Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Force Classification

Force Classification

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,...

You might also read

Related Articles

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

Sort by

Same author

Compensatory Effects of Joint Bracing From a Kinetic Chain Perspective: Lower Limb Movement Coordination Analysis During Badminton Lunge Movements.

European journal of sport science·2026

Same author

Immediate effects of ankle brace design on mediolateral postural control and perceived support in young adults with functional ankle instability.

Physical therapy in sport : official journal of the Association of Chartered Physiotherapists in Sports Medicine·2026

Same author

Quantitative study on the discriminative value of fingerprint minutiae.

Journal of forensic sciences·2026

Same author

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

Journal of forensic sciences·2026

Same author

Arch-pad design and insole material jointly influence regional plantar loading and perceived comfort during walking in women's occupational footwear.

Ergonomics·2026

Same author

Overexpression of mango GF14I1 and GF14I2 promotes early flowering and enhances abiotic stress tolerance in Arabidopsis.

Journal of plant physiology·2026

Search research articles

Related Experiment Video

Updated: May 1, 2026

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Published on: December 24, 2015

A score based likelihood ratio framework for deepfake image identification in forensic science.

Tianli Guo¹, Jisong Li¹, Yunqi Tang²

¹School of Criminal Investigation, People's Public Security University of China, Beijing, 100038, China.

Scientific Reports

|March 4, 2026

Summary

This study introduces a novel score-based likelihood ratio system for deepfake image forensic identification. The system shows promise for forensic applications, achieving high accuracy on benchmark datasets.

Keywords:

Deepfake images Detection Identification LR Score

More Related Videos

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Published on: October 2, 2016

Detection and Removal of Tooth-Colored Composite Resin Using the Fluorescence-Aided Identification Technique

Detection and Removal of Tooth-Colored Composite Resin Using the Fluorescence-Aided Identification Technique

Published on: July 27, 2022

Related Experiment Videos

Last Updated: May 1, 2026

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Published on: December 24, 2015

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Published on: October 2, 2016

Detection and Removal of Tooth-Colored Composite Resin Using the Fluorescence-Aided Identification Technique

Detection and Removal of Tooth-Colored Composite Resin Using the Fluorescence-Aided Identification Technique

Published on: July 27, 2022

Area of Science:

Digital Forensics
Artificial Intelligence
Computer Vision

Background:

Deepfake technology poses significant challenges to digital media identification.
Existing methods struggle to keep pace with rapid advancements in deepfake generation.

Purpose of the Study:

To develop and evaluate a robust score-based likelihood ratio system for forensic identification of deepfake images.
To address the limitations of current deepfake detection techniques in forensic contexts.

Main Methods:

Utilized the FaceForensics++ dataset with video-level splits to prevent data leakage.
Evaluated six candidate models, identifying the Capsule detector as the most robust.
Employed kernel density estimation for score distribution modeling and optimized bandwidths.
Applied empirical bounds and Pool Adjacent Violators (PAV) calibration for likelihood ratio optimization.

Main Results:

The Capsule detector achieved an Area Under the Curve (AUC) of 0.983 on the FF++ test set.
The system demonstrated low misleading evidence rates (RMEP=0.069, RMED=0.092) and good error control (EER=0.0804).
Generalization tests on unseen datasets showed variable performance (AUCs 0.621-0.783), with the highest on UADFV.

Conclusions:

The proposed likelihood ratio system shows potential for forensic deepfake identification.
Further validation across diverse real-world scenarios is necessary before practical forensic application.