First Steps
Head over to Antigranular ↗ and click the top right button to login (or register) with your email, GitHub or Google.
Open the Getting Started Notebook ↗ and follow the steps to connect to our platform and run your code in our enclaves!
Explore the following API References, Guides and Core Concepts to learn more!
Guides
Working with Antigranular
The AG Python client and Jupyter extension can bring your script to life in a secure environment by using a specialised version of Python created by AG This Python version operates under restricted conditions, allowing only methods that guarantee differential privacy.
Read MoreUsing Private Pandas
AG provides a differentially private version of the pandas library, which lets users handle private data frames and series and perform various statistical analyses with differential privacy guarantees.
Read MoreUsing Private TensorFlow
TensorFlow Privacy is a Python library developed by Google that enables training of machine learning models with privacy guarantees, in particular through the implementation of differential privacy.
Read MoreUsing Private Opacus
Opacus is a library enabling differentially private training of PyTorch models. By adjusting the model's training process, Opacus ensures the model's outputs do not disclose individual data points from the training set.
Read MoreConcepts
What is Private Python?
Private Python is a specialised version of Python created by Oblivious. It is designed specifically for working with differentially private data, ensuring privacy protections are embedded at every step.
What is Differential Privacy?
Differential Privacy (DP) is a framework crafted to safeguard the privacy of individual data during statistical analyses. It achieves this by inserting controlled random noise into data queries, concealing any specific record's impact. This approach shields against re-identification and other privacy breaches, even when dealing with sensitive data.
What is a Privacy Budget?
Learn what is and how to manage your privacy budget. Epsilon (ϵ) and delta (δ) are the base parameters that quantify and manage privacy protection in differential privacy. All Competitions have a Privacy Budget. Each query made spends Epsilon from the Privacy Budget.
What are Enclaves?
Confidential Computing, synonymous with the terms 'Trusted Execution Environment' (TEE) or 'Secure Enclave', represents a significant leap in data security and privacy. It is a concept that is pushing the boundaries of what is possible in data protection, particularly in the realm of cloud computing.
API References
Pandas API
op_pandas is AG's implementation of the Pandas library. The op_pandas library allows you to import datasets and handle their data efficiently and privately.
Read MoreDiffprivlib API
The Diffprivlib library implements differential privacy techniques for various data analysis tasks. It can be viewed as a differentialy private version of scikit-learn, implementing the DP-equivalents of many of the sklearn models.
Read MoreOpenDP API
OpenDP is a powerful library for privacy-preserving data analysis. It provides a wide range of functions and methods to ensure the privacy of sensitive data while enabling a meaningful analysis.
Read MoreSmartNoise Synth API
SmartNoise-Synth is part of SmartNoise SDK and is built on OpenDP. It offers multiple differentially private synthesizers.
Read More