CipherNet | Project introduces the concept of data

CipherNet is a Jupyter Notebook library. CipherNet has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

This Project introduces the concept of data hiding in distributed machine learning system. Data hiding prevents cloud services where the machine learning models are hosted/ deployed, to access the sensitive data we upload in the form of datasets. We talk briefly about how we achieve Data hiding. The core concepts of the project include Encryption techniques to encrypt the data, which are essential to the data hiding problem we are trying to solve. We use two popular datasets for Image recognition and classification, we encrypt the data based on the techniques we learned and train the model which in this case is a neural network. We build an architecture loosely based on the Arch net architecture of our base paper, which enables us to perform encryption methods on the data and also recognize and classify the data accordingly. With the rise in cloud server services, Encryption on the data and model will be essential for the progress of AI industry with safety, precaution and assurance that our data won’t be misused by some wrong entities.