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

Survival Tree01:19

Survival Tree

176
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
176
Force Classification01:22

Force Classification

1.8K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.8K

You might also read

Related Articles

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

Sort by
Same author

CBCT-guided adaptive radiotherapy using self-supervised sequential domain adaptation with uncertainty estimation.

Medical image analysis·2023
Same author

Can Hierarchical Transformers Learn Facial Geometry?

Sensors (Basel, Switzerland)·2023
Same author

Multimodal explainable AI predicts upcoming speech behavior in adults who stutter.

Frontiers in neuroscience·2022
Same author

Interpretable Self-Supervised Facial Micro-Expression Learning to Predict Cognitive State and Neurological Disorders.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2021
Same author

Summarizing Complex Graphical Models of Multiple Chronic Conditions Using the Second Eigenvalue of Graph Laplacian: Algorithm Development and Validation.

JMIR medical informatics·2020

Related Experiment Video

Updated: Oct 4, 2025

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

671

Deepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models.

Samuel Henrique Silva1, Mazal Bethany2, Alexis Megan Votto2

  • 1Secure AI & Autonomy Laboratory, Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, TX, USA.

Forensic Science International. Synergy
|February 7, 2022
PubMed
Summary

This study introduces a new deepfake detection method that combines AI with human analysis for improved accuracy. The explainable forensics algorithm enhances deepfake detection by incorporating human expertise into the loop.

Keywords:
Deep learningDeepfakeFacial recognitionForensics

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K

Related Experiment Videos

Last Updated: Oct 4, 2025

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

671
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Digital Forensics

Background:

  • Deepfakes are increasingly sophisticated, posing risks of disinformation.
  • Current deep learning methods for deepfake detection, while effective, struggle with evolving generation algorithms.
  • A need exists for more robust and adaptable deepfake detection techniques.

Purpose of the Study:

  • To propose a hierarchical explainable forensics algorithm for deepfake detection.
  • To enhance deepfake detection by integrating human expertise into the loop.
  • To improve the generalization capabilities of deepfake detection models.

Main Methods:

  • Developed an attention-based explainable deepfake detection algorithm.
  • Implemented an ensemble of standard and attention-based data-augmented detection networks.
  • Utilized Grad-CAM for visualizing model attention and performed frequency/statistical analyses on cropped regions.

Main Results:

  • Achieved 92.4% accuracy on the challenging DFDC dataset.
  • Demonstrated maintained accuracy on unseen datasets, indicating strong generalization.
  • The hierarchical approach successfully incorporated human decision-making with AI analysis.

Conclusions:

  • The proposed explainable forensics algorithm offers a robust solution to evolving deepfake generation techniques.
  • Integrating human expertise with AI-driven detection significantly improves reliability.
  • This method shows promise for real-world applications in combating disinformation.