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 Experiment Video

Updated: May 5, 2026

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

1.3K

DIFC-Net: Diffusion-Intrinsic Feature Capture for AI-Generated Image Detection.

Shaofeng Lu1, Jin Tian1, Yujin Zhang1

  • 1School of Electric and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.

Sensors (Basel, Switzerland)
|May 4, 2026
PubMed
Summary

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

Research on Omnidirectional Gait Switching and Attitude Control in Hexapod Robots.

Biomimetics (Basel, Switzerland)·2024
Same author

Commodity Wi-Fi-Based Wireless Sensing Advancements over the Past Five Years.

Sensors (Basel, Switzerland)·2024
Same author

WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi.

Sensors (Basel, Switzerland)·2023
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 summary is machine-generated.

We developed DIFC-Net, a novel AI image detection method. It analyzes image reconstruction during diffusion inversion, achieving high accuracy on unseen generative models without needing specific training data.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Digital Forensics

Background:

  • Diffusion models generate highly realistic synthetic images, posing challenges for detection.
  • Existing methods often rely on visual artifacts, which are becoming less effective.

Purpose of the Study:

  • To propose DIFC-Net, a diffusion-intrinsic framework for detecting AI-generated images.
  • To overcome limitations of current synthetic image detection techniques.

Main Methods:

  • DIFC-Net analyzes image reconstruction behavior during diffusion inversion.
  • It captures spatial discrepancy signals and latent diffusion trajectory evolution.
  • Adaptive fusion creates a unified forensic representation.

Main Results:

Keywords:
diffusion model detectionimage forensic analysislatent diffusion inversionmultimodal feature fusionresidual discrepancysynthetic image authenticity

Related Experiment Videos

Last Updated: May 5, 2026

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

1.3K
  • DIFC-Net achieved 90.29% average AUC on unseen diffusion generators.
  • Outperformed state-of-the-art synthetic image detectors.
  • Demonstrated strong generalization capabilities.

Conclusions:

  • DIFC-Net offers a robust approach to synthetic image detection.
  • The diffusion-intrinsic method is effective across various generative models.
  • It provides reliable forensic analysis without model-specific training.