US 12,001,577 B1
Encrypted machine learning models
Yuanjun Xiong, Seattle, WA (US); Jia Bi Zhang, Kirkland, WA (US); Bing Shuai, Seattle, WA (US); and Juan Pablo Escalona Garcia, Edmonds, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Sep. 30, 2021, as Appl. No. 17/491,380.
Int. Cl. G06F 21/62 (2013.01); G06N 3/04 (2023.01); H04L 9/00 (2022.01)
CPC G06F 21/6218 (2013.01) [G06N 3/04 (2013.01); H04L 9/008 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
obtaining input data to be processed using a machine learning model, the obtained input data being in plaintext form;
using a first portion of the machine learning model, comprising a first set of layers of a neural network, to calculate plaintext intermediate data, the first portion of the machine learning model, comprising a second set of layers of the neural network, in plaintext form and a second portion of the machine learning model in ciphertext form according to a homomorphic encryption scheme;
using the homomorphic encryption scheme to encrypt the plaintext intermediate data to obtain ciphertext intermediate data;
using the second portion of the machine learning model to obtain, without decrypting the ciphertext intermediate data, encrypted output data according to the homomorphic encryption scheme; and
transmitting a request to a service to cause the service to decrypt the encrypted output data and provide corresponding plaintext output data in response to the request.