This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import hnumpy as hnp | |
import numpy as np |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
weights = np.array([0.1, 0.2, 0.3, 0.4, 0.5]) | |
bias = np.array([0.1]) | |
def sigmoid(x): | |
return 1 / (1 + np.exp(-x)) | |
def func(x): | |
return sigmoid(np.dot(x, weights) + bias) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
h = hnp.compile_fhe( | |
func, | |
{ | |
'x': hnp.encrypted_ndarray(bounds=(-1, 1), shape=(5,)), | |
} | |
) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
x = np.random.uniform(-1, 1, 5) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
print(f"Simulation result: {h.simulate(x)}") | |
print(f"Plain NumPy result: {func(x)}") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ctx = h.create_context() | |
keys = ctx.keygen() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
print(f"Encrypted computation result: {h.encrypt_and_run(keys, x)}") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
x_enc= keys.encrypt(x) | |
res = h.run(keys.public_keys, x_enc) | |
print(f"Encrypted computation result: {keys.decrypt(res)}") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
HIDDEN_SIZE = 100 | |
class Model(torch.nn.Module): | |
def __init__(self): | |
super().__init__() | |
self.lstm = torch.nn.LSTM(input_size=300, hidden_size=HIDDEN_SIZE) | |
self.fc = torch.nn.Linear(HIDDEN_SIZE, 1) | |
self.sigmoid = torch.nn.Sigmoid() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Inferer: | |
def __init__(self, model): | |
parameters = list(model.lstm.parameters()) | |
W_ii, W_if, W_ig, W_io = parameters[0].split(HIDDEN_SIZE) | |
W_hi, W_hf, W_hg, W_ho = parameters[1].split(HIDDEN_SIZE) | |
b_ii, b_if, b_ig, b_io = parameters[2].split(HIDDEN_SIZE) | |
b_hi, b_hf, b_hg, b_ho = parameters[3].split(HIDDEN_SIZE) | |
self.W_ii = W_ii.detach().numpy() |
OlderNewer