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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

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

Sort by

Same author

Sustained improvement in survival for primary ocular adnexal lymphoma from 2005 to 2024 by model-based period analysis.

Discover oncology·2026

Same author

Highly Programmable Liquid Crystalline Polyurethane/MXene Hybrids for Large-Strain, High-Work-Capacity Artificial Muscles.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Intratumoral and peritumoral radiomics based on multi-parametric magnetic resonance imaging for predicting microsatellite instability in endometrial cancer.

Diagnostic and interventional radiology (Ankara, Turkey)·2026

Same author

Support vector machine-driven Parkinson's disease identification: a 7-Tesla multidimensional structural MRI approach.

NPJ Parkinson's disease·2026

Same author

Docosahexaenoic Acid Attenuates Visceral Pain by Suppressing Spinal CXCL10/CXCR3/ERK Signaling.

Nutrients·2026

Same author

Integrating Local Precision With Global Consistency for Unsupervised Magnetic Resonance Image Registration.

Magnetic resonance in medicine·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

Search research articles

Related Experiment Video

Updated: Jul 20, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Reverse Engineering of Generative Models: Inferring Model Hyperparameters From Generated Images.

Vishal Asnani, Xi Yin, Tal Hassner

IEEE Transactions on Pattern Analysis and Machine Intelligence

|August 2, 2023

Summary

This summary is machine-generated.

Researchers developed a new method to identify the specific generative models (GMs) used to create realistic fake images. This "model parsing" technique analyzes generated images to infer the underlying GM architecture and training parameters, aiding in deepfake detection.

More Related Videos

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Jul 20, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

State-of-the-art Generative Models (GMs) produce highly realistic synthetic images, blurring the line between real and fake media.
The proliferation of manipulated media raises significant societal concerns regarding potential misuse of GMs.
Effective identification and understanding of manipulated media are crucial for mitigating these risks.

Purpose of the Study:

To develop a method for reverse-engineering Generative Models (GMs) by analyzing their generated images.
To introduce and address the novel problem of 'model parsing': estimating GM network architectures and training loss functions from synthesized images.
To provide tools for identifying the origin and parameters of generated visual content.

Main Methods:

Proposed a framework comprising two key components: a Fingerprint Estimation Network (FEN) and a Parsing Network (PN).
The FEN estimates a unique 'GM fingerprint' from a generated image, trained with four specific constraints.
The PN predicts the GM's network architecture and loss functions based on the estimated fingerprints.

Main Results:

A comprehensive fake image dataset of 100,000 images generated by 116 diverse GMs was collected for evaluation.
Experiments demonstrated encouraging accuracy in parsing hyperparameters of previously unseen generative models.
The proposed fingerprint estimation method achieved state-of-the-art results on both deepfake detection (Celeb-DF) and image attribution benchmarks.

Conclusions:

The developed 'model parsing' framework successfully infers generative model characteristics from synthesized images.
The fingerprint estimation technique shows significant promise for practical applications in digital forensics.
This research contributes to combating the misuse of generative models by enhancing capabilities in deepfake detection and image attribution.