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

Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

592
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
592
Associative Learning01:27

Associative Learning

2.1K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
2.1K
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

2.1K
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
2.1K

You might also read

Related Articles

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

Sort by
Same author

Nop2 is required for mammalian preimplantation development.

Molecular reproduction and development·2015
Same author

Treatment of right ventricular perforation during percutaneous coronary intervention.

Cardiovascular journal of Africa·2015
Same author

Biological variations of thirteen plasma biochemical indicators.

Clinica chimica acta; international journal of clinical chemistry·2015
Same author

Recent Progress in Cobalt-Based Heterogeneous Catalysts for Electrochemical Water Splitting.

Advanced materials (Deerfield Beach, Fla.)·2015
Same author

[APPLICATION OF HIGH VISCOSITY BONE CEMENT IN UNILATERAL PUNCTURE PERCUTANEOUS VERTEBROPLASTY FOR TREATMENT OF FRESH VERTEBRAL FRACTURE].

Zhongguo xiu fu chong jian wai ke za zhi = Zhongguo xiufu chongjian waike zazhi = Chinese journal of reparative and reconstructive surgery·2015
Same author

Application prospect and clinical effect analysis of Fu Chan Xue Jing during bleeding after abortion.

Pakistan journal of pharmaceutical sciences·2015

Related Experiment Video

Updated: Apr 30, 2026

Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.2K

Defending against and generating adversarial examples together with generative adversarial networks.

Ying Wang1, Xiao Liao2, Wei Cui2

  • 1State Grid Information and Telecommunication Group Co., Ltd, Beijing, China. yingwang0926@foxmail.com.

Scientific Reports
|April 15, 2025
PubMed
Summary

Deep neural networks are vulnerable to adversarial examples. The proposed DG-GAN framework defends against and generates these examples, enhancing deep learning security and offering a novel black-box attack method.

More Related Videos

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
06:20

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

2.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

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

Published on: December 6, 2024

463

Related Experiment Videos

Last Updated: Apr 30, 2026

Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.2K
Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
06:20

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

2.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

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

Published on: December 6, 2024

463

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Deep neural networks (DNNs) are widely used but susceptible to adversarial examples.
  • Adversarial examples are subtly modified inputs that cause DNNs to misclassify.
  • Existing defense mechanisms often require modifying classifier structures or training procedures.

Purpose of the Study:

  • To propose a novel DG-GAN framework for defending against and generating adversarial examples.
  • To establish a bidirectional mapping between images and adversarial examples for defense and generation.
  • To develop a defense method compatible with any classification model without structural modifications.

Main Methods:

  • The DG-GAN framework integrates a generator, encoder, and discriminator.
  • Bidirectional mapping is used to relate images and adversarial examples.
  • The generator is employed for defense, and the encoder is used for generating adversarial examples without gradient information.

Main Results:

  • DG-GAN effectively defends against various adversarial attacks, outperforming existing defense strategies.
  • The framework improves the robustness of classification models.
  • DG-GAN demonstrates comparable performance as a black-box attack method.

Conclusions:

  • The DG-GAN framework offers a versatile solution for both defending against and generating adversarial examples.
  • It enhances deep neural network security without altering existing models or training processes.
  • DG-GAN presents a dual capability for both robust defense and effective black-box attacks.