CA3177679A1 - Systemes et procedes de fourniture d'une plateforme d'intelligence artificielle multimodale privee - Google Patents

Systemes et procedes de fourniture d'une plateforme d'intelligence artificielle multimodale privee Download PDF

Info

Publication number
CA3177679A1
CA3177679A1 CA3177679A CA3177679A CA3177679A1 CA 3177679 A1 CA3177679 A1 CA 3177679A1 CA 3177679 A CA3177679 A CA 3177679A CA 3177679 A CA3177679 A CA 3177679A CA 3177679 A1 CA3177679 A1 CA 3177679A1
Authority
CA
Canada
Prior art keywords
client
data
side network
server
network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CA3177679A
Other languages
English (en)
Inventor
Greg STORM
Gharib GHARIBI
Riddhiman Das
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
TripleBlind Inc
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Publication of CA3177679A1 publication Critical patent/CA3177679A1/fr
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/098—Distributed learning, e.g. federated learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un système et un procédé de fourniture d'une plateforme d'intelligence artificielle multimodale privée. Le procédé comprend la division d'un réseau neuronal en un premier réseau côté client, un second réseau côté client et un réseau côté serveur, et l'envoi du premier réseau côté client à un premier client. Le premier réseau côté client traite des premières données du premier client, les premières données ayant un premier type. Le procédé consiste à envoyer le second réseau côté client à un second client. Le second réseau côté client traite des secondes données du second client, les secondes données ayant un second type. Le premier type et le second type ont une association commune. Une propagation avant et arrière se produit entre les réseaux côté client et les types de données disparates sur les différents réseaux côté client et le réseau côté serveur pour entraîner le réseau neuronal.
CA3177679A 2020-05-06 2021-05-06 Systemes et procedes de fourniture d'une plateforme d'intelligence artificielle multimodale privee Pending CA3177679A1 (fr)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US202063020930P 2020-05-06 2020-05-06
US63/020,930 2020-05-06
US202117180475A 2021-02-19 2021-02-19
US17/180,475 2021-02-19
PCT/US2021/031012 WO2021226302A1 (fr) 2020-05-06 2021-05-06 Systèmes et procédés de fourniture d'une plateforme d'intelligence artificielle multimodale privée

Publications (1)

Publication Number Publication Date
CA3177679A1 true CA3177679A1 (fr) 2021-11-11

Family

ID=78468414

Family Applications (1)

Application Number Title Priority Date Filing Date
CA3177679A Pending CA3177679A1 (fr) 2020-05-06 2021-05-06 Systemes et procedes de fourniture d'une plateforme d'intelligence artificielle multimodale privee

Country Status (5)

Country Link
EP (1) EP4147178A4 (fr)
JP (1) JP2023524289A (fr)
KR (1) KR20230005900A (fr)
CA (1) CA3177679A1 (fr)
WO (1) WO2021226302A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116151370A (zh) * 2023-04-24 2023-05-23 西南石油大学 一种模型参数优化选择系统
WO2023144022A1 (fr) * 2022-01-26 2023-08-03 Cardiologs Technologies Sas Systèmes et procédés de restriction de droits à un système de traitement d'électrocardiogrammes

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118633336A (zh) * 2022-02-24 2024-09-10 华为技术有限公司 用于自适应交换人工智能/机器学习参数的方法和装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10755172B2 (en) * 2016-06-22 2020-08-25 Massachusetts Institute Of Technology Secure training of multi-party deep neural network
US10924460B2 (en) 2019-12-13 2021-02-16 TripleBlind, Inc. Systems and methods for dividing filters in neural networks for private data computations

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023144022A1 (fr) * 2022-01-26 2023-08-03 Cardiologs Technologies Sas Systèmes et procédés de restriction de droits à un système de traitement d'électrocardiogrammes
CN116151370A (zh) * 2023-04-24 2023-05-23 西南石油大学 一种模型参数优化选择系统

Also Published As

Publication number Publication date
EP4147178A4 (fr) 2023-10-18
WO2021226302A1 (fr) 2021-11-11
JP2023524289A (ja) 2023-06-09
KR20230005900A (ko) 2023-01-10
EP4147178A1 (fr) 2023-03-15

Similar Documents

Publication Publication Date Title
CA3177679A1 (fr) Systemes et procedes de fourniture d'une plateforme d'intelligence artificielle multimodale privee
US11991156B2 (en) Systems and methods for secure averaging of models for federated learning and blind learning using secure multi-party computation
US20200019865A1 (en) System and method for processing data and managing information
CN113177645A (zh) 联邦学习方法、装置、计算设备及存储介质
CN112989399B (zh) 数据处理系统及方法
US20240154942A1 (en) Systems and methods for blind multimodal learning
US12088565B2 (en) Systems and methods for privacy preserving training and inference of decentralized recommendation systems from decentralized data
Xu et al. Client selection based weighted federated few-shot learning
WO2023038963A1 (fr) Systèmes et procédés d'apprentissage vertical aveugle
WO2023038978A1 (fr) Systèmes et procédés d'entraînement préservant la confidentialité et inférence de systèmes de recommandation décentralisés à partir de données décentralisées
Qin et al. A split-federated learning and edge-cloud based efficient and privacy-preserving large-scale item recommendation model
Alnajar et al. Tactile internet of federated things: Toward fine-grained design of FL-based architecture to meet TIoT demands
US20230252277A1 (en) Systems and methods for enabling the training of sequential models using a blind learning approach applied to a split learning
US20230306254A1 (en) Systems and methods for quantifying data leakage from a split layer
US20230244914A1 (en) Systems and methods for training predictive models on sequential data using 1-dimensional convolutional layers in a blind learning approach
WO2023039001A1 (fr) Systèmes et procédés pour fournir une approche d'inférence divisée pour protéger des données et un modèle
US20240146730A1 (en) Conducting multi-party authentication in a privacy preserving manner
WO2024192358A1 (fr) Apprentissage et réalisation d'opérations d'inférence de modèles d'apprentissage machine à l'aide d'un calcul sécurisé multipartite
CN116341014A (zh) 一种多方联邦隐私数据资源交互方法、装置和介质
CN115510466A (zh) 密文预测方法、相关装置及存储介质
Addo Master of Science in Information Security and Cryptography