Search research articles

Search research articles

Related Experiment Video

Updated: Jul 5, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

CyberDetect MLP a big data enabled optimized deep learning framework for scalable cyberattack detection in IoT

Talluri Upender¹, M Neelakantappa², C Prakasa Rao³

¹Department of Computer Science and Engineering, CMR College of Engineering & Technology, Hyderabad, Telangana, India. talluri.upender@gmail.com.

Scientific Reports

|November 19, 2025

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

Comment on "explainable electronic medical record-based machine learning to predict 1-year incident protein-energy wasting in non-dialysis chronic kidney disease: A single-center development study".

Clinical nutrition ESPEN·2026

Same author

SLA aware deep reinforcement learning for adaptive EdgeCloud task scheduling.

Scientific reports·2026

Same author

BugPrioritizeAI for multimodal test case prioritisation using bug reports, code changes, and test metadata.

Scientific reports·2025

Same author

Enhanced effective convolutional attention network with squeeze-and-excitation inception module for multi-label clinical document classification.

Scientific reports·2025

Same author

Intelligent wearable-assisted digital healthcare industry 5.0.

Artificial intelligence in medicine·2024

Same author

AI and Blockchain-Based Secure Data Dissemination Architecture for IoT-Enabled Critical Infrastructure.

Sensors (Basel, Switzerland)·2023

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

CyberDetect-MLP offers a scalable, explainable deep learning framework for detecting Internet of Things (IoT) cyberattacks. It achieves high accuracy, addressing limitations of traditional systems in big data environments.

Area of Science:

Cybersecurity
Machine Learning
Big Data Analytics

Background:

The proliferation of Internet of Things (IoT) ecosystems generates vast, multidimensional data, creating significant attack surfaces for cyber threats.
Traditional intrusion detection systems (IDS) and many machine learning (ML) models struggle with scalability, interpretability, and high-dimensional data streams, limiting their effectiveness in large-scale IoT applications.

Purpose of the Study:

To propose CyberDetect-MLP, a scalable, explainable, big data-enabled, and optimized deep learning framework for IoT cyberattack detection.
To address the limitations of existing IDS and ML models in handling the complexities of IoT security.

Main Methods:

Utilized Apache Spark for distributed data ingestion and preprocessing.
Implemented Mutual Information-based feature selection.

Keywords:

Big data analytics Cyberattack detection Deep learning Intrusion detection system IoT security

Related Experiment Videos

Last Updated: Jul 5, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Employed a multi-layer perceptron (MLP) with batch normalization, dropout, and cosine annealing scheduling.

Integrated an optional explainable AI (XAI) module using Grad-CAM and SHAP for transparency.

Main Results:

CyberDetect-MLP achieved 98.87% accuracy and 99.10% ROC-AUC on the TON_IoT dataset, outperforming baseline models like Random Forest, XGBoost, and vanilla MLP.
Ablation studies and explainability evaluations confirmed the framework's robustness and trustworthiness.

Conclusions:

The proposed CyberDetect-MLP framework effectively bridges the gap between big data analytics and interpretable deep learning for cybersecurity.
It provides an end-to-end IDS solution suitable for real-time applications in smart cities, industrial IoT, and critical infrastructure.
The framework's public availability promotes reproducibility and transparency in IoT security research.