Using Encrypted Models with OpenVINO¶
Deploying deep-learning capabilities to edge devices can present security challenges like ensuring inference integrity, or providing copyright protection of your deep-learning models.
One possible solution is to use cryptography to protect models as they are deployed and stored on edge devices. Model encryption, decryption and authentication are not provided by OpenVINO but can be implemented with third-party tools (i.e., OpenSSL). While implementing encryption, ensure that the latest versions of tools are used and follow cryptography best practices.
This guide presents how to use OpenVINO securely with protected models.
Secure Model Deployment¶
After a model is optimized by the OpenVINO Model Optimizer, it’s deployed to target devices in the OpenVINO Intermediate Representation (OpenVINO IR) format. An optimized model is stored on edge device and is executed by the OpenVINO Runtime. ONNX and PDPD models can be read natively by OpenVINO Runtime as well.
Encrypting and optimizing model before deploying it to the edge device can be used to protect deep-learning models. The edge device should keep the stored model protected all the time and have the model decrypted in runtime only for use by the OpenVINO Runtime.
Loading Encrypted Models¶
The OpenVINO Runtime requires model decryption before loading. Allocate a temporary memory block for model decryption and use the
ov::Core::read_model method to load the model from a memory buffer. For more information, see the
ov::Core Class Reference Documentation.
std::vector<uint8_t> model_data, weights_data;
std::string password; // taken from an user
std::ifstream model_file("model.xml"), weights_file("model.bin");
// Read model files and decrypt them into temporary memory block
decrypt_file(model_file, password, model_data);
decrypt_file(weights_file, password, weights_data);
Hardware-based protection such as Intel Software Guard Extensions (Intel SGX) can be used to protect decryption operation secrets and bind them to a device. For more information, see the Intel Software Guard Extensions.
ov::Core::read_model to set model representations and weights respectively.
Currently there is no way to read external weights from memory for ONNX models. The
ov::Core::read_model(const std::string& model, const Tensor& weights) method should be called with
weights passed as an empty
Intel® Distribution of OpenVINO™ toolkit home page.
Model Optimizer Developer Guide.
For more information on Sample Applications, see the OpenVINO Samples Overview
For information on a set of pre-trained models, see the Overview of OpenVINO™ Toolkit Pre-Trained Models.
For IoT Libraries and Code Samples, see the Intel® IoT Developer Kit.