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: Jun 26, 2026

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

RNN-based detection of IoT malware using diverse feature engineering methods.

Mahmoud Khaled Abd-Ellah1, Nayera A Alsayed2, Osama M Elkomy3

  • 1Faculty of Artificial Intelligence, Egyptian Russian University, Cairo, 11829, Egypt. Mahmoud-khaled@eru.edu.eg.

Scientific Reports
|May 11, 2026
PubMed
Summary

Related Concept Videos

Rapid Identification of Pathogens01:25

Rapid Identification of Pathogens

MALDI-TOF MS has transformed clinical microbiology by offering a rapid and reliable method for pathogen identification. The traditional approach to microbial identification typically involves time-consuming culture techniques and biochemical tests, which can delay the initiation of appropriate antimicrobial therapy. MALDI-TOF MS avoids these delays by using characteristic ribosomal protein mass patterns of microbial cells, enabling accurate species-level identification within minutes.Principle...

You might also read

Related Articles

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

Sort by
Same author

Malware detection in IoT networks with CNNs and integrated feature engineering.

Scientific reports·2026
Same author

SFARP: a multi-layered real-time security framework for hybrid ARP and DDoS attack defense in SD-IoT networks.

Scientific reports·2025
Same author

A new hybrid model for improving outlier detection using combined autoencoder and variational autoencoder.

Scientific reports·2025
Same author

Deep learning and explainable AI for classification of potato leaf diseases.

Frontiers in artificial intelligence·2025
Same author

MT-nCov-Net: A Multitask Deep-Learning Framework for Efficient Diagnosis of COVID-19 Using Tomography Scans.

IEEE transactions on cybernetics·2021
Same author

Two-Stage Deep Learning Framework for Discrimination between COVID-19 and Community-Acquired Pneumonia from Chest CT scans.

Pattern recognition letters·2021

This study introduces a novel framework using recurrent neural networks (RNNs) and advanced feature engineering to improve malware detection in the Internet of Things (IoT). The approach significantly enhances security against sophisticated cyber threats in connected environments.

Area of Science:

  • Cybersecurity
  • Machine Learning
  • Network Security

Background:

  • The Internet of Things (IoT) is expanding rapidly, creating significant security vulnerabilities.
  • Sophisticated malware poses a challenge to traditional security methods in IoT environments.

Purpose of the Study:

  • To develop and evaluate a deep learning framework for enhanced malware detection in IoT.
  • To improve the accuracy and effectiveness of identifying malicious software targeting IoT devices.

Main Methods:

  • Utilized recurrent neural networks (RNNs) for malware detection.
  • Implemented advanced preprocessing and multilevel feature engineering (label encoding, MinMax scaling, TF-IDF, bag-of-words, word2vec, PCA).
  • Evaluated three RNN architectures on the UNSW-NB15 dataset using stratified fivefold cross-validation.
Keywords:
Deep learningFeature extractionIoT securityMalware detectionNetwork trafficRecurrent neural networks (RNNs)

Related Experiment Videos

Last Updated: Jun 26, 2026

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Main Results:

  • The proposed framework demonstrated progressively improved performance across multiple RNN architectures.
  • The final model achieved near-optimal classification results for accuracy, precision, recall, F1 score, specificity, and AUC.
  • The study highlights the effectiveness of combining deep learning with diverse feature engineering strategies.

Conclusions:

  • Deep learning techniques, particularly RNNs combined with comprehensive feature engineering, offer a powerful approach for IoT malware detection.
  • The developed framework is a scalable and validated solution for enhancing IoT security against evolving cyber threats.