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