Paillier Encrypted Linear Classification Example

DISCLAIMER: This is a proof-of-concept implementation. It does not represent a remotely product ready implementation or follow proper conventions for security, convenience, or scalability. It is part of a broader proof-of-concept demonstrating the vision of the OpenMined project, its major moving parts, and how they might work together.



In [11]:

    
from syft.he.paillier import KeyPair
from syft.nn.linear import LinearClassifier
import numpy as np



In [12]:

    
pubkey,prikey = KeyPair().generate(n_length=1024)



In [13]:

    
model = LinearClassifier(n_inputs=4,n_labels=2).encrypt(pubkey)



In [14]:

    
input = np.array([[0,0,1,1],[0,0,1,0],[1,0,1,1],[0,0,1,0]])
target = np.array([[0,1],[0,0],[1,1],[0,0]])



In [15]:

    
for iter in range(3):
    for i in range(len(input)):
        print("Grads:" + str((model.learn(input=input[i],target=target[i],alpha=0.5))))









    



Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]
Grads:[[e e]
 [e e]
 [e e]
 [e e]]



In [16]:

    
model = model.decrypt(prikey)



In [17]:

    
for i in range(len(input)):
    print(model.forward(input[i]))









    



[ 0.26074219  0.26074219]
[ 0.02050781  0.02050781]
[ 1.08691406  1.08691406]
[ 0.02050781  0.02050781]



In [ ]:



In [ ]: