Unity Network
  • Unity Network
    • Introduction
    • Unity Network FL Architecture
    • Data Security
    • Case Study
      • Flashback Overview
      • Registration
      • Integration
      • Model Training
      • Objectives and Outcomes
  • Unity Network SDK
    • Key Features
    • Registration
    • Node Setup
    • SDK Integration
      • Wallet Module
      • Node Module
  • Permissions Management
    • User Permissions
  • Model Training
    • Organization registration
    • Model Training Requests
    • Secure Training and Updates
      • Model Training
        • Model Loading and Initialization
        • Data Loading
        • Training
      • Secure Transmission of Encrypted Updates
        • ECDH Key Exchange for Secure Encryption Key Generation
        • Encrypt and Transmit Model Updates
        • Secure Aggregation and Decryption at Central Server
        • Distribute Updated Model and Continue Training
      • Sharing Model Updates with the Model Owner and Verifying Authenticity of Training
        • Construct the Merkle Tree and Commit to the Merkle Root
        • Log Hashes of Accessed Dataset Chunks During Training
        • Transmission of Model Updates, Merkle Proofs, and Hash Log to the Model Owner
        • Verification by the Model Owner
  • Training rewards
    • Incentivization Process
Powered by GitBook
On this page
  1. Model Training
  2. Secure Training and Updates
  3. Sharing Model Updates with the Model Owner and Verifying Authenticity of Training

Transmission of Model Updates, Merkle Proofs, and Hash Log to the Model Owner

  1. Encrypt Model Updates:

    • After completing the training, each node encrypts the final model updates using a symmetric key to ensure secure transmission to the model owner.

  2. Generate and Include Merkle Proofs:

    • Each node generates Merkle proofs for the data chunks used in training, confirming that each chunk belongs to the committed dataset (matching the Merkle root).

    • These proofs are attached to the encrypted model updates, allowing the model owner to verify the data used without direct data access.

  3. Transmit the Hash Log, Encrypted Model Updates, and Merkle Proofs:

    • Each node securely transmits the following to the model owner:

      • Encrypted model updates.

      • Merkle proofs of data chunks used in training.

      • Hash log of accessed data chunks.

PreviousLog Hashes of Accessed Dataset Chunks During TrainingNextVerification by the Model Owner

Last updated 7 months ago