Examining the Suitability of NetFlow Features in Detecting IoT Network Intrusions

Awad, Mohammed; Fraihat, Salam; Salameh, Khouloud; Redhaei, Aneesa Al

doi:10.3390/s22166164

Cited by 19 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 9 and Fig. 5 compares the precision conventional 41 and proposed security methodologies by using Netflow-BoT-IoT-v2 dataset. Typically, precision is the metric that assesses a performance of the model by determining how frequently the model's forecast is accurate when it correctly foresees an occurrence.…”

Section: Resultsmentioning

confidence: 99%

A novel IoT intrusion detection framework using Decisive Red Fox optimization and descriptive back propagated radial basis function models

Rabie,

Selvarajan,

Hasanin

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The Internet of Things (IoT) is extensively used in modern-day life, such as in smart homes, intelligent transportation, etc. However, the present security measures cannot fully protect the IoT due to its vulnerability to malicious assaults. Intrusion detection can protect IoT devices from the most harmful attacks as a security tool. Nevertheless, the time and detection efficiencies of conventional intrusion detection methods need to be more accurate. The main contribution of this paper is to develop a simple as well as intelligent security framework for protecting IoT from cyber-attacks. For this purpose, a combination of Decisive Red Fox (DRF) Optimization and Descriptive Back Propagated Radial Basis Function (DBRF) classification are developed in the proposed work. The novelty of this work is, a recently developed DRF optimization methodology incorporated with the machine learning algorithm is utilized for maximizing the security level of IoT systems. First, the data preprocessing and normalization operations are performed to generate the balanced IoT dataset for improving the detection accuracy of classification. Then, the DRF optimization algorithm is applied to optimally tune the features required for accurate intrusion detection and classification. It also supports increasing the training speed and reducing the error rate of the classifier. Moreover, the DBRF classification model is deployed to categorize the normal and attacking data flows using optimized features. Here, the proposed DRF-DBRF security model's performance is validated and tested using five different and popular IoT benchmarking datasets. Finally, the results are compared with the previous anomaly detection approaches by using various evaluation parameters.

show abstract

Section: Resultsmentioning

confidence: 99%

A novel IoT intrusion detection framework using Decisive Red Fox optimization and descriptive back propagated radial basis function models

Rabie,

Selvarajan,

Hasanin

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Flow-based detection (ref. [11,15]) has numerous advantages. It focuses explicitly on analyzing IP stream records, which provide aggregated information about packet headers and summarize network traffic as IP streams.…”

Section: Related Workmentioning

confidence: 99%

“…These methods mainly consist of traffic-based detection (ref. [11][12][13][14][15]) and graph-based detection (ref. [16][17][18][19][20]).…”

Section: Introductionmentioning

confidence: 99%

Research on Virus Propagation Network Intrusion Detection Based on Graph Neural Network

Ying,

Pan,

Chen

et al. 2024

Mathematics

View full text Add to dashboard Cite

The field of network security is highly concerned with intrusion detection, which safeguards the security of computer networks. The invention and application of intrusion detection technology play indispensable roles in network security, and it is crucial to investigate and comprehend this topic. Recently, with the continuous occurrence of intrusion incidents in virus propagation networks, traditional network detection algorithms for virus propagation have encountered limitations and have struggled to detect these incidents effectively and accurately. Therefore, updating the intrusion detection algorithm of the virus-spreading network is imperative. This paper introduces a novel system for virus propagation, whose core is a graph-based neural network. By organically combining two modules—a standardization module and a computation module—this system forms a powerful GNN model. The standardization module uses two methods, while the calculation module uses three methods. Through permutation and combination, we obtain six GNN models with different characteristics. To verify their performance, we conducted experiments on the selected datasets. The experimental results show that the proposed algorithm has excellent capabilities, high accuracy, reasonable complexity, and excellent stability in the intrusion detection of virus-spreading networks, making the network more secure and reliable.

show abstract

“…Anomaly detection is a crucial procedure in protecting networked systems as it allows for the identification of unusual or abnormal behavior within a network of connected devices. This is particularly important in the context of the IoT, where the sheer volume of data generated by vulnerable devices can make it difficult to identify and respond to potential security threats [8,9].…”

Section: Introductionmentioning

confidence: 99%

Enhancing IoT Security: Optimizing Anomaly Detection through Machine Learning

Balega,

Farag,

et al. 2024

Electronics

View full text Add to dashboard Cite

As the Internet of Things (IoT) continues to evolve, securing IoT networks and devices remains a continuing challenge. Anomaly detection is a crucial procedure in protecting the IoT. A promising way to perform anomaly detection in the IoT is through the use of machine learning (ML) algorithms. There is a lack of studies in the literature identifying optimal (with regard to both effectiveness and efficiency) anomaly detection models for the IoT. To fill the gap, this work thoroughly investigated the effectiveness and efficiency of IoT anomaly detection enabled by several representative machine learning models, namely Extreme Gradient Boosting (XGBoost), Support Vector Machines (SVMs), and Deep Convolutional Neural Networks (DCNNs). Identifying optimal anomaly detection models for IoT anomaly detection is challenging due to diverse IoT applications and dynamic IoT networking environments. It is of vital importance to evaluate ML-powered anomaly detection models using multiple datasets collected from different environments. We utilized three reputable datasets to benchmark the aforementioned machine learning methods, namely, IoT-23, NSL-KDD, and TON_IoT. Our results show that XGBoost outperformed both the SVM and DCNN, achieving accuracies of up to 99.98%. Moreover, XGBoost proved to be the most computationally efficient method; the model performed 717.75 times faster than the SVM and significantly faster than the DCNN in terms of training times. The research results have been further confirmed by using our real-world IoT data collected from an IoT testbed consisting of physical devices that we recently built.

show abstract

Examining the Suitability of NetFlow Features in Detecting IoT Network Intrusions

Cited by 19 publications

References 24 publications

A novel IoT intrusion detection framework using Decisive Red Fox optimization and descriptive back propagated radial basis function models

A novel IoT intrusion detection framework using Decisive Red Fox optimization and descriptive back propagated radial basis function models

Research on Virus Propagation Network Intrusion Detection Based on Graph Neural Network

Enhancing IoT Security: Optimizing Anomaly Detection through Machine Learning

Contact Info

Product

Resources

About