How do I encrypt, run and decrypt separately?

Zama Concrete ML
1

Concrete-ML offers to the user the possibility to easily encrypt the inputs, run the inference and decrypt the outputs. For all available models, these steps are gathered in a single method predict, following the same API as provided in the scikit-learn library. Here’s an example using a LogisticRegression model:

from concrete.ml.sklearn import LogisticRegression

# Instantiate and train
model = LogisticRegression()
model.fit(x,y)

# Compile
model.compile(x)

# Get the model's class predictions with FHE execution
y_pred = model.predict(x, execute_in_fhe=True)

As with scikit-learn, it is possible to predict the logits as well as the class probabilities by respectively using the decision_function or predict_proba methods instead. Note that for now, only the matrix multiplication is executed in FHE, following post-processing steps (sigmoid, argmax) are done in the clear.

Additionally, it is possible to execute each step (quantization, key generation, encrypt, run, decrypt) separately :

from concrete.ml.sklearn import LogisticRegression
import numpy

# Instantiate and train
model = LogisticRegression()
model.fit(x,y)

# Compile
fhe_circuit = model.compile(x)

# Keygen
fhe_circuit.keygen()

# Quantize an input and encrypt
input = x[:1]
q_input = model.quantize_input(input)
q_input_enc = fhe_circuit.encrypt(q_input)

# Execute the inference in FHE
q_y_enc = fhe_circuit.run(q_input_enc)

# Decrypt and dequantize to get logits 
q_y = fhe_circuit.decrypt(q_y_enc)
y_logit = model.dequantize_output(q_y)

# Apply the sigmoid to get probabilities (in the clear)
y_proba = model.post_processing(y_logit, already_dequantized=True)

# Apply the argmax to get class predictions (in the clear)
y_pred = numpy.argmax(y_proba, axis=1)
1 Like
2

Is there a way to print the individual values?

(keys, quantized input, encrypted input, encrypted result, decrypted result, dequantized result)

want to demonstrate the inner workings in a presentation

3

Hi @lstk,

You can do:

import base64

fhe_circuit.keys.generate()
print(base64.b64encode(fhe_circuit.keys.serialize()))

q_input_enc = fhe_circuit.encrypt(q_input)
print(base64.b64encode(q_input_enc.serialize()))

Keep in mind it’ll be quite a lot :slightly_smiling_face:

1 Like
4

This is perfect. thanks a lot!!

1 Like
5

Also @lstk , for quantized inputs (here q_input), quantized outputs (here q_y) and de-quantized outputs (here y_logit, y_proba or y_pred depending on your goal), you can directly print them since they are regular Numpy arrays :wink:

1 Like