Blockchain recordation of device usage
Data verification in federate learning is faster and simpler. As artificial intelligence grows in usage, data verification is needed to prove custody and/or control. Electronic data representing an original version of training data may be hashed to generate one or more digital signatures. The digital signatures may then be incorporated into one or more blockchains for historical documentation. Any auditor may then quickly verify and/or reproduce the training data using the digital signatures. For example, a current version of the training data may be hashed and compared to the digital signatures generated from the current version of the training data. If the digital signatures match, then the training data has not changed since its creation. However, if the digital signatures do not match, then the training data has changed since its creation. The auditor may thus flag the training data for additional investigation and scrutiny.
1. A memory device storing instructions that when executed cause a hardware processor to perform operations, the operations comprising:
receiving a bit string representing a usage reported by a mobile device executing a federated learning model;
identifying a master blockchain dedicated to the federated learning model; identifying a sub-blockchain integrated within the master blockchain, the sub-blockchain dedicated to only the mobile device;
identifying an intersecting data block within the sub-blockchain that is dedicated to documenting usages of the mobile device executing the federated learning model;
generating a shorter bit string representing the usage reported by the mobile device by hashing the bit string;
splitting the shorter bit string representing the usage reported by the mobile device into multiple shares via a secret sharing algorithm: and
recording the shorter bit string representing the usage reported by the mobile device to the intersecting data block within the sub-blockchain that is dedicated to documenting the usages of the mobile device executing the federated learning model.
2. The memory device of claim 1 , wherein the operations further comprise distributing the multiple shares via a number Nb of different blockchains according to a ratio Nr/Nb, wherein Nr is a number of recipients of the different blockchains.
3. The memory device of claim 1 , wherein the operations further comprise distributing the multiple shares via the master blockchain dedicated to the federated learning model.
4. The memory device of claim 1 , wherein the operations further comprise distributing the multiple shares via the sub-blockchain dedicated to only the mobile device.
5. The memory device of claim 1 , wherein the operations further comprise distributing the bit string representing the usage reported by the mobile device via the master blockchain dedicated to the federated learning model.
6. A method executed by a server that records usages reported via a network by a mobile device, the method comprising:
receiving a bit string representing a usage of the usages reported via the network by the mobile device executing a federated learning model;
identifying a master blockchain dedicated to the federated learning model; identifying a sub-blockchain integrated within the master blockchain, the sub-blockchain dedicated to only the mobile device;
identifying an intersecting data block within the sub-blockchain that is dedicated to documenting the usages of the mobile device executing the federated learning model;
generating a shorter bit string representing the usage reported by the mobile device by hashing the bit string;
splitting the shorter bit string representing the usage reported by the mobile device into multiple shares via a secret sharing algorithm; and
recording the shorter bit string representing the usage reported by the mobile device to the intersecting data block within the sub-blockchain that is dedicated to documenting the usages of the mobile device executing the federated learning model.
7. A server that records usages reported via a network by a mobile device, the server comprising:
a hardware processor; and
a memory device storing instructions that when executed by the hardware processor perform operations, the operations comprising:
receiving a bit string representing a usage of the usages reported via the network by the mobile device executing a federated learning model;
identifying a master blockchain dedicated to the federated learning model; identifying a sub-blockchain integrated within the master blockchain, the sub-blockchain dedicated to only the mobile device;
identifying an intersecting data block within the sub-blockchain that is dedicated to documenting the usages of the mobile device executing the federated learning model;
generating a shorter bit string representing the usage reported by the mobile device by hashing the bit string;
splitting the shorter bit string representing the usage reported by the mobile device into multiple shares via a secret sharing algorithm; and
recording the shorter bit string representing the usage reported by the mobile device to the intersecting data block within the sub-blockchain that is dedicated to documenting the usages of the mobile device executing the federated learning model.