BastionLab

Daniel Huynh
Members Public

Rust: How We Built a Privacy Framework for Data Science

We could have built our privacy framework BastionLab in any language - Python, for example, which is data science’s beloved. But we chose Rust because of its efficiency and security features. Here are the reasons why we loved doing so, but also some challenges we encountered along the way.

Daniel Huynh
Members Public

How Python Data Science Libraries Can Be Hijacked (and What You Can Do About It)

Hackers can easily hijack the data science libraries you use every day and get full access to the datasets you are working with. Data owners need tools to prevent it from happening.

Charles Chudant
Members Public

Jupyter Notebooks Are Not Made for Sensitive Data Science Collaboration

When collaborating remotely on sensitive data, their usually amazing interactivity and flexibility need safeguards, or whole datasets can be extracted in a few lines of code.

Daniel Huynh
Members Public

Introducing BastionLab - A Simple Privacy Framework for Data Science Collaboration

BastionLab is a simple privacy framework for data science collaboration. It lets data owners protect the privacy of their datasets and enforces that only privacy-friendly operations are allowed on the data and anonymized outputs are shown to the data scientist.

Daniel Huynh
Members Public

Our Roadmap to Build a Simple Privacy Toolkit for Data Science Collaboration

One year and a half later, Mithril Security’s roadmap has transformed significantly, but our initial goal stayed the same: democratizing privacy in data science.

Daniel Huynh
Members Public

Introducing BastionAI, an Open-Source Privacy-Friendly AI Training Framework in Rust

Discover BastionAI, a Rust project for Confidential deep learning training. BastionAI leverages Confidential Computing and Differential Privacy to make AI training between multiple parties more privacy-friendly