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

Vector Algebra: Graphical Method01:10

Vector Algebra: Graphical Method

12.1K
Vectors can be multiplied by scalars, added to other vectors, or subtracted from other vectors. The vector sum of two (or more) vectors is called the resultant vector or, for short, the resultant.
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
12.1K
Neural Circuits01:25

Neural Circuits

1.2K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.2K
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

100
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
100
Network Function of a Circuit01:25

Network Function of a Circuit

286
Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
286
Ogive Graph01:07

Ogive Graph

5.6K
An ogive graph is sometimes called a cumulative frequency polygon. It is one type of frequency polygon that shows cumulative frequency. In other words, the cumulative percentages are added to the graph from left to right. An ogive graph plots cumulative frequency on the vertical y-axis and class boundaries along the horizontal x-axis. It’s very similar to a histogram; only instead of rectangles, an ogive displays a single point where the top right of the rectangle would be. Creating this...
5.6K
Reducing Line Loss01:18

Reducing Line Loss

151
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
151

You might also read

Related Articles

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

Sort by
Same author

Not All, but the Right Ones: Energy-Guided Representation Learning for Incomplete Multiview Clustering.

IEEE transactions on neural networks and learning systems·2026
Same author

Structure-property relationships of pyrrolopyrrole Aza-BODIPYs: Substituent effects on NIR absorption and photosensitization.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Understanding county-level mental health determinants to guide community prevention efforts.

Proceedings (Baylor University. Medical Center)·2026
Same author

Thermal-Driven Diode Polarity Switching From Competing Helical Superconducting States in WTe<sub>2</sub>/α-Fe<sub>2</sub>O<sub>3</sub> Heterostructures.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Decomposition-based interval multi-objective evolutionary algorithm for patrol robot path planning in chemical plants.

Scientific reports·2026
Same author

Acoustoelectric control of optoelectronic anisotropy for reconfigurable polarimetry.

Science advances·2026
Same journal

Fourier multi-component and multi-layer neural networks: Unlocking high-frequency potential.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dual-channel hard negative sample generation for graph contrastive learning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DMWFuse: A degradation-adaptive unified framework for RGB-IR image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

LLM-Driven Regime-Adaptive strategy synthesis for Polymorphic Network routing.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

ES-DETR: Real-time detection transformer with encover and soft-dropout.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

MDFAT: Interactive mask decoupling and frequency-adaptive transformer for multi-focus image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles
  1. Home
  3. A Dual Robust Graph Neural Network Against Graph Adversarial Attacks.
  1. Home
  3. A Dual Robust Graph Neural Network Against Graph Adversarial Attacks.

Related Experiment Video

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

529

A Dual Robust Graph Neural Network Against Graph Adversarial Attacks.

Qian Tao1, Jianpeng Liao2, Enze Zhang2

  • 1School of Software, South China University of Technology, Guangzhou, Guangdong, 510006, China; Pazhou Lab, Guangzhou, Guangdong, 510006, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 10, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

Graph Neural Networks (GNNs) are vulnerable to adversarial attacks. We introduce DualRGNN, a novel model that refines graph structure and identifies adversarial edges, significantly enhancing GNN robustness against attacks.

Keywords:
Dual robustnessGraph adversarial attacksGraph attention networkGraph neural network

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.1K
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

550

Related Experiment Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

529
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.1K
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

550

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Graph Neural Networks

Background:

  • Graph Neural Networks (GNNs) are widely used but vulnerable to adversarial attacks that modify graph structures.
  • These vulnerabilities pose security and privacy risks, necessitating robust GNN models.
  • Existing graph remodeling methods struggle to preserve node similarity and lack supervision for detecting adversarial perturbations.

Purpose of the Study:

  • To develop a robust Graph Neural Network (GNN) model that effectively defends against graph adversarial attacks.
  • To address limitations in existing methods regarding node similarity preservation and adversarial edge recognition.

Main Methods:

  • Proposed a novel Dual Robust Graph Neural Network (DualRGNN) architecture.
  • Incorporated a node-similarity-preserving graph refining (SPGR) module to prune and refine graph structures.
  • Employed an adversarial-supervised graph attention (ASGAT) network to identify adversarial edges using supervised signals.

    • Main Results:

    • DualRGNN demonstrated remarkable robustness against various graph adversarial attacks in experiments.
    • The SPGR module effectively weakened the impact of adversarial perturbations by preserving node similarity.
    • The ASGAT network enhanced the model's ability to recognize and mitigate adversarial edges.

    Conclusions:

    • DualRGNN offers a significant advancement in defending GNNs against adversarial attacks.
    • The proposed approach effectively enhances GNN robustness by preserving node relationships and identifying malicious graph modifications.
    • This work contributes to more secure and reliable applications of GNNs in real-world scenarios.