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 Experiment Video

Updated: Jan 5, 2026

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

956

Privacy-enhanced multi-party deep learning.

Maoguo Gong1, Jialun Feng1, Yu Xie1

  • 1School of Electronic Engineering, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, Shaanxi Province 710071, China.

Neural Networks : the Official Journal of the International Neural Network Society
|October 25, 2019
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Masking and Demasking Agents01:19

Masking and Demasking Agents

3.4K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
3.4K

You might also read

Related Articles

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

Sort by
Same author

SSA-KD: Self-structure-aware knowledge distillation for convolutional neural networks.

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

Evolutionary Multiobjective Neural Architecture Search for Binary Neural Networks by Two-Stage Optimization.

IEEE transactions on cybernetics·2026
Same author

RCVQA: Visual question answering model based on reading comprehension.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Rapid determination of lamb meat freshness using the hyperspectral imaging combined with symmetric stacking ensemble algorithm.

Meat science·2025
Same author

Revisiting Siamese-Based 3D Single Object Tracking With a Versatile Transformer.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

SPCNet: Deep Self-Paced Curriculum Network Incorporated With Inductive Bias.

IEEE transactions on neural networks and learning systems·2025
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

This study introduces a new multi-party deep learning framework using differential privacy and homomorphic encryption. It enhances privacy defenses against curious participants and servers while optimizing the privacy budget for better utility.

Area of Science:

  • Artificial Intelligence
  • Computer Science
  • Cryptography

Background:

  • Multi-party deep learning enables collaborative model training without data sharing.
  • Existing frameworks face challenges in defending against honest-but-curious participants and servers.
  • Current methods often consume high privacy budgets, risking data leakage.

Purpose of the Study:

  • To develop a privacy-enhanced multi-party deep learning framework.
  • To address simultaneous attacks from participants and the server without a trusted manager.
  • To reduce the total privacy budget consumption while maintaining model utility.

Main Methods:

  • Integration of differential privacy and homomorphic encryption.
  • Design of a framework to prevent privacy leakage to participants and the central server.
Keywords:
Differential privacyHomomorphic encryptionMulti-party deep learningPrivacyPrivacy budget

Related Experiment Videos

Last Updated: Jan 5, 2026

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

956
  • Proposal of three dynamic privacy budget allocation strategies per epoch.

    • Main Results:

    • The proposed framework effectively defends against honest-but-curious attacks without a trusted manager.
    • Dynamic budget allocation strategies enhance privacy guarantees and model utility.
    • Analytical and experimental evaluations confirm the framework's promising performance.

    Conclusions:

    • The novel framework offers robust privacy protection in multi-party deep learning.
    • Dynamic privacy budget management balances privacy and efficiency.
    • The approach provides a practical solution for secure collaborative AI.