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 Concept Videos

Strategies for Assessing and Addressing Confounding01:25

Strategies for Assessing and Addressing Confounding

356
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
356
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

238
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
238
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

282
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
282
Fast Decoupled and DC Powerflow01:24

Fast Decoupled and DC Powerflow

724
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
724

You might also read

Related Articles

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

Sort by
Same author

Efficient and Accurate Zero-Day Electricity Theft Detection from Smart Meter Sensor Data Using Prototype and Ensemble Learning.

Sensors (Basel, Switzerland)·2025
Same author

CANGuard: An Enhanced Approach to the Detection of Anomalies in CAN-Enabled Vehicles.

Sensors (Basel, Switzerland)·2025
Same author

Privacy-Preserving Detection of Tampered Radio-Frequency Transmissions Utilizing Federated Learning in LoRa Networks.

Sensors (Basel, Switzerland)·2024
Same author

Identifying Tampered Radio-Frequency Transmissions in LoRa Networks Using Machine Learning.

Sensors (Basel, Switzerland)·2024
Same author

Deep Anomaly Detection Framework Utilizing Federated Learning for Electricity Theft Zero-Day Cyberattacks.

Sensors (Basel, Switzerland)·2024
Same author

Detection of Malicious Threats Exploiting Clock-Gating Hardware Using Machine Learning.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jan 13, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

FedECPA: An Efficient Countermeasure Against Scaling-Based Model Poisoning Attacks in Blockchain-Based Federated

Rukayat Olapojoye1, Tara Salman1, Mohamed Baza2

  • 1Department of Computer Science, Texas Tech University, Lubbock, TX 79409, USA.

Sensors (Basel, Switzerland)
|October 29, 2025
PubMed
Summary

Blockchain-based federated learning (BFL) is vulnerable to scaling attacks. This study introduces FedECPA, an efficient defense mechanism that protects BFL models from these attacks, maintaining high accuracy.

Keywords:
FedECPAIoTblockchainfederated learningscaling-based model poisoning attacksecuritysmart contract

Related Experiment Videos

Last Updated: Jan 13, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Blockchain Technology
  • Internet of Things

Background:

  • Federated learning (FL) enables distributed machine learning (ML) on Internet of Things (IoT) data while preserving privacy.
  • Blockchain-based federated learning (BFL) enhances FL with decentralization but introduces new vulnerabilities, particularly model poisoning attacks.
  • Scaling-based model poisoning attacks pose a significant threat to the integrity of BFL systems.

Purpose of the Study:

  • To investigate the vulnerabilities of BFL systems to scaling-based model poisoning attacks.
  • To propose and evaluate FedECPA, an efficient countermeasure against these attacks in BFL.
  • To demonstrate the effectiveness of FedECPA compared to existing defense mechanisms.

Main Methods:

  • Analysis of scaling-based model poisoning attack vectors in BFL environments.
  • Development of FedECPA, an extension of the FedAvg algorithm incorporating outlier client detection.
  • Experimental evaluation using MNIST and CIFAR-10 datasets under various attack scenarios and data distributions (IID and non-IID).
  • Comparison of FedECPA's performance against the Multikrum defense mechanism.

Main Results:

  • BFL systems are susceptible to scaling-based model poisoning attacks, degrading model performance.
  • FedECPA effectively identifies and filters out clients contributing to poisoning attacks.
  • FedECPA significantly outperforms the baseline and Multikrum, achieving 98% accuracy on MNIST (IID) and 89% (non-IID), outperforming the baseline by 4% and 38% respectively.
  • Similar performance gains were observed on the CIFAR-10 dataset.

Conclusions:

  • FedECPA provides a robust defense against scaling-based model poisoning attacks in BFL.
  • The proposed method enhances the security and reliability of decentralized federated learning systems.
  • FedECPA offers a practical solution for deploying secure and accurate BFL applications.