Search research articles

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

Related Concept Videos

Neural Circuits

Neural Circuits

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...

Neural Regulation

Neural Regulation

Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.

You might also read

Related Articles

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

Sort by

Same author

Organic base-promoted formal [4+1] cycloaddition of vinylethylene carbonates with elemental sulfur for facile access to thiophenones.

Chemical communications (Cambridge, England)·2026

Same author

Trend-Conditioned Residual Learning for Early Fault Warning in Nonstationary Multi-Sensor Oil Monitoring.

Sensors (Basel, Switzerland)·2026

Same author

Multi-Modal Iterative Refinement Network with K-space Posterior Correction for MRI reconstruction.

Magnetic resonance imaging·2026

Same author

Theaflavin-3,3'-digallate improves porcine oocyte maturation and independently enhances embryo development in vitro via modulating redox homeostasis and lipid-associated metabolism.

Reproductive biology·2026

Same author

The clinical efficacy of Astragalus-containing Chinese patent medicines in the effective treatment of heart failure: A systematic review and network meta-analysis.

Medicine·2026

Same author

A multicenter retrospective study comparing the therapeutic effects and relapse rates of secukinumab on plaque psoriasis of varying severity.

Journal of the American Academy of Dermatology·2026

Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 4, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Explanatory subgraph attacks against Graph Neural Networks.

Huiwei Wang¹, Tianhua Liu², Ziyu Sheng³

¹College of Electronic and Information Engineering, Southwest University, Chongqing, 400715, China; The Key Laboratory of Networks and Cloud Computing Security of Universities in Chongqing, Chongqing, 400715, China.

Neural Networks : the Official Journal of the International Neural Network Society

|January 29, 2024

Summary

This summary is machine-generated.

Explanation methods for Graph Neural Networks (GNNs) can be exploited for attacks. This study demonstrates how explanatory subgraphs can be used for evasion and backdoor attacks against GNN models.

Keywords:

Adversarial attacks Backdoor attacks Explainability Graph Neural Networks

More Related Videos

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Brain Mapping Using a Graphene Electrode Array

Brain Mapping Using a Graphene Electrode Array

Published on: October 20, 2023

Related Experiment Videos

Last Updated: Jul 4, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Brain Mapping Using a Graphene Electrode Array

Brain Mapping Using a Graphene Electrode Array

Published on: October 20, 2023

Area of Science:

Artificial Intelligence
Machine Learning
Graph Neural Networks

Background:

Graph Neural Networks (GNNs) lack transparency, hindering critical applications.
Existing GNN explanation methods provide insights but may introduce security vulnerabilities.
Interpretability in GNNs is crucial for trust and security.

Purpose of the Study:

To investigate the security risks associated with GNN explanation methods.
To propose novel evasion and backdoor attack strategies leveraging explanatory subgraphs.
To evaluate the effectiveness and characteristics of these attacks.

Main Methods:

Utilized SubgraphX, a GNN explanation method, to obtain local explanatory subgraphs.
Developed evasion attacks by replacing explanatory subgraphs to induce misclassification.
Designed backdoor attacks using explanatory triggers and strategic injection points.

Main Results:

Demonstrated the effectiveness of proposed evasion and backdoor attacks against state-of-the-art GNN models.
Validated attacks across various datasets.
Showcased the enhanced efficiency, adaptability, and concealment of the proposed backdoor attack.

Conclusions:

GNN explanation methods, while aiding interpretability, can be weaponized.
Exploiting explanatory subgraphs presents a viable attack vector for GNNs.
The proposed attacks highlight the need for robust security measures in interpretable GNNs.