AI privacy made easy
An open source, accesible and fast
AI inference solution for confidential data
Our mission
AI is a promising technology that has the potential to revolutionise many sectors such as healthcare, biometrics and industry. However, current security and privacy concerns prevent AI teams from accessing sensitive data to train and deploy their models. The current lack of toolings, providing technical guarantees, hinders AI adoption due to data owners’ fear of uncontrolled data usage.
That is why we have created BlindAI, an open source solution, to help AI teams leverage sensitive data, while providing the technical guarantees to data owners and regulation that data shared to AI models remains protected at all time.
By leveraging Confidential Computing and existing AI solutions like ONNX or Pytorch, we make AI privacy easy for data teams.
Protect data at all time
With current solutions, even if data is sent securely, data is in clear when analysed by third party AI solutions. This means that once you share data externally, you no longer have control on what is done on it. malicious service provider could sell your data, exploit its IP, or simply get compromised by an attacker and leak your data.
With BlindAI end-to-end protection guarantees, your data is never accessible by anyone else, even while it is manipulated by third parties. This way you safely share data to AI teams who can improve their model and provide you a prediction, without ever fearing losing control over your data.
BlindAI in action
Step #1 – Launch the inference server
Deploy our confidential inference server in one command using Docker. We provide one image for production workload with all the security guarantees but requiring specific hardware, and one simulation image that can be run anywhere for testing.
docker run -p 50051:50051 -p 50052:50052 --device /dev/sgx/enclave --device /dev/sgx/provision blindai-server /root/start.sh $PCCS_API_KEY
Step #2 – Load the AI model
Pytorch or Tensorflow models can be loaded inside the confidential inference server using the ONNX format. Simply export your model in ONNX and use our SDK to upload it securely to the inference server.
from blindai.client import BlindAiClient
# Create the connection
client = BlindAiClient()
client.connect_server(
"localhost",
policy="policy.toml",
certificate="host_server.pem"
)
# Upload the model to the server
response = client.connect_server(model="./distilbert-base-uncased.onnx", shape=(1, 8), dtype=ModelDatumType.I64)
Step #3 – Perform confidential inference on sensitive data
Use our client SDK to check that the remote inference server has the right security features (i.e. right code loaded and right model), before sending your data to be analysed with end-to-end protection.
from blindai.client import BlindAiClient
from transformers import DistilBertTokenizer
# Create the connection
client = BlindAiClient()
client.connect_server(
"localhost",
policy="policy.toml",
certificate="host_server.pem"
)
# Prepare the inputs
tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased")
sentence = "I love AI and privacy"
inputs = tokenizer(sentence, padding = "max_length", max_length = 8)["input_ids"]
# Get prediction
response = client.run_model(inputs)