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

You might also read

Related Articles

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

Sort by
Same author

N-Acetylcysteine protects the developing brain in neonatal sepsis-like inflammation via a redox-neurovascular pathway.

Journal of neuroinflammation·2026
Same author

Warehouse Fire Detection System Based on Multi-Sensor Information Fusion.

Sensors (Basel, Switzerland)·2026
Same author

HS-QFNet: Deep learning-enhanced hyperspectral fluorescence correction for accurate <i>in vivo</i> photosensitizer concentration quantification.

iScience·2026
Same author

Clinical Study of Ultrasound-Guided Modified Percutaneous Endoscopic Interlaminar Discectomy Combined With Medical Chitosan in Lumbar 4-5 Disc Herniation Treatment.

Orthopaedic surgery·2026
Same author

Time in target systolic blood pressure range and cardiometabolic disease-free life expectancy in hypertensive elderly.

American journal of preventive cardiology·2026
Same author

Genetic characteristics and agronomic traits in leafy head Chinese cabbage breeding.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Jan 17, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.6K

Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective.

Nan Zhong, Mian Zou, Yiran Xu

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |January 14, 2026
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel self-supervised method for AI-generated image detection using camera metadata. The approach leverages Exchangeable Image File Format (EXIF) tags to improve cross-model applicability and robustness in multimedia forensics.

    More Related Videos

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
    06:37

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

    Published on: December 15, 2023

    5.3K
    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

    1.0K

    Related Experiment Videos

    Last Updated: Jan 17, 2026

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    9.6K
    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
    06:37

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

    Published on: December 15, 2023

    5.3K
    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

    1.0K

    Area of Science:

    • Multimedia Forensics
    • Computer Vision
    • Artificial Intelligence

    Background:

    • AI-generated imagery presents significant challenges for digital forensics.
    • Existing AI image detectors often lack cross-model generalizability due to reliance on specific generative model assumptions.

    Purpose of the Study:

    • To develop a robust and generalizable method for detecting AI-generated images.
    • To overcome the limitations of current detectors by not relying on generative model specifics.

    Main Methods:

    • A self-supervised learning approach utilizing Exchangeable Image File Format (EXIF) tags from digital photographs.
    • A pretext task involving classification and ranking of EXIF tags to train a feature extractor.
    • One-class and binary detection models employing EXIF-induced features and high-frequency residuals.

    Main Results:

    • The proposed EXIF-induced detectors significantly outperform existing methods.
    • Demonstrated strong generalization capabilities across diverse generative models and in-the-wild samples.
    • Exhibited robustness against common image perturbations.

    Conclusions:

    • Leveraging camera metadata (EXIF tags) offers a powerful, generalizable strategy for AI-generated image detection.
    • This approach enhances multimedia forensics by providing a more reliable tool against sophisticated AI image generation.