Jove
Visualize
Contact Us

Related Concept Videos

Reducing Line Loss01:18

Reducing Line Loss

152
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
152
Improving Translational Accuracy02:07

Improving Translational Accuracy

10.3K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
10.3K
Neuroplasticity01:01

Neuroplasticity

344
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
344
Compacting Factor test01:22

Compacting Factor test

145
The compacting factor test is a method used to assess the workability of concrete. It is  especially suitable for concrete mixes containing aggregates up to one and a half inches in size. This test involves specialized equipment consisting of two truncated cone-shaped hoppers and a cylinder, all with polished interior surfaces to minimize friction.
The procedure begins by placing concrete into the upper hopper without any compaction. Once filled, the bottom door of this hopper is opened,...
145
Censoring Survival Data01:09

Censoring Survival Data

88
Survival analysis is a statistical method used to analyze time-to-event data, often employed in fields such as medicine, engineering, and social sciences. One of the key challenges in survival analysis is dealing with incomplete data, a phenomenon known as "censoring." Censoring occurs when the event of interest (such as death, relapse, or system failure) has not occurred for some individuals by the end of the study period or is otherwise unobservable, and it might have many different...
88
Types of Errors: Detection and Minimization01:12

Types of Errors: Detection and Minimization

1.6K
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...
1.6K

You might also read

Related Articles

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

Sort by
Same author

YOLOv8 computer vision for automated offside detection in professional football validated through supervised learning.

Scientific reports·2026
Same author

Temporal and Behaviour-Aware Multimodal Modelling for Hour-Ahead Hypoglycaemia Prediction During Ramadan Fasting in Type 1 Diabetes.

Sensors (Basel, Switzerland)·2026
Same author

When collaboration fails: persuasion driven adversarial influence in multi agent large language model debate.

Scientific reports·2026
Same author

Innovative temporal summarization for complex video classification.

Scientific reports·2026
Same author

ML/GA-based performance optimization of PBG-enhanced THz microstrip patch antennas on PTFE-SWCNT.

Scientific reports·2025
Same author

Sustainable E-Health: Energy-Efficient Tiny AI for Epileptic Seizure Detection via EEG.

Biomedical engineering and computational biology·2025
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 Experiment Video

Updated: Jun 30, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K

Defense against adversarial attacks: robust and efficient compressed optimized neural networks.

Insaf Kraidia1, Afifa Ghenai2, Samir Brahim Belhaouari3

  • 1LIRE Laboratory, University of Constantine 2 - Abdelhamid Mehri, Ali Mendjeli Campus, 25000, Constantine, Algeria. insaf.kraidia@univ-constantine2.dz.

Scientific Reports
|March 18, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method to enhance deep neural network (DNN) efficiency and adversarial attack resistance using batch-cumulative optimization and weight compression. The approach significantly improves model accuracy and speed while reducing resource usage.

Keywords:
Adversarial attacksCompressionGenerative pre-trained transformer (GPT)Multi expert

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

531
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K

Related Experiment Videos

Last Updated: Jun 30, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

531
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Cybersecurity

Background:

  • Adversarial attacks pose a significant threat to the reliability and security of deep neural networks (DNNs).
  • Enhancing model efficiency and resistance to these attacks is crucial for practical deployment in real-world applications.
  • Existing optimization techniques often struggle to balance performance, efficiency, and robustness.

Purpose of the Study:

  • To introduce a novel four-component methodology for improving DNN efficiency and adversarial attack resistance.
  • To develop a robust framework that enhances model accuracy, storage efficiency, and inference speed.
  • To significantly bolster model resilience against a wide range of adversarial attack scenarios.

Main Methods:

  • Developed an exponential particle swarm optimization (ExPSO) algorithm with a batch-cumulative approach for parameter fine-tuning.
  • Applied weight compression to streamline generative pre-trained transformer (GPT) parameters, achieving 65% compression without performance loss.
  • Integrated compressed GPT models via a novel multi-expert architecture, training multiple versions across different compression rates and dataset segments.

Main Results:

  • Achieved the lowest perplexity (14.28) and highest accuracy (93.72%) compared to state-of-the-art methods.
  • Demonstrated an 8x speedup in central processing unit (CPU) inference time.
  • Showcased a 25% average performance improvement across 14 attack scenarios, significantly enhancing adversarial robustness.

Conclusions:

  • The proposed methodology effectively enhances DNN efficiency and adversarial robustness.
  • The combination of batch-cumulative optimization, weight compression, and a multi-expert architecture provides superior performance and security.
  • This approach offers a promising solution for deploying secure and efficient DNNs in adversarial environments.