Security and Communication Networks

Computational Technologies for Malicious Traffic Identification in IoT Networks


Publishing date
01 Oct 2022
Status
Published
Submission deadline
27 May 2022

Lead Editor

1The University of Lahore, Lahore, Pakistan

2University of Naples Parthenope, Naples, Italy

3Universitatea Stefan cel Mare din Suceava, Suceava, Romania


Computational Technologies for Malicious Traffic Identification in IoT Networks

Description

The fast-growing and widespread development of Internet of Things (IoT) applications offers new opportunities in multiple domains but also presents new challenges. An increasing number of IoT devices (sensors, actuators, etc.) have been deployed to collect critical data and to control environments such as manufacturing, healthcare, urban/built areas, and public safety. At the same time, machine learning (ML) has shown significant success in transforming heterogeneous and complex datasets into coherent outputs and actionable insights. Thus, the marriage of ML and IoT has a pivotal role in enabling smart environments with precision in decision-making and adaptive automation. Machine learning techniques have been effectively used in multiple applications in intelligent intrusion detection systems, including network traffic analysis, access logs analysis, spam, and malware detection. However, while current machine learning methods and their implementations are designed to handle tens of thousands of data, they have complexity issues with bigger datasets. Big Data analytics require new and enhanced models to handle complex problems such as network attack detection.

Identifying attack traffic is very important for the security of Internet of Things (IoT) in smart cities by using Machine Learning (ML) algorithms. Recently, the IoT security research community has endeavored to build anomaly, intrusion, and cyber-attack traffic identification models using Machine Learning algorithms for IoT security analysis. However, some critical and significant problems have not yet been studied in depth. One such problem is how to select an effective ML algorithm when there are a number of ML algorithms for a cyber-attack detection system for IoT security.

This Special Issue aims to provide state-of-the-art systems for malicious traffic identification in the Internet of things (IoT) network using machine learning (ML) techniques. The goal of the Special Issue is to collect contributions in the disciplines of IoT devices, computer science, engineering, machine learning, protocols, feature selection and traffic classification, and identification in IoT that extend the current state of the art with innovative ideas and solutions. Experimental and theoretical studies for IoT networks are encouraged. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

  • Internet of Things network traffic classification
  • Intelligent systems for security and privacy in IoT networks
  • IoT network traffic management using machine learning
  • Malicious IoT traffic identification using Machine Learning
  • QoE/QoS for IoT network management
  • Machine Learning algorithms for IoT traffic classification
  • Techniques for IoT device management
  • Authentication techniques for IoT based on Machine Learning
  • Real-time online IoT traffic classification system based on Machine Learning
  • IoT network security based on Machine Learning
  • Security strategy in IoT systems using Machine Learning techniques
  • Security and privacy techniques in IoT environments
  • Smart IoT device selection in IoT networks using Machine Learning techniques
  • Security-related classification and analytics
  • Blockchain-based security management for IoT applications
  • New concepts and architectures for IoT traffic management
  • Malicious behavior identification for IoT networks using Machine Learning techniques

Articles

  • Special Issue
  • - Volume 2024
  • - Article ID 9762430
  • - Retraction

Retracted: Secure and Energy-Efficient Computational Offloading Using LSTM in Mobile Edge Computing

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9872894
  • - Retraction

Retracted: Uncovering Resilient Actions of Robotic Technology with Data Interpretation Trajectories Using Knowledge Representation Procedures

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9861864
  • - Retraction

Retracted: Accurate Ranging Based on Transmission Line Channel Monitoring Image and Point Cloud Data Mapping

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9756350
  • - Retraction

Retracted: Construction of Real Estate Debt Crisis Early Warning Model Based on RBF Neural Network

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9869740
  • - Retraction

Retracted: Image Processing and Recognition Algorithm Design in Intelligent Imaging Device System

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9796151
  • - Retraction

Retracted: Multi-region Nonuniform Brightness Correction Algorithm Based on L-Channel Gamma Transform

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9784062
  • - Retraction

Retracted: Performance Evaluation Model of Short-Term Mutual Funds Based on Return-Variance-Liquidity

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9786595
  • - Retraction

Retracted: English Listening Prediction Strategy and Training Method with Data Mining

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9820548
  • - Retraction

Retracted: Sports Risk Analysis Based on Knowledge Discovery and Data Driven

Security and Communication Networks
  • Special Issue
  • - Volume 2023
  • - Article ID 9810961
  • - Retraction

Retracted: DDoS Attack Detection by Hybrid Deep Learning Methodologies

Security and Communication Networks
Security and Communication Networks
Publishing Collaboration
More info
Wiley Hindawi logo
 Journal metrics
See full report
Acceptance rate11%
Submission to final decision185 days
Acceptance to publication40 days
CiteScore2.600
Journal Citation Indicator-
Impact Factor-
 Submit Evaluate your manuscript with the free Manuscript Language Checker

We have begun to integrate the 200+ Hindawi journals into Wiley’s journal portfolio. You can find out more about how this benefits our journal communities on our FAQ.