust and Explainable Network Intrusion Detection Systems Based on Deep Learning

et al. 2022

View full text Add to dashboard Cite

The ever-evolving cybersecurity environment has given rise to sophisticated adversaries who constantly explore new ways to attack cyberinfrastructure. Recently, the use of deep learning-based intrusion detection systems has been on the rise. This rise is due to deep neural networks (DNN) complexity and efficiency in making anomaly detection activities more accurate. However, the complexity of these models makes them black-box models, as they lack explainability and interpretability. Not only is the DNN perceived as a black-box model, but recent research evidence has also shown that they are vulnerable to adversarial attacks. This paper developed an adversarial robust and explainable network intrusion detection system based on deep learning by applying adversarial training and implementing explainable AI techniques. In our experiments with the NSL-KDD dataset, the PGD adversarial-trained model was a more robust model than DeepFool adversarial-trained and FGSM adversarial-trained models, with a ROC-AUC of 0.87. The FGSM attack did not affect the PGD adversarial-trained model’s ROC-AUC, while the DeepFool attack caused a minimal 9.20% reduction in PGD adversarial-trained model’s ROC-AUC. PGD attack caused a 15.12% reduction in the DeepFool adversarial-trained model’s ROC-AUC and a 12.79% reduction in FGSM trained model’s ROC-AUC.

show abstract

“…The main security requisites in the IoT situation are availability, lightweight solution, authentication confidentiality, privacy integrity [5][6][7], and resource limitations [8,9]. It is shown in Figure 1.…”

Section: Coap Security Conceptsmentioning

confidence: 99%

Analysis and Validation of Lightweight Authentication Algorithm

Salankar¹,

Avasthi²,

Pasricha³

2022

ISI

View full text Add to dashboard Cite

The Constrained Application Protocol (CoAP) is extensively used in several industrial Internet of Things (IoT) applications. Using heavy-weight algorithms is not feasible in resource-constrained IoT environments, and lightweight solutions are vulnerable to security attacks. The trade-off between computing cost and security strength plays a significant role in deciding the right solution. Therefore, developing a lightweight security mechanism with a higher security level is paramount. Therefore, a lightweight authentication with Two-way Encryption for Secure Transmission in CoAP Protocol (LATEST) was proposed to achieve secure data transfer with a lightweight security mechanism. The proposed LATEST ensures high confidentiality and integrity against modification, impersonation, and replay attacks. Security analysis and validation tests are performed with the help of validation tools to measure the strength of the proposed LATEST mechanism. Testing and validation proved that the performance and security level improved significantly.

show abstract

A Semi-supervised Deep Auto-encoder Based Intrusion Detection for IoT

Cited by 12 publications

References 35 publications

Practical autoencoder based anomaly detection by using vector reconstruction error

Practical autoencoder based anomaly detection by using vector reconstruction error

Adversarial Robust and Explainable Network Intrusion Detection Systems Based on Deep Learning

Analysis and Validation of Lightweight Authentication Algorithm

Contact Info

Product

Resources

About