Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Interference: Path Lengths01:10

Interference: Path Lengths

Consider two sources of sound, that may or may not be in phase, emitting waves at a single frequency, and consider the frequencies to be the same.
Two special sources may be considered when they are in phase. This can be easily achieved by feeding the two sources from the same source. An example would be synchronizing the two speakers by feeding them with the same source, such as the sound waves produced by a tuning fork. This setup ensures that the two sources have the same frequency and are...
Classification of Signals01:30

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear.
Force Classification01:22

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,...
Sound Waves: Interference00:53

Sound Waves: Interference

Sound waves can be modeled either as longitudinal waves, wherein the molecules of the medium oscillate around an equilibrium position, or as pressure waves. When two identical waves from the same source superimpose on each other, the combination of two crests or two troughs results in amplitude reinforcement known as constructive interference. If two identical waves, that are initially in phase, become out of phase because of different path lengths, the combination of crests with troughs...
Interference and Superposition of Waves01:07

Interference and Superposition of Waves

When two waves of the same nature occur in the same region simultaneously, they result in interference. Interference of waves implies that the net effect of the waves is the sum of the individual waves' effects. However, it does not imply that the individual waves affect the propagation of other waves.
Interference occurs in mechanical waves, such as sound waves, waves on a string, and surface water waves. Mechanical waves correspond to the physical displacement of particles. Hence,...

You might also read

Related Articles

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

Sort by
Same author

Comparison of 5-year survival rates and prognostic factors between adenoid cystic carcinoma and squamous cell carcinoma of the maxillary sinus: a SEER database analysis.

Translational cancer research·2026
Same author

Host genetic regulation of rumen 6-hydroxymelatonin reduces methane emissions in dairy cattle.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Cationic Potential-Driven Surface Reconstruction Enables Stable High-Voltage Cylindrical Sodium-Ion Batteries.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Multi-omics analysis of soy isoflavone-induced responses in rumen fermentation, endocrine status and milk production in cows with varying milk yields.

Journal of animal science and biotechnology·2026
Same author

Self-injection blue laser interferometric salinometer via configurable beating frequency.

Optics express·2026
Same author

Single-Particle Insights Into the Electronic Structure and Enhanced Stability of CsPbBr<sub>3</sub>/FAPbBr<sub>3</sub> Core/Crown Nanoplatelets at the Nanometer Scale.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

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

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

Q-learning based asynchronous Boolean control networks stabilization with data loss.

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

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Videos

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Yi Li1, Yan Zhang2, Chenguang Zhang2

  • 1School of Cyberspace Security, Hainan University, Haikou, Hainan, 570228, China.

Neural Networks : the Official Journal of the International Neural Network Society
|July 4, 2026
PubMed
Summary
This summary is machine-generated.

We introduce a complex-valued amplitude-phase interference (CAPI) method to enhance deep neural network robustness against adversarial attacks. CAPI improves classification performance by introducing structured constraints at the decision stage.

Keywords:
Adversarial trainingAmplitude–phase interferenceComplex-valued representationRobust classification

Related Experiment Videos

Area of Science:

  • Computer Vision
  • Deep Learning
  • Quantum Computing Principles

Background:

  • Deep neural networks (DNNs) excel in computer vision but are vulnerable to adversarial perturbations, limiting safety-critical applications.
  • Current adversarial training methods use softmax-based classification heads with fixed decision boundaries, hindering robustness.
  • Existing methods struggle to capture complex, flexible decision boundaries needed for robust DNNs.

Purpose of the Study:

  • To propose a novel method, complex-valued amplitude-phase interference (CAPI), for enhancing DNN robustness against adversarial perturbations.
  • To improve model decision boundaries beyond linear or angular constraints for better adversarial defense.
  • To leverage quantum interference principles for structured constraints in DNN decision stages.

Main Methods:

  • Developed a multi-branch complex-amplitude formulation inspired by quantum probabilistic amplitude superposition.
  • Utilized phase differences for constructive/destructive interference and amplitudes to modulate interference strength.
  • Integrated CAPI into the decision stage of DNNs to introduce structured constraints.

Main Results:

  • CAPI demonstrated robust classification performance against various adversarial attacks, including FGSM, BIM, MIM, PGD, and AA.
  • The method effectively improved model robustness by introducing structured constraints at the decision level.
  • Experimental results on benchmark datasets validated the effectiveness of CAPI under significant adversarial perturbations.

Conclusions:

  • The proposed complex-valued amplitude-phase interference (CAPI) method significantly enhances DNN robustness against adversarial attacks.
  • CAPI offers a novel approach to improving adversarial defense by enabling more flexible decision boundaries.
  • This work highlights the potential of quantum-inspired principles in advancing secure and reliable deep learning models.