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 Videos

WAFF: A Synergetic Face Forgery Video Detection Method via Weakly Supervised EfficientNet.

Zhengzhuo Pan1, Bohan Chen2, Longxiang Ma2

  • 1School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430079, China.

Journal of Imaging
|June 25, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Association Areas of the Cortex01:21

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Masking and Demasking Agents01:19

Masking and Demasking Agents

EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on the metal...

You might also read

Related Articles

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

Sort by
Same author

Copper sulfide nanozyme with antioxidative stress, anti-inflammation, and anti-calcification for vascular regeneration.

Biomaterials advances·2026
Same author

Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models.

IEEE transactions on bio-medical engineering·2026
Same author

Plasma-activated nanocellulose for sustainable Pickering emulsions: Enhanced stability and antibacterial performance.

Carbohydrate polymers·2026
Same author

A novel continuous-flow three-stage tandem system based on partial nitrification/Anammox granular sludge and partial denitrification-Anammox biofilm (PN/A-PD-A) for advanced nitrogen removal from mature landfill leachate.

Bioresource technology·2026
Same author

Pathogenicity variation of CC4821 Neisseria meningitidis in China from 2005 to 2024.

Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases·2026
Same author

Pathogenicity and vaccine protection of circulating pertactin- and filamentous hemagglutinin-deficient <i>Bordetella pertussis</i> strains.

Emerging microbes & infections·2026
Same journal

Human-AI Interaction in Interventional Radiology: A Narrative Review of Current Applications, Challenges, and Future Directions.

Journal of imaging·2026
Same journal

Coronary Artery Anomalies and Anatomical Variants: Cross-Sectional Diagnostic Imaging and Clinical Background.

Journal of imaging·2026
Same journal

YoLeTooth: A Unified Framework for Joint Tooth Segmentation and Periapical Lesion Detection in Panoramic Radiographs.

Journal of imaging·2026
Same journal

Radiomics-Guided Multi-Sequence Learning for Pathological Complete Response Prediction from Breast MRI with Missing Auxiliary Sequences.

Journal of imaging·2026
Same journal

Cutaneous Thermography in Arthropathies: Quantitative Imaging, Machine Learning, and Clinical Translation.

Journal of imaging·2026
Same journal

Two-Stage Dynamic Synergistic Segmentation Method for Myocardial Pathology.

Journal of imaging·2026
See all related articles

This study introduces the Weakly Supervised EfficientNet Augmented Face Forgery Detector (WAFF) to improve deepfake detection. WAFF enhances generalization across diverse forgery types and perturbations, offering robust media authenticity verification.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Digital Forensics

Background:

  • Deepfake detection is crucial for digital media authenticity.
  • Existing methods struggle with generalization to new forgery types and perturbations like compression and noise.
  • Vulnerability to adversarial attacks remains a significant challenge for current deepfake detectors.

Purpose of the Study:

  • To propose a novel framework, the Weakly Supervised EfficientNet Augmented Face Forgery Detector (WAFF), for enhanced deepfake detection.
  • To improve the generalization capabilities of deepfake detectors against unseen forgery techniques and common perturbations.
  • To develop a robust system that balances sensitivity and stability in identifying manipulated media.

Main Methods:

  • Developed WSEffiNet, an EfficientNet-B3 backbone integrated with a Weakly Supervised Data Augmentation Network (WS-DAN).
Keywords:
deepfake detectionface forgeryweakly supervised attention

Related Experiment Videos

  • Implemented fine-grained per-frame analysis with attention map generation to highlight subtle forgery artifacts.
  • Employed an adaptive video-level fusion strategy combining fake-frame counting, confidence averaging, and attention-guided voting.

    • Main Results:

    • WAFF achieved state-of-the-art performance on benchmark datasets including FaceForensics++, Celeb-DF v2, DFD, DFDC, and FFIW-10K.
    • Demonstrated superior performance under both high- and low-quality compression scenarios.
    • Showcased enhanced cross-dataset generalization capabilities, indicating robustness to variations in data distribution.

    Conclusions:

    • The proposed WAFF framework offers a significant advancement in deepfake detection.
    • WAFF effectively addresses limitations in generalization and robustness to perturbations faced by existing methods.
    • The integration of weakly supervised augmentation and adaptive fusion strategies contributes to a more stable and accurate deepfake detection system.