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

Search research articles

Related Experiment Video

Updated: Jan 11, 2026

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

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

Published on: December 15, 2023

Securing IoT Vision Systems: An Unsupervised Framework for Adversarial Example Detection Integrating Spatial

Naile Wang¹, Jian Li¹, Chunhui Zhang¹

¹School of Cyberspace Security, Beijing University of Post and Telecommunications, Beijing 100876, China.

Sensors (Basel, Switzerland)

|November 13, 2025

Summary

This summary is machine-generated.

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

Family Functioning and Medication Self-Management in Rural Older Adults With Chronic Comorbidities: The Mediating Role of Self-Efficacy.

Journal of clinical nursing·2026

Same author

Targeted Isolation of Novel Calcium-Binding Peptides via Hydroxyapatite Affinity and Their Promotion Effect on Osteogenesis in MC3T3-E1 Cells.

Journal of food science·2026

Same author

The organelle-targeting duality of nanomaterials: physicochemical property-guided therapeutic effects and toxicological outcomes.

Biochemical pharmacology·2026

Same author

ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026

Same author

Covalent Modification of Keap1 by the Key Metabolic Cofactor Coenzyme A Under Oxidative and Metabolic Stress.

Antioxidants (Basel, Switzerland)·2026

Same author

Multiparticle entanglement of nuclear spins in silicon.

Nature communications·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

This study introduces an unsupervised method to detect adversarial attacks on deep learning models in IoT systems. The approach effectively identifies sophisticated Generative Adversarial Network (AdvGAN) attacks and generalizes to other attack types, enhancing IoT security.

Area of Science:

Artificial Intelligence
Computer Vision
Cybersecurity

Background:

Deep learning models in Internet of Things (IoT) systems face significant threats from adversarial attacks.
Generative Adversarial Networks (AdvGANs) pose a particular challenge for detecting adversarial examples.

Purpose of the Study:

To propose an unsupervised detection method for adversarial examples generated by AdvGANs.
To enhance the robustness of IoT systems against sophisticated cyber threats.

Main Methods:

A dual-module architecture integrating spatial statistical features and multidimensional distribution characteristics was designed.
Module A extracted spatial statistics and calculated category prototype similarity.
Module B extracted multidimensional statistical features and used Mahalanobis distance for anomaly detection.

Keywords:

IoT security Mahalanobis distance adversarial example detection spatial statistics unsupervised detection

Related Experiment Videos

Last Updated: Jan 11, 2026

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

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

Published on: December 15, 2023

Main Results:

The method achieved high Area Under the Receiver Operating Characteristic Curve (AUROC) scores (up to 0.9937 on ResNet50 and 0.9753 on VGG16) for AdvGAN detection.
AUROC scores exceeded 0.95 against traditional attacks (FGSM, PGD), demonstrating cross-attack generalization.
Cross-dataset evaluation on Fashion-MNIST confirmed robust generalization across data domains.

Conclusions:

The proposed unsupervised method effectively detects AdvGAN attacks without requiring adversarial training samples.
This approach offers a versatile solution for enhancing the security of IoT systems in critical applications.
The findings underscore the potential for improved IoT system robustness against diverse adversarial threats.