Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 17, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.5K

Real-time detection of Wi-Fi attacks using hybrid deep learning models on NodeMCU.

Mohamed Hussien Moharam1, Kareem Ashraf2, Hussien Alaa2

  • 1Department of Electronics and Communications Engineering, Misr University for Science and Technology, P.O. Box 23546, Sixth of October, Giza, Egypt. Mohamed.moharem@must.edu.eg.

Scientific Reports
|September 15, 2025
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Structural design and cytotoxic profiling of a novel 1,3,4-thiadiazole derivative targeting MCF-7 and HCT-116 cell lines: synthesis, cytotoxicity, and <i>in silico</i> study.

RSC advances·2026
Same author

Gateway: patient olfactory neurons for large-scale discovery in neurodegenerative disease.

bioRxiv : the preprint server for biology·2026
Same author

DC bias optimization in intelligent DCO-OFDM Li-Fi systems using hybrid machine learning with hardware validation.

Scientific reports·2026
Same author

Correction: Rapid point-of-care detection of vitamin D deficiency using disposable electrochemical immunosensors based on a La<sub>2</sub>O<sub>3</sub>-WO<sub>3</sub>@CNT Bi-metal oxide nanocomposite.

Analytical methods : advancing methods and applications·2026
Same author

Rapid point-of-care detection of vitamin D deficiency using disposable electrochemical immunosensors based on a La<sub>2</sub>O<sub>3</sub>-WO<sub>3</sub>@CNT Bi-metal oxide nanocomposite.

Analytical methods : advancing methods and applications·2026
Same author

Impact of COVID-19 vaccination and vaccine type on morbidity and mortality in hospitalized patients: a retrospective cohort study in Egypt.

Frontiers in microbiology·2026

This study introduces a real-time Wi-Fi deauthentication attack detection system for IoT using NodeMCU. The hybrid GRU-LR model achieved 96% accuracy, offering a practical, explainable intrusion detection solution.

Area of Science:

  • Cybersecurity
  • Wireless Networking
  • Machine Learning

Background:

  • Wi-Fi deauthentication attacks pose a significant threat to network security, particularly in IoT environments.
  • Existing intrusion detection systems often rely on cloud-based processing or non-interpretable models, limiting their applicability in low-power settings.

Purpose of the Study:

  • To develop a real-time, lightweight system for detecting Wi-Fi deauthentication attacks using an embedded microcontroller.
  • To integrate hybrid temporal deep learning models with interpretable classification for enhanced threat detection.

Main Methods:

  • Utilized NodeMCU ESP8266 for live Wi-Fi packet sniffing and feature extraction (RSSI, DA, packet count, SNR).
  • Implemented and compared hybrid models: Long Short-term Memory (LSTM)-Logistic Regression (LR), Gate Recurrent Unit (GRU)-LR, and Recurrent Neural Network (RNN)-LR.
Keywords:
Deauthentication attacksDeep learningEdge computingGRU_LRHybrid AI modelsLSTM_LRMachine learningNetwork anomaly detectionNodeMCUOLED displayRNN_LRRSSIReal-time securityTemporal pattern recognitionWi-Fi monitoring

Related Experiment Videos

Last Updated: Jan 17, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.5K
  • Trained and validated models on a dataset of over 5,600 labeled samples under varied network conditions.

    • Main Results:

    • The GRU-LR hybrid model achieved the highest detection accuracy at 96%.
    • The system demonstrated superior performance in identifying minority-class threats.
    • Real-time monitoring of Wi-Fi traffic and key metrics was achieved on an OLED screen.

    Conclusions:

    • The proposed framework offers a practical and transparent intrusion detection approach by combining explainable AI with cost-effective embedded sensing.
    • This system addresses a gap in intrusion detection research, providing a readily adaptable solution for diverse IoT and wireless security contexts.