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

Aliasing

Aliasing

Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...

Reconstruction of Signal using Interpolation

Reconstruction of Signal using Interpolation

Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...

Discrete Fourier Transform

Discrete Fourier Transform

The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...

IR Frequency Region: Fingerprint Region

IR Frequency Region: Fingerprint Region

IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...

Sampling Theorem

Sampling Theorem

In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.

IR Spectrometers

IR Spectrometers

There are two main infrared (IR) spectrophotometers: dispersive IR spectrometers and Fourier transform infrared (FTIR) spectrometers. In a dispersive IR spectrometer, a beam of infrared radiation produced by a hot wire is divided into two parallel equal-intensity beams using mirrors. One beam passes through the sample, while another is a reference beam. The beams then move through the monochromator, which separates the radiations into a continuous spectrum of different frequencies. The...

You might also read

Related Articles

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

Sort by

Same author

A Multi-Scale-Enhanced YOLO-V5 Model for Detecting Small Objects in Remote Sensing Image Information.

Sensors (Basel, Switzerland)·2024

Same author

Machine learning: an approach to preoperatively predict PD-1/PD-L1 expression and outcome in intrahepatic cholangiocarcinoma using MRI biomarkers.

ESMO open·2020

Same author

Potential role of imaging for assessing acute pancreatitis-induced acute kidney injury.

The British journal of radiology·2020

Same author

MRI-based radiomics analysis to predict preoperative lymph node metastasis in papillary thyroid carcinoma.

Gland surgery·2020

Same author

Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer.

Frontiers in oncology·2020

Same author

Tibiofemoral Contact Mechanics After Horizontal or Ripstop Suture in Inside-Out and Transtibial Repair for Meniscus Radial Tears in a Porcine Model.

Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association·2020

Search research articles

Related Experiment Video

Updated: Jun 13, 2025

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Published on: February 23, 2018

A Novel Adversarial Example Detection Method Based on Frequency Domain Reconstruction for Image Sensors.

Shuaina Huang^1,2,3, Zhiyong Zhang^1,2,3, Bin Song^1,2,3

¹Information Engineering College, Henan University of Science and Technology, Luoyang 471023, China.

Sensors (Basel, Switzerland)

|September 14, 2024

Summary

This study introduces Frequency Domain Reconstruction (FDR), a novel method to detect adversarial examples in Convolutional Neural Networks (CNNs) without altering the model. FDR effectively removes adversarial interference, enhancing CNN robustness for critical applications.

Keywords:

adversarial detection deep learning attacks frequency domain gradient masking reconstruction

More Related Videos

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Related Experiment Videos

Last Updated: Jun 13, 2025

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Published on: February 23, 2018

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Area of Science:

Computer Vision
Machine Learning
Remote Sensing

Background:

Convolutional Neural Networks (CNNs) excel in remote sensing but are vulnerable to adversarial examples, compromising safety-critical applications.
Existing detection methods often require CNN modification, increasing costs and potentially degrading performance.
Robustness against adversarial attacks is crucial for reliable AI in sensitive domains.

Purpose of the Study:

To propose an effective adversarial example detection algorithm for CNNs that does not require model modification.
To maintain high classification accuracy for normal examples while detecting adversarial ones.
To enhance the security and reliability of CNNs in remote sensing and other critical applications.

Main Methods:

Frequency Domain Reconstruction (FDR) detects adversarial examples by transforming input data into the frequency domain using Fourier transform.
Adversarial disturbances are mitigated by modifying specific frequencies, and the image is reconstructed in the spatial domain via inverse Fourier transform.
Gradient masking is incorporated into FDR to improve detection of complex adversarial examples.

Main Results:

Extensive experiments on five adversarial attacks across three benchmark datasets demonstrate FDR's superior performance over state-of-the-art methods.
FDR successfully detects adversarial examples without modifying the underlying CNN architecture.
The method shows potential for integration into sensing devices to ensure detection safety.

Conclusions:

Frequency Domain Reconstruction (FDR) offers a non-intrusive and effective solution for detecting adversarial examples in CNNs.
FDR enhances the robustness of CNNs against adversarial attacks without compromising performance on legitimate data.
The proposed method is a significant advancement for deploying secure and reliable AI in safety-critical remote sensing tasks.