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

Collisions in Multiple Dimensions: Introduction

Collisions in Multiple Dimensions: Introduction

It is far more common for collisions to occur in two dimensions; that is, the initial velocity vectors are neither parallel nor antiparallel to each other. Let's see what complications arise from this. The first idea is that momentum is a vector. Like all vectors, it can be expressed as a sum of perpendicular components (usually, though not always, an x-component and a y-component, and a z-component if necessary). Thus, when the statement of conservation of momentum is written for a...

Collisions in Multiple Dimensions: Problem Solving

Collisions in Multiple Dimensions: Problem Solving

In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...

State Space Representation

State Space Representation

The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...

Elastic Collisions: Introduction

Elastic Collisions: Introduction

An elastic collision is one that conserves both internal kinetic energy and momentum. Internal kinetic energy is the sum of the kinetic energies of the objects in a system. Truly elastic collisions can only be achieved with subatomic particles, such as electrons striking nuclei. Macroscopic collisions can be very nearly, but not quite, elastic, as some kinetic energy is always converted into other forms of energy such as heat transfer due to friction and sound. An example of a nearly...

Elastic Collisions: Case Study

Elastic Collisions: Case Study

Elastic collision of a system demands conservation of both momentum and kinetic energy. To solve problems involving one-dimensional elastic collisions between two objects, the equations for conservation of momentum and conservation of internal kinetic energy can be used. For the two objects, the sum of momentum before the collision equals the total momentum after the collision. An elastic collision conserves internal kinetic energy, and so the sum of kinetic energies before the collision equals...

Random Variables

Random Variables

A random variable is a single numerical value that indicates the outcome of a procedure. The concept of random variables is fundamental to the probability theory and was introduced by a Russian mathematician, Pafnuty Chebyshev, in the mid-nineteenth century.
Uppercase letters such as X or Y denote a random variable. Lowercase letters like x or y denote the value of a random variable. If X is a random variable, then X is written in words, and x is given as a number.
For example, let X = the...

You might also read

Related Articles

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

Sort by

Same author

Artificial intelligence-based algorithm for predicting outcomes in early-stage lung cancer: An annotation-free imaging artificial intelligence study.

JTCVS open·2026

Same author

Topographic correspondence between retinotopic and whisker somatosensory map in mouse higher visual area and its development.

Frontiers in neural circuits·2025

Same author

Auditory cortex neurons that encode negative prediction errors respond to omissions of sounds in a predictable sequence.

PLoS biology·2025

Same author

Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors.

Scientific reports·2025

Same author

Orthogonalization of spontaneous and stimulus-driven activity by hierarchical neocortical areal network in primates.

Nature communications·2024

Same author

ARViS: a bleed-free multi-site automated injection robot for accurate, fast, and dense delivery of virus to mouse and marmoset cerebral cortex.

Nature communications·2024

Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 16, 2025

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Adversarial attacks and defenses using feature-space stochasticity.

Jumpei Ukita¹, Kenichi Ohki²

¹Department of Physiology, The University of Tokyo School of Medicine, 7-3-1, Hongo, Bunkyo-ku, 113-0033, Tokyo, Japan.

Neural Networks : the Official Journal of the International Neural Network Society

|September 18, 2023

Summary

This summary is machine-generated.

Injecting random noise in deep neural networks helps defend against some attacks. However, new feature-space adversarial examples require noise injection in hidden layers for effective defense against unrestricted adversarial attacks.

Keywords:

Adversarial attack Adversarial defense Feature smoothing

More Related Videos

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Related Experiment Videos

Last Updated: Jul 16, 2025

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Area of Science:

Artificial Intelligence
Machine Learning
Deep Neural Networks

Background:

Deep neural networks (DNNs) are vulnerable to adversarial perturbations.
Input-layer noise injection is a known defense against Lp-norm-bounded adversarial examples.
This defense is insufficient against unrestricted adversarial examples not bounded in the input layer.

Purpose of the Study:

To introduce a novel class of unrestricted adversarial examples: feature-space adversarial examples.
To investigate the efficacy of noise injection in different layers of DNNs against these new examples.

Main Methods:

Generation of feature-space adversarial examples, characterized by input-space distance but hidden-layer proximity.
Empirical evaluation of noise injection in the input layer versus hidden layers against these examples.

Main Results:

Input-layer noise injection failed to defend against feature-space adversarial examples.
Hidden-layer noise injection successfully defended against feature-space adversarial examples.
Stochasticity in higher network layers offers a novel defense mechanism.

Conclusions:

Feature-space adversarial examples pose a threat not mitigated by traditional input-layer defenses.
Noise injection in hidden layers is a promising strategy for defending DNNs against a broader range of adversarial attacks.
The findings underscore the importance of exploring stochasticity in deeper network layers for enhanced adversarial robustness.