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

Verification by the Model Owner

  1. Verify Merkle Proofs Against Merkle Root:

    • The model owner uses the Merkle proofs to verify that the data chunks used in training belong to the committed dataset.

    • The model owner checks each proof against the pre-committed Merkle root. Any inconsistency between the proofs and the Merkle root indicates unauthorized data usage.

  2. Verify Hash Log Consistency:

    • The model owner examines the hash log to confirm that the hashes of accessed chunks match the Merkle root structure.

    • Any hash in the log that doesn’t align with the Merkle Tree indicates tampering or unauthorized data usage.

  3. Decrypt Model Updates:

    • After verifying the proofs and hash log, the model owner decrypts the model updates and confirms that they were generated based on the authorized dataset.

PreviousTransmission of Model Updates, Merkle Proofs, and Hash Log to the Model OwnerNextIncentivization Process

Last updated 5 months ago