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

Types of Errors: Detection and Minimization

Types of Errors: Detection and Minimization

Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...

Detection of Gross Error: The Q Test

Detection of Gross Error: The Q Test

When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...

Survival Tree

Survival Tree

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...

You might also read

Related Articles

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

Sort by

Same author

Crop-weed classification using deep learning: a comparative study of CNNs, vision transformers, and interpretable models.

Scientific reports·2026

Same author

Sustainable valorization of artisanal sour buttermilk using nanofiltration and spray drying.

Frontiers in nutrition·2026

Same author

Development of a human iPSC-derived corticospinal tract-on-a-chip.

Cell reports methods·2026

Same author

Reversing Pathophysiology in Fragile X Syndrome Mice by Promoting PGC-1α and Mitochondrial Functions.

bioRxiv : the preprint server for biology·2026

Same author

Biosorption of Procion Magenta and Black Azabache textile dyes using banana and carrot peel waste: a comparative analysis of pure and blended systems.

International journal of phytoremediation·2026

Same author

18β-Glycyrrhetinic acid attenuates endoplasmic reticulum stress and neuroinflammation via the PI3K/AKT-dependent pathway in MPTP/p-induced Parkinson's disease mouse model.

3 Biotech·2026

Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026

Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026

Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026

Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

DAMAD: Database, Attack, and Model Agnostic Adversarial Perturbation Detector.

Akshay Agarwal, Gaurav Goswami, Mayank Vatsa

IEEE Transactions on Neural Networks and Learning Systems

|March 12, 2021

Summary

This summary is machine-generated.

This study introduces DAMAD, a generalized algorithm for detecting adversarial perturbations in deep learning. DAMAD is model-agnostic, offering robust defense against various attacks across different datasets and architectures.

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Nov 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Deep learning models are vulnerable to adversarial attacks.
Current detection methods are often dependent on specific models, datasets, or loss functions.

Purpose of the Study:

To propose DAMAD, a generalized adversarial perturbation detection algorithm.
To develop a detection method that is agnostic to model architecture, training data, and loss function.

Main Methods:

Fusion of autoencoder embeddings and statistical texture features from Convolutional Neural Networks (CNNs).
Evaluation using cross-database, cross-attack, and cross-architecture scenarios.

Main Results:

DAMAD demonstrates effectiveness across six diverse databases (ImageNet, CIFAR-10, Multi-PIE, MEDS, PaSC, MNIST).
The algorithm shows strong performance in challenging cross-scenario evaluations.
Comparison with state-of-the-art methods confirms DAMAD's effectiveness on nearly 250,000 images.

Conclusions:

DAMAD offers a generalized and robust approach to adversarial perturbation detection.
The proposed method overcomes limitations of existing, dependent detection algorithms.
DAMAD provides a significant advancement in securing deep learning models against adversarial attacks.