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: Jun 4, 2026

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

A forensic evaluation method of stable diffusion-generated images using feature-based likelihood ratio by deep

Hao Luo1, Yunqi Tang1, Weizheng Jin1

  • 1School of Criminal Investigation, People's Public Security University of China, Beijing, China.

Journal of Forensic Sciences
|June 3, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Assessment of Diffusion and Perfusion01:17

Assessment of Diffusion and Perfusion

Understanding and evaluating diffusion and perfusion is critical in assessing a patient's respiratory and circulatory health. These processes play key roles in maintaining the body's internal environment, ensuring that tissues receive adequate oxygen while waste products are efficiently removed.
The Role of Diffusion in Respiration
Diffusion is the process by which molecules move from an area of higher concentration to an area of lower concentration. In the respiratory system, this principle...

You might also read

Related Articles

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

Sort by
Same author

GPR177 in A-fiber sensory neurons drives diabetic neuropathic pain via WNT-mediated TRPV1 activation.

Science translational medicine·2022
Same author

Lesion-attention pyramid network for diabetic retinopathy grading.

Artificial intelligence in medicine·2022
Same author

Development and Validation of a Nomogram to Predict Cancer-Specific Survival for Middle-Aged Patients With Early-Stage Hepatocellular Carcinoma.

Frontiers in public health·2022
Same author

Expanding the DNA-encoded library toolbox: identifying small molecules targeting RNA.

Nucleic acids research·2022
Same author

Depression duration and risk of incident cardiovascular disease: A population-based six-year cohort study.

Journal of affective disorders·2022
Same author

Adverse Events Reporting of Clinical Trials in Exercise Oncology Research (ADVANCE): Protocol for a Scoping Review.

Frontiers in oncology·2022
Same journal

Commentary on: Maskell PD, de Korompay A. Letter to the Editor-The transition point from zero-order to first order in blood alcohol elimination curves. Where is it? J Forensic Sci. 2025;70 (1):398-400. https://doi.org/10.1111/1556-4029.15650.

Journal of forensic sciences·2026
Same journal

A novel relationship between time offsets in capillary electrophoresis and DNA sequence variations in short tandem repeats.

Journal of forensic sciences·2026
Same journal

A 4-zone model to determine fentanyl overdose probability.

Journal of forensic sciences·2026
Same journal

Authors' response.

Journal of forensic sciences·2026
Same journal

Determining the utility of radio frequency identification (RFID) technology for disaster victim identification (DVI).

Journal of forensic sciences·2026
Same journal

Stakeholders' perspectives on integrating point-of-care diagnostics into forensic death investigations in South Africa.

Journal of forensic sciences·2026
See all related articles

Forensic experts can now better verify AI-generated images using a new deep learning model. This feature-based likelihood ratio approach enhances the accuracy of identifying images created by Stable Diffusion, improving judicial admissibility.

Area of Science:

  • Digital Forensics
  • Artificial Intelligence
  • Computer Vision

Background:

  • Increasing realism of AI-generated images poses challenges for forensic image authenticity verification.
  • Stable Diffusion and similar models create highly realistic synthetic images.
  • Need for robust methods to authenticate digital evidence in legal proceedings.

Purpose of the Study:

  • To propose a feature-based likelihood ratio model for identifying AI-generated images.
  • To enhance the judicial admissibility of forensic image authentication conclusions.
  • To assist forensic practitioners in distinguishing authentic from synthetic images.

Main Methods:

  • Trained a Swin-transformer algorithm on authentic (ImageNet) and Stable Diffusion v1.4 generated images.
Keywords:
deep learning featurefeature‐based likelihood ratioimage identificationstable diffusion

Related Experiment Videos

Last Updated: Jun 4, 2026

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

  • Mapped images to a feature space for classification based on feature values.
  • Constructed a feature likelihood ratio model using deep learning features.

    • Main Results:

    • Achieved 99.4% detection accuracy on a test set.
    • Evaluated the likelihood ratio model using Tippett plots, EER, Cllr, and ECE curves.
    • Demonstrated superior performance of the proposed deep learning-based feature likelihood ratio model.

    Conclusions:

    • The proposed feature-based likelihood ratio model effectively identifies Stable Diffusion-generated images.
    • Deep learning features provide a robust basis for forensic image authentication.
    • The method shows promise for improving the reliability of digital evidence in legal contexts.