Protection of neural network models on edge devices
AssigneeFortifyiq, Inc.
InventorsUry Kreimer, Valery Teper, Yaacov Belenky, Alexander Kesler
Life of this patent
Estimating the term…
Loading patent…
AssigneeFortifyiq, Inc.
InventorsUry Kreimer, Valery Teper, Yaacov Belenky, Alexander Kesler
Estimating the term…
Techniques are directed to integrating a trusted execution environment directly into an edge device, physically locating both a secure “protected” processor block and a standard “untrusted” processor block on the same motherboard or chip. Rather than encrypting the entire neural network—which may be computationally prohibitive—the technical solution involves decomposing the parameter values using techniques like Singular Value Decomposition so that the vast majority of parameter values are stored unencrypted in the untrusted block, as they reveal no intellectual property on their own. Only a small, highly sensitive set of parameter values is kept in the protected block where they may be secured with, e.g., efficient, on-the-fly decryption.
A method, comprising:
A computer program product comprising a nontransitory storage medium, the computer program product including code that, when executed by processing circuitry, causes the processing circuitry to perform a method, the method comprising:
Processing circuitry configured to perform a method, the method comprising:
A system, comprising:
Dependencies are inferred from the claim text.