Wireless Local Area Networks Threat Detection Using 1D-CNN

Natkaniec, Marek; Bednarz, Marcin

doi:10.3390/s23125507

Cited by 9 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross-entropy is used in combination with Softmax to process the output, such that the sum of the probabilities of multiple classification predictions is 1. Cross-entropy is then used to calculate the loss, and the smaller the value of cross-entropy, the better the performance of the classification model [ 26 ].…”

Section: Methodsmentioning

confidence: 99%

“…The convolutional layer and the pooling layer can be set alternately. The convolutional layer consists of multiple feature maps, and each feature map consists of multiple neurons, each of which is connected to a local region of the previous layer through a convolutional kernel [ 26 ]. In this study, the sequences of enterprise quality labels are stitched with quality-service transaction behaviors, the sequence data of quality features are input, and one-dimensional convolutional neural network (1D-CNN) is used for enterprise quality-service demand prediction.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

An Enterprise Service Demand Classification Method Based on One-Dimensional Convolutional Neural Network with Cross-Entropy Loss and Enterprise Portrait

Zhou

Chen

2023

Entropy

View full text Add to dashboard Cite

To address the diverse needs of enterprise users and the cold-start issue of recommendation system, this paper proposes a quality-service demand classification method—1D-CNN-CrossEntorpyLoss, based on cross-entropy loss and one-dimensional convolutional neural network (1D-CNN) with the comprehensive enterprise quality portrait labels. The main idea of 1D-CNN-CrossEntorpyLoss is to use cross-entropy to minimize the loss of 1D-CNN model and enhance the performance of the enterprise quality-service demand classification. The transaction data of the enterprise quality-service platform are selected as the data source. Finally, the performance of 1D-CNN-CrossEntorpyLoss is compared with XGBoost, SVM, and logistic regression models. From the experimental results, it can be found that 1D-CNN-CrossEntorpyLoss has the best classification results with an accuracy of 72.44%. In addition, compared to the results without the enterprise-quality portrait, the enterprise-quality portrait improves the accuracy and recall of 1D-CNN-CrossEntorpyLoss model. It is also verified that the enterprise-quality portrait can further improve the classification ability of enterprise quality-service demand, and 1D-CNN-CrossEntorpyLoss is better than other classification methods, which can improve the precision service of the comprehensive quality service platform for MSMEs.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

An Enterprise Service Demand Classification Method Based on One-Dimensional Convolutional Neural Network with Cross-Entropy Loss and Enterprise Portrait

Zhou

Chen

2023

Entropy

View full text Add to dashboard Cite

show abstract

“…This information can be processed by anyone with a device capable of collecting WLAN traffic, potentially without the user's consent, and based on the user location pattern, third parties might use the information for various purposes, such as creating a user profile [3,4]. Wi-Fi networks are susceptible to various security threats, including unauthorized access, data interception, network spoofing, and malicious attacks targeting vulnerabilities in routers, bridges and client devices [5,6]. To conceal the device identity and enhance user privacy, modern Wi-Fi devices use disposable random MAC during the scanning process [7].…”

Section: Introductionmentioning

confidence: 99%

A Novel Covert Channel for IEEE 802.11 Networks Utilizing MAC Address Randomization

Teca,

Natkaniec

2023

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Vendors implement the MAC address randomization technique to prevent IEEE 802.11 client station devices from being tracked. Although it conceals device identity, it cannot hide its occurring data transmission. This paper presents a novel covert channel that leverages the MAC address randomization technique to create a covert channel to hide data transmission inside IEEE 802.11 networks. The secret data are a disposable random MAC address generated by the IEEE 802.11 station as part of the probe request frame while scanning the network. The paper presents the concept of the covert channel, its implementation, and performance metrics. The study covers diverse scenarios, including the adaptation of the modified Selective Repeat ARQ protocol to alleviate the impact of the number of client stations and their offered loads on the covert channel. The results show that with the appropriate parameter selections, we can adapt the covert channel to produce excellent throughput, efficiency, delay, and jitter according to the environment in which it is installed.

show abstract

“…The use of one-dimensional convolutional neural networks (1D-CNN) for threat detection in wireless local area networks was suggested by Natkaniec & Bednarz (2023). They suggested building and deploying a machine learning system that could identify different network risks at the IEEE 802.11 wireless network's MAC layer by analyzing traffic patterns.…”

Section: Wpa3-enterprisementioning

confidence: 99%

New Trends in Computer Sciences

View full text Add to dashboard Cite

Agriculture plays a crucial role in driving economic growth worldwide. With the continuous growth of the global population, the need for food production and labor has become increasingly demanding. However, agriculture faces various challenges throughout the entire process, from planting to harvesting. Key obstacles include inadequate chemical application, pest and disease infestation, improper irrigation, and drainage, weed control, and yield forecasting. These challenges have sparked discussions and concerns about automating agricultural practices. The advent of artificial intelligence (AI) has brought about significant changes in the field of agriculture. This transformative technology offers solutions to safeguard agricultural production against threats such as population growth, climate change, labor disputes, and food security concerns. By harnessing sensors and incorporating them into robots and drones, AI can assist with irrigation, crop monitoring and other vital agricultural tasks. This not only improves worker safety but also mitigates the impact on natural ecosystems, enabling the maintenance of affordable food prices while ensuring increased food production to meet the needs of our expanding global population. This proposed study is designed to highlight the paradigm shift taking place in agriculture, placing a strong emphasis on the integration of AI-driven robots and drones in cultivation, irrigation and crop monitoring. It underscores the tremendous potential of these evolving technologies to address the global challenges associated with feeding a growing population while simultaneously promoting sustainable farming practices. By leveraging AI, robotic farming offers a promising future where agricultural processes are more efficient, productive, and environmentally friendly.

show abstract

Wireless Local Area Networks Threat Detection Using 1D-CNN

Cited by 9 publications

References 43 publications

An Enterprise Service Demand Classification Method Based on One-Dimensional Convolutional Neural Network with Cross-Entropy Loss and Enterprise Portrait

An Enterprise Service Demand Classification Method Based on One-Dimensional Convolutional Neural Network with Cross-Entropy Loss and Enterprise Portrait

A Novel Covert Channel for IEEE 802.11 Networks Utilizing MAC Address Randomization

New Trends in Computer Sciences

Contact Info

Product

Resources

About